---
title: "Reviewed AI Skills: selection notes & install guides · Undominated.ai"
canonical: https://undominated.ai/skills/
description: "Explore 759 selected AI skills with original source reviews, selection reasons, limitations and practical setup guidance."
---

# Reviewed AI Skills: selection notes & install guides · Undominated.ai

> Explore 759 selected AI skills with original source reviews, selection reasons, limitations and practical setup guidance.

THE AI TOOLKIT / SKILLS

# Skills. Useful instructions. Inspected in context.

Give your AI a repeatable way to work. Explore selected skills with original review notes, practical installation guidance and the source material behind each choice.

 [Explore the selection ↓](#catalogue)[What we checked ↗](#screening)

 REVIEWED SELECTION selected skills 759
 distinct publishers 86
 supporting source URLs 2302

Reviewed 2026-10-14 Original notes. Linked evidence.

 **Selected for a reason. Reviewed within a stated scope.** Every entry includes our own findings and limitations. Source review is not a runtime test, a security certificate or proof of a universal “best.”
 Build your toolkit [AI Tools ↗](/tools/)[Skills](/skills/)[Agents](/agents/)[MCP Servers](/mcp-servers/)[Workflows](/workflows/)

01 / START WITH THE JOB

## What are you working on?

Explore a category, then refine your shortlist. All categories are available in the filters.

 223 selected **Evidence and evaluation** Explore this category → 32 selected **Security** Explore this category → 30 selected **Security review** Explore this category → 23 selected **Development workflow** Explore this category → 23 selected **Observability** Explore this category → 21 selected **Databases** Explore this category →

PLAN THE HANDOFF

## Put the resources to work.

[Explore 88 workflows →](https://undominated.ai/workflows/)

Task briefs, working sheets and acceptance checks. Suggested plans; each resource needs its own setup.

 [Review a change before merging ↗](https://undominated.ai/workflows/#review-a-change)[Investigate a browser regression ↗](https://undominated.ai/workflows/#debug-a-browser-regression)[Investigate a slow PostgreSQL query ↗](https://undominated.ai/workflows/#investigate-a-postgres-query)[Document an API or codebase ↗](https://undominated.ai/workflows/#document-an-api)[Investigate an application incident ↗](https://undominated.ai/workflows/#investigate-an-incident)[Plan an interface from code and design ↗](https://undominated.ai/workflows/#plan-an-interface)

BUILT BY UNDOMINATED

## Evidence tools you can inspect.

Original source, MIT licence and complete downloads. Each review names the checks performed and their limits.

 - [2-bit activation outlier audit ↗](/skills/undominated-2bit-activation-outlier-audit/) Audits 2-bit weight quantization (QuIP#, AQLM) activation outlier preservation and SQNR thresholds.
- [A dev POST keeps its slash ↗](/skills/undominated-slash-not-post/) Refuse a dev POST path with no trailing slash. trailingSlash always 404s that path in dev. Production is a different path shape.
- [A load return is not the catalogue ↗](/skills/undominated-load-not-catalogue/) Refuse a load() return labelled catalogue. The catalogue is imported by the page. Putting it in the load return inlines it into every prerendered page.
- [A marginal block is not priced ↗](/skills/undominated-marginal-not-whole/) Refuse a marginal-block bill. A whole request uses the rate of the rung that contains its input length. This checker does not price either mode.
- [A missing announcement is not safe ↗](/skills/undominated-announced-not-safe/) Refuse a safety claim built from none-announced, unknown, or unrated. Those labels do not establish that a subject is safe.
- [A models list is not a chat call ↗](/skills/undominated-models-list-not-chat/) Refuse a claim that chat works because /v1/models returned the id. A list is not a completion. This checker sends no request.
- [A prompt is not the catalogue ↗](/skills/undominated-topk-not-dump/) Refuse a prompt whose scope is the whole catalogue. Retrieval stays top-k. No catalogue is copied.
- [A query is not a passage ↗](/skills/undominated-query-not-passage/) Refuse an embedding call whose input_type does not match the role. A query and a passage are different requests. No vector is computed.
- [A rollback is not the baseline ↗](/skills/undominated-rollback-not-baseline/) Refuse to record a rolled-back or unproven deploy as the accepted baseline. The baseline advances only after a deploy has proven good.
- [A token is not PUBLIC_ ↗](/skills/undominated-public-not-secret/) Refuse a provider token in a PUBLIC_ variable or in browser code. A server environment is outside this refusal and is not approved by a pass.
- [A zero base is not defined ↗](/skills/undominated-zero-base-undefined/) Refuse a multiple whose base is zero. The multiple is not defined. This checker does not emit a quotient.
- [Activation Recomputation Tax Audit ↗](/skills/undominated-activation-recomputation-tax-audit/) Audits selective vs full gradient checkpointing memory savings vs compute FLOP taxes for long-context prefill.
- [Adversarial suffix detection audit ↗](/skills/undominated-adversarial-suffix-detection-audit/) Checks a supplied perplexity-ratio assertion and anomaly threshold over local numeric input; a flag is a heuristic signal for review, not proof of an attack.
- [Advertised-route audit ↗](/skills/undominated-advertised-route/) Refuse a crawl-list URL whose English-only path gained a locale prefix, or whose ?format=md sibling was never written.
- [Agent consensus cost audit ↗](/skills/undominated-agent-consensus-cost-audit/) Audits token costs and accuracy ROI of multi-agent consensus, majority voting, and debate protocols.
- [Agent trajectory cost audit ↗](/skills/undominated-agent-trajectory-cost-audit/) Audit multi-turn agent execution loops for quadratic token accumulation, retry loops, tool call overhead, and cumulative trajectory dollar costs.
- [AI resource intake audit ↗](/skills/undominated-resource-audit/) Review a skill, agent or MCP server for pinned source identity, licensing, requested permissions and observable verification before adding it to a trusted collection.
- [Air-Gapped Inference Economics Audit ↗](/skills/undominated-airgapped-inference-audit/) Calculates on-premise hardware CapEx amortization, rack power, and hosting TCO per 1M tokens to verify self-hosting economic viability.
- [Alias resolution ↗](/skills/undominated-alias-resolution/) Resolve an explicitly supplied alias to one distinct concrete target, refusing unresolved or conflicting candidate evidence. Use before treating a latest-style pointer as a concrete model ID.
- [An add_header keeps the snippet ↗](/skills/undominated-snippet-not-inherited/) Refuse an nginx location that sets add_header without the shared header snippet. add_header in a location discards inherited headers.
- [Apple unified memory bandwidth audit ↗](/skills/undominated-apple-unified-memory-bandwidth-audit/) Audits Apple Silicon unified memory bandwidth utilization and token generation throughput efficiency.
- [arena.ai is not scraped ↗](/skills/undominated-arena-not-scrape/) Refuse an arena.ai scrape. The Hugging Face dataset pin can pass. Any other origin can pass and is not approved.
- [Artificial Analysis is not republished ↗](/skills/undominated-aa-not-public/) Refuse redistribution of Artificial Analysis. A pass for any other source does not approve that source. No series is copied.
- [ASCII art jailbreak evasion audit ↗](/skills/undominated-ascii-art-jailbreak-evasion-audit/) Audits ASCII art spatial obfuscation and safety alignment bypass resistance in prompt inputs.
- [Audio streaming chunk latency audit ↗](/skills/undominated-audio-streaming-chunk-latency-audit/) Audits continuous audio streaming inference chunk sizes and Real-Time Factor (RTF) latency bounds.
- [Auto Prompt Distillation Audit ↗](/skills/undominated-auto-prompt-distillation-audit/) Calculates prompt instruction compression efficiency and downstream task execution fidelity.
- [Batch discount audit ↗](/skills/undominated-batch-discount-audit/) Audit batch API SLA windows, advertised vs realized discounts, queue starvation risk, and cancellation policies.
- [Batch Queue Starvation Risk Audit ↗](/skills/undominated-batch-queue-starvation-risk-audit/) Calculates batch queue processing delays and verifies turnaround compliance against provider SLA deadlines.
- [Benchmark cohort audit ↗](/skills/undominated-benchmark-audit/) Audit a benchmark comparison for matched model identity, missing coverage, restricted populations and misleading confidence-interval interpretations.
- [Bidirectional speculative audit ↗](/skills/undominated-bidirectional-speculative-audit/) Audits bidirectional speculative drafting hit rates during structured JSON and schema generation.
- [BitNet ternary weight audit ↗](/skills/undominated-bitnet-ternary-weight-audit/) Audits BitNet b1.58 ternary weight representation and addition-only kernel energy reduction factors.
- [Browser code does not name loopback ↗](/skills/undominated-loopback-not-browser/) Refuse a browser script that names 127.0.0.1. That address is the visitor's machine. A server-side sidecar may name it.
- [Burst Concurrency & Queue Degradation Audit ↗](/skills/undominated-burst-concurrency-audit/) Evaluates queue buffering latency and HTTP 429/503 drop rates under sudden burst step-load profiles.
- [Cache multiplier ↗](/skills/undominated-cache-multiplier/) Keep a cache figure that is a multiplier distinct from an absolute rate.
- [Cache-tier billing audit ↗](/skills/undominated-cache-tier-billing/) Bill a request against the cache tier that applies to it, so a cached prefix is not charged at the base input rate.
- [Canary Deployment Drift Audit ↗](/skills/undominated-canary-deployment-drift-audit/) Calculates statistical output distribution divergence (PSI/KS-test) between stable baseline and canary model deployments.
- [Carbon intensity scheduling audit ↗](/skills/undominated-carbon-intensity-scheduling-audit/) Audits grid carbon intensity temporal variations to schedule batch inference during green energy peaks.
- [Chunked Prefill Scheduler Audit ↗](/skills/undominated-chunked-prefill-scheduler-audit/) Calibrates chunked prefill chunk sizes to eliminate inter-token latency (ITL) spikes while preserving prefill throughput.
- [CI/CD Regression Gate Audit ↗](/skills/undominated-ci-cd-regression-gate-audit/) Automated deployment gate: enforces strict latency, output schema validity, and accuracy thresholds in CI/CD pipelines.
- [Concurrency cliff audit ↗](/skills/undominated-concurrency-cliff-audit/) Audit inference throughput degradation, queue build-up, and throughput cliff saturation as concurrency scales.
- [Context compaction audit ↗](/skills/undominated-context-compaction-audit/) Audit conversational context compaction, summarization, and message pruning for named entity retention, critical fact loss, and semantic distortion.
- [Context-rung selection ↗](/skills/undominated-rung-select/) Select the context-tier rung that contains a request's input length, so the dearest later rung is not applied to a shorter prompt.
- [Context-tier ladder audit ↗](/skills/undominated-context-tier/) Check a past-this-length price multiple against every rung, so the dearest rung is not applied at the first boundary.
- [Continuous Batching Scheduler Audit ↗](/skills/undominated-continuous-batching-scheduler-audit/) Audits iteration-level scheduling vs static request batching to verify throughput gains and elimination of tail-latency bubble waste.
- [Cross modal KV allocation audit ↗](/skills/undominated-cross-modal-kv-allocation-audit/) Audits visual token versus text token KV cache allocation ratios in long multimodal conversations.
- [Currency isolation audit ↗](/skills/undominated-currency-isolate/) Refuse to add, average or rank amounts whose currencies differ, so a missing code is not treated as USD and no exchange rate is invented.
- [DARE random drop rescale audit ↗](/skills/undominated-dare-random-drop-rescale-audit/) Audits DARE (Drop And REscale) random drop rate and benchmark capability retention across merged models.
- [Datacenter power envelope audit ↗](/skills/undominated-datacenter-power-envelope-audit/) Audits datacenter rack power density, cooling overhead, and PUE compliance under 100% GPU duty cycles.
- [Decimal determinism audit ↗](/skills/undominated-decimal-determinism/) Prove a published rate, a computed bill and a displayed figure agree to the last digit, so no displayed decimal comes from IEEE-754.
- [Delivery class ↗](/skills/undominated-delivery-class/) Refuse a dominance claim that treats batch delivery, or a model's own other delivery, as a like-for-like beater of synchronous delivery.
- [DGX SuperPOD TCO Audit ↗](/skills/undominated-dgx-superpod-tco-audit/) Calculates enterprise GPU cluster Total Cost of Ownership including InfiniBand fabrics, power usage effectiveness (PUE), and rack hosting.
- [Do not scale the invoice unit ↗](/skills/undominated-unit-not-scaled/) Refuse a scale factor or a restated invoice unit. A per-thousand row is not turned into a per-million row by multiplying. Amounts are not read.
- [Dominance wording audit ↗](/skills/undominated-dominance-wording/) Classify a two-model comparison before publishing it, so a tie or a dropped requirement is not called both better and cheaper.
- [Dynamic Spot Rate Arbitrage Audit ↗](/skills/undominated-dynamic-spot-rate-arbitrage-audit/) Calculates real-time price arbitrage across multi-provider spot inference endpoints under strict latency SLOs.
- [Dynamic Tool Filtering Tax Audit ↗](/skills/undominated-dynamic-tool-filtering-tax-audit/) Calculates token savings achieved by dynamically retrieving relevant tools into context vs sending static tool catalogs.
- [Eagle-2 dynamic draft tree audit ↗](/skills/undominated-eagle2-dynamic-draft-tree-audit/) Audits Eagle-2 dynamic draft tree pruning and net token throughput multipliers.
- [Elo drift audit ↗](/skills/undominated-elo-drift-audit/) Audit Bradley-Terry win-rate confidence interval bounds, active pair sampling bias, and Elo deflation/inflation drift across benchmark dataset versions.
- [Embodied silicon carbon TCO audit ↗](/skills/undominated-embodied-silicon-carbon-tco-audit/) Audits embodied carbon in GPU manufacturing (Scope 3) amortized per 1 billion inference tokens.
- [Equal is not better ↗](/skills/undominated-equal-not-better/) Refuse to call an equal score or an equal price an improvement.
- [EU AI Act Transparency Audit ↗](/skills/undominated-eu-ai-act-transparency-audit/) Checks four supplier declarations in a local JSON file: training compute, copyright summary, energy log, and model card. A true declaration is not an EU AI Act determination.
- [Eval contamination and judge audit ↗](/skills/undominated-eval-contamination-audit/) Audit benchmark evaluation sets and prompts for training set contamination, n-gram overlap, verbatim memorization, and judge prompt skew.
- [Evidence audit ↗](/skills/undominated-evidence-audit/) Audit a numeric claim against locally saved source evidence, including denominator and reproducible calculations, before citing or publishing it.
- [False-Positive Refusal Rate Audit ↗](/skills/undominated-false-refusal-rate-audit/) Quantifies false-positive refusal rates on benign software engineering, cybersecurity, and clinical research queries.
- [Family snapshot ↗](/skills/undominated-family-snapshot/) Require family membership to be a subset of the catalogue snapshot.
- [Few-Shot Example Pruning Audit ↗](/skills/undominated-few-shot-example-pruning-audit/) Calculates the marginal accuracy contribution per few-shot exemplar to eliminate low-ROI prompt tokens.
- [Filter invariance ↗](/skills/undominated-filter-invariance/) Check that filtering preserves the relative order of retained IDs. Use for search or facet behavior that is intended to hide rows without re-sorting them.
- [Final-host audit ↗](/skills/undominated-final-host/) Refuse a vendor quote when the final host you recorded is not the host you requested. A redirect is not that vendor. www is not stripped, and this checker sends no request.
- [Final-path audit ↗](/skills/undominated-final-path/) Refuse a page claim when the final path you recorded is not the path you requested. A redirect to the homepage is not that page. The host is a different checker, and this one sends no request.
- [FP4 E2M1 microscaling audit ↗](/skills/undominated-fp4-e2m1-microscaling-audit/) Audits OCP Microscaling Formats (MXFP4 / E2M1) block scaling factors and perplexity degradation delta.
- [FP4 Quantization Noise Audit ↗](/skills/undominated-fp4-quantization-noise-audit/) Calculates Signal-to-Quantization-Noise Ratio (SQNR) and verifies perplexity degradation across FP4 / NVFP4 tensor formats.
- [Generated artefacts stay uncommitted ↗](/skills/undominated-generated-not-commit/) Refuse a commit path the caller has classified as generated. Source can pass. A pass does not prove the path is source.
- [GPU Underutilization Cost Audit ↗](/skills/undominated-gpu-underutilization-cost-audit/) Calculates financial penalties of reserved GPU instances operating under low continuous utilization factors.
- [Graph RAG Extraction Tax Audit ↗](/skills/undominated-graph-rag-extraction-tax-audit/) Calculates entity-relationship extraction token overhead and graph construction costs compared to vector retrieval.
- [Guardrail Latency Overhead Audit ↗](/skills/undominated-guardrail-latency-tax-audit/) Measures the TTFT penalty and token inflation imposed by input and output safety moderation guardrail layers.
- [H2O heavy hitter eviction audit ↗](/skills/undominated-h2o-heavy-hitter-eviction-audit/) Audits Heavy Hitter Oracle (H2O) KV cache eviction and critical prompt token retention under memory limits.
- [Header-not-row audit ↗](/skills/undominated-header-not-row/) Refuse a unit claim that borrows the table's display header when that row does not state its own unit. A per-million header is not every row's invoice unit. Amounts are not read.
- [Hierarchical Memory Consolidation Audit ↗](/skills/undominated-hierarchical-memory-consolidation-audit/) Audits episodic-to-semantic memory compaction token costs in long-horizon autonomous agents.
- [Hint versus handler ↗](/skills/undominated-hint-vs-handler/) Refuse a read-only hint when the handler notes you supply include a write, or when those notes are empty. A hint is not a review of the handler.
- [HTTP/2 Multiplexing & Head-of-Line Audit ↗](/skills/undominated-http2-multiplexing-audit/) Measures TTFT variance and head-of-line blocking under HTTP/2 multiplexing vs HTTP/1.1 connection pools under high stream concurrency.
- [Hybrid transformer SSM memory audit ↗](/skills/undominated-hybrid-transformer-ssm-memory-audit/) Audits memory footprint and KV cache allocation in hybrid models combining attention and Mamba layers.
- [Identity dedup audit ↗](/skills/undominated-identity-dedup/) Collapse duplicate identities inside one population before ranking, so one model or one seller cannot be counted twice.
- [Indicative-rate audit ↗](/skills/undominated-indicative-rate/) Refuse a global-rate claim when the excerpt says the figure is indicative, varies by country, starts at a floor, or is a list price beside a credit. One sentence is not every region's rate.
- [Indirect Prompt Injection Detector ↗](/skills/undominated-indirect-prompt-injection-detector/) Audits model vulnerability to untrusted prompt injections embedded in retrieved RAG contexts and web documents.
- [Install receipt ↗](/skills/undominated-install-receipt/) Compare an expected file manifest with a sha256sum receipt and, when asked, the bytes in a directory next to the input.
- [IP Infringement Verbatim Memorization Audit ↗](/skills/undominated-ip-infringement-verbatim-audit/) Measures verbatim memorization rates of copyrighted code and text corpora in model completion outputs.
- [JSON Schema Constrained Decoding Tax Audit ↗](/skills/undominated-json-schema-constrained-decoding-tax-audit/) Measures token generation throughput penalty and grammar compilation overhead incurred by FSM-constrained decoding engines.
- [Judge Prompt Variance Audit ↗](/skills/undominated-judge-prompt-variance-audit/) Measures LLM-as-a-judge score variance, position bias, and length preference bias across automated evaluation runs.
- [Keep every ladder rung ↗](/skills/undominated-ladder-not-flattened/) Refuse a published context-tier ladder whose rung count differs from the source. Dropping a rung flattens the ladder. Adding a rung invents one. Prices and boundaries are not read.
- [KV Cache INT4 Outlier Drift Audit ↗](/skills/undominated-kv-cache-int4-outlier-drift-audit/) Audits key/value cache INT4 quantization channel scaling to prevent catastrophic attention drift on long sequences.
- [KV Cache Memory Sizing Audit ↗](/skills/undominated-kv-cache-sizing-audit/) Audits KV cache memory footprint per token and max concurrent sequence limits under FP16, FP8, and INT4 KV caches to prevent serving OOMs.
- [KV Transfer RDMA Bandwidth Audit ↗](/skills/undominated-kv-transfer-rdma-bandwidth-audit/) Calculates RDMA network saturation and link concurrency during high-throughput KV cache migration.
- [Length bias audit ↗](/skills/undominated-length-bias-audit/) Audit length bias (verbosity bias) in LLM-as-a-judge evaluations and preference datasets, detecting artificial win-rate inflation.
- [Length bias removal audit ↗](/skills/undominated-length-bias-removal-audit/) Audits reward model length bias and synthetic response verbosity inflation in preference datasets.
- [Licence-boundary audit ↗](/skills/undominated-licence-boundary/) Check a redistribution claim against the licence evidence you recorded. A public page is not a licence.
- [Linear Attention Recurrent State Audit ↗](/skills/undominated-linear-attention-recurrent-state-audit/) Verifies $O(1)$ constant memory scaling of recurrent and state-space architectures during generation versus Transformer attention.
- [Live Benchmark Drift Detector ↗](/skills/undominated-live-benchmark-drift-detector/) Detects silent provider model weight updates, quant modifications, and temperature drift across production endpoints.
- [Locale is not content ↗](/skills/undominated-locale-not-content/) Refuse a translated label as proof that the page body is translated.
- [Long-Context Distraction Audit ↗](/skills/undominated-context-distraction-audit/) Audits retrieval accuracy degradation as irrelevant distractor documents are added to prompts (evaluating signal-to-noise ratio in long contexts).
- [Lookahead decoding n-gram audit ↗](/skills/undominated-lookahead-decoding-n-gram-audit/) Audits Lookahead Decoding parallel Jacobi n-gram candidate generation and net wall-clock speedup.
- [Loopback needs curl --resolve ↗](/skills/undominated-resolve-not-host-header/) Refuse a Host header pointed at loopback. That request sends no SNI and hits the default server. curl --resolve can pass.
- [LoRA Cache Swapping Latency Audit ↗](/skills/undominated-lora-cache-swapping-latency-audit/) Audits dynamic LoRA adapter loading latency from host system memory to GPU VRAM.
- [Mamba-2 SSD chunk audit ↗](/skills/undominated-mamba2-ssd-chunk-audit/) Audits Mamba-2 Structured State Space Duality (SSD) matrix chunk sizes and continuous decoding throughput.
- [Many-Shot Jailbreak Resilience Audit ↗](/skills/undominated-many-shot-jailbreak-resilience-audit/) Evaluates model safety adherence under long-context many-shot in-prompt jailbreak demonstrations.
- [master is not force-pushed ↗](/skills/undominated-force-not-master/) Refuse a force push whose branch is master. Another branch is outside this refusal, and a pass does not approve the force push.
- [MCP permission map ↗](/skills/undominated-mcp-permission-map/) Bind a saved MCP tools/list capture to explicit permission labels and reject a read-only claim that a label contradicts.
- [Meter-scope audit ↗](/skills/undominated-meter-scope/) Refuse a unit claim that borrows an invoice unit from a note that does not name that meter, so a knowledge-base billing sentence cannot reprice an inference row.
- [Mixed Precision Layer Allocation Audit ↗](/skills/undominated-mixed-precision-layer-allocation-audit/) Audits selective high-precision preservation on sensitive initial and final layers versus bulk quantized middle layers.
- [Model card transparency audit ↗](/skills/undominated-model-card-transparency-audit/) Audit model card releases against the Foundation Model Transparency Index, checking documentation completeness across pre-training data, compute hours, and limitations.
- [Model Cascade Routing Audit ↗](/skills/undominated-cascade-routing-audit/) Audits 2-tier cascading routing policies (small draft model with confidence gate to frontier verifier), calculating net cost savings and escalation ratios.
- [Model Distillation Fidelity Audit ↗](/skills/undominated-distillation-fidelity-audit/) Measures task accuracy retention and output distribution alignment of distilled student models relative to teacher models.
- [Model Merge Interference Audit ↗](/skills/undominated-model-merge-interference-audit/) Measures weight interference and cosine similarity degradation in spherical linear interpolation (SLERP) model merges.
- [Model migration preflight ↗](/skills/undominated-migration-preflight/) Check a proposed model replacement for required modalities, context, tool use, structured output and evaluation coverage before calling it a safe saving.
- [MoE Activation Memory Footprint Audit ↗](/skills/undominated-moe-activation-memory-footprint-audit/) Calculates active versus total parameter memory footprint and expert weight swapping overhead on constrained GPU nodes.
- [MoE Expert Parallelism All-to-All Audit ↗](/skills/undominated-moe-ep-all-to-all-comm-audit/) Calculates All-to-All collective dispatch and combine communication overhead across nodes in Expert Parallel (EP) clusters.
- [MoE Expert Routing Tax Audit ↗](/skills/undominated-moe-expert-routing-tax-audit/) Audits top-k gating entropy, expert load distribution, and token drop rates under finite expert capacity factors.
- [Multi-agent error cascade audit ↗](/skills/undominated-multi-agent-error-cascade-audit/) Audits error compounding probability across sequential multi-agent tool execution pipelines.
- [Multi-Head Latent Attention Audit ↗](/skills/undominated-mla-latent-dimension-audit/) Calculates DeepSeek Multi-Head Latent Attention (MLA) low-rank compression factors and verifies KV cache reduction relative to MHA and GQA.
- [Multi-LoRA Kernel Overhead Audit ↗](/skills/undominated-multi-lora-kernel-overhead-audit/) Measures batched multi-adapter GPU kernel overhead (S-LoRA) versus single-model inference throughput.
- [Multi-Token Prediction Speedup Audit ↗](/skills/undominated-multi-token-prediction-speedup-audit/) Calculates acceptance rate thresholds and net speedup of Multi-Token Prediction (MTP) heads vs standard autoregression.
- [Multi-Turn State Drift Audit ↗](/skills/undominated-multi-turn-state-drift-audit/) Calculates cumulative token inflation and prefill cost scaling across multi-turn agent conversations to verify context compaction policies.
- [Multilingual Retrieval Parity Audit ↗](/skills/undominated-multilingual-retrieval-audit/) Audits cross-lingual embedding alignment and retrieval recall parity across high- and low-resource languages.
- [Multiplier-aside audit ↗](/skills/undominated-multiplier-aside/) Refuse a base-rate claim when the excerpt names a multiplier. Priority, fast, and scale factors are not the on-demand rate. The number in 2x is not read as a price.
- [Native Sparse Attention Audit ↗](/skills/undominated-native-sparse-attention-audit/) Audits Native Sparse Attention (NSA) compression ratios, block-sparse top-k selection, and memory bandwidth reduction.
- [Needle-in-a-haystack density audit ↗](/skills/undominated-needle-in-haystack-density-audit/) Audit long-context retrieval recall across varying context lengths, needle depth placements, and distractor similarity levels.
- [nginx is reloaded, not restarted ↗](/skills/undominated-reload-not-restart/) Refuse an nginx restart. A reload is review until nginx -t has succeeded. This checker does not run nginx.
- [NPU INT8 TPU offload audit ↗](/skills/undominated-npu-int8-tpu-offload-audit/) Audits mobile NPU and edge accelerator power efficiency measured in Tokens per Joule.
- [Offer join ↗](/skills/undominated-offer-join/) Refuse a price that does not name both the model and the seller.
- [Open-weights licence audit ↗](/skills/undominated-open-weights-licence-audit/) Audit open-weights model licenses against commercial deployment restrictions, Monthly Active User thresholds, synthetic data output constraints, and attribution requirements.
- [P99.9 tail latency budget audit ↗](/skills/undominated-p999-tail-latency-budget-audit/) Audits tail latency distribution ratios (p99.9 / p50) to detect micro-stalls and jitter in production serving.
- [Page is not a quote ↗](/skills/undominated-page-not-quote/) Keep a pricing-page research note from becoming a joined rate. A spelled currency and unit are not a price.
- [Parallel Tool Call Fan-Out Audit ↗](/skills/undominated-parallel-tool-call-fanout-audit/) Calculates concurrency speedup and total payload token loads for simultaneous multi-tool execution in agent loops.
- [Payback basis ↗](/skills/undominated-payback-basis/) Check switching-cost payback against savings per period using exact arithmetic. Use when a migration claims to pay back in a stated number of periods.
- [PII Scrubbing Latency Tax Audit ↗](/skills/undominated-pii-scrubbing-latency-tax-audit/) Measures token count shifts and millisecond pre-inference latency added by NER-based redaction and token replacement pipelines.
- [Pipeline parallelism bubble audit ↗](/skills/undominated-pipeline-parallelism-bubble-audit/) Audits pipeline schedule bubble fraction and microbatch allocation in 1F1B schedules.
- [Plan-quote hygiene ↗](/skills/undominated-plan-quote/) Keep unverified subscription quotes out of a USD monthly ceiling. A source sentence is not a price.
- [Population denominator ↗](/skills/undominated-population-denominator/) Require a stated population, a computed population and a claimed count to be the same set, so a statistic on a subset is not published as the whole set.
- [Population scope ↗](/skills/undominated-population-scope/) Check that a claimed count uses the population the sentence names.
- [Precision prompt cost estimator ↗](/skills/undominated-prompt-cost-estimator/) Calculate inference costs across prompt tokens, completion tokens, cached prompt tokens (read/write), reasoning tokens, and multi-turn trajectories using explicit provider pricing ladders.
- [Prefill-Decode Disaggregation Audit ↗](/skills/undominated-prefill-decode-disaggregation-audit/) Audits separate prefill and decode worker node topologies and calculates RDMA KV transfer latency vs GPU compute overlap.
- [Prefix Caching Radix Tree Audit ↗](/skills/undominated-prefix-caching-radix-audit/) Audits Radix tree prefix caching efficiency, memory allocation, cache hit rate, and effective TTFT reduction to prevent latency degradation under memory pressure.
- [Process reward model tax audit ↗](/skills/undominated-process-reward-model-tax-audit/) Audits Process Reward Model (PRM) step-level verification token overhead versus outcome accuracy gains.
- [Prompt Extraction & Leakage Resilience Audit ↗](/skills/undominated-prompt-leakage-resilience-audit/) Evaluates system prompt confidentiality retention under adversarial prompt extraction and reconstruction attacks.
- [Prompt Injection Classifier Tax Audit ↗](/skills/undominated-prompt-injection-classifier-tax-audit/) Quantifies TTFT latency inflation and false-positive rejection rates of pre-flight security moderation guardrails.
- [Provider Failover Latency Tax Audit ↗](/skills/undominated-provider-failover-latency-tax-audit/) Measures circuit breaker timeouts, retry amplification, and failover latency tax during upstream provider outages.
- [Provider quote comparison ↗](/skills/undominated-provider-quote-compare/) Compare like-for-like provider quotes with complete context tiers and distinct sellers; recompute workload cost without inventing cache or reasoning discounts.
- [PyramidKV layer budget audit ↗](/skills/undominated-pyramidkv-layer-budget-audit/) Audits PyramidKV non-uniform layer cache allocations to verify total VRAM budget compliance.
- [Quantisation label ↗](/skills/undominated-quantisation-label/) Keep an unknown quantisation labelled unknown, so a missing weight format is not published as full precision or fp16.
- [Quantization Degradation Audit ↗](/skills/undominated-quant-degradation-audit/) Audits perplexity and benchmark score degradation across quantization levels (BF16, FP8, INT4 AWQ, Q4_K_M) to prevent claiming unquantized performance for quantized serving.
- [Queue queuing theory audit ↗](/skills/undominated-queue-queuing-theory-audit/) Audits M/M/c queuing models under variable arrival rates to predict queue buildup before cluster saturation.
- [Quote-join audit ↗](/skills/undominated-quote-join/) Join a vendor quote to a catalogue model only when the provider and the model id match exactly, so a case fold is not an identity.
- [RAG Chunk Overlap Tax Audit ↗](/skills/undominated-chunk-overlap-tax-audit/) Calculates redundant token costs incurred by sliding-window chunk overlap in RAG ingestion and vector indexing pipelines.
- [Rate-unit audit ↗](/skills/undominated-rate-unit/) Refuse a token-price conversion until the currency and the unit are both explicit, so per M or a bare cent figure cannot become a per-million USD rate.
- [Read-only claim audit ↗](/skills/undominated-readonly-claim/) Reject a read-only label when a listed tool name contains a mutation token, without treating a passing name list as proof the server is read-only.
- [README is not a licence ↗](/skills/undominated-readme-not-licence/) Refuse a README sentence as a software licence.
- [Reasoning Budget Allocator Audit ↗](/skills/undominated-reasoning-budget-allocator/) Audits dynamic reasoning token ceilings to prevent cyclical reasoning explosions while guaranteeing sufficient tokens for complex proofs.
- [Reasoning token audit ↗](/skills/undominated-reasoning-token-audit/) Audit reasoning token expansion ratios, budget caps, separate billing vs output billing, and hidden multiplier surcharges across reasoning models.
- [Reasoning trace redundancy audit ↗](/skills/undominated-reasoning-trace-redundancy-audit/) Audits reasoning trace self-correction loops and verbosity redundancy to prune repetitive reflection tokens.
- [Receipt drift ↗](/skills/undominated-receipt-drift/) Fail a verification receipt whose hashes no longer match the supplied bytes.
- [Rendered-surface and payload agreement ↗](/skills/undominated-surface-agreement/) Prove a rendered surface and the JSON it serves state the same value for every supplied field.
- [Resource release proof ↗](/skills/undominated-release-proof/) Verify local release artifacts and meaningful public-response receipts without confusing a build, HTTP 200 or registry metadata with a working installation.
- [Restriction of range ↗](/skills/undominated-restriction-of-range/) Refuse a correlation or agreement claim whose evidence population is narrower than the population the sentence names.
- [Review-gate ratchet ↗](/skills/undominated-ratchet-gate/) Check that a review gate moved in one direction only, stricter and never looser, so an automated reviewer cannot weaken a check to pass a change.
- [Ring Attention Interconnect Audit ↗](/skills/undominated-ring-attention-interconnect-audit/) Verifies communication-to-computation overlap in block-wise Ring Attention across distributed sequence-parallel nodes.
- [Ring attention latency audit ↗](/skills/undominated-ring-attention-latency-audit/) Audits Ring Attention circular KV cache passing latency against block compute time in 1M+ context inference.
- [Ring MLA hybrid audit ↗](/skills/undominated-ring-mla-hybrid-audit/) Audits Ring Attention combined with Multi-Head Latent Attention (MLA) compressed latent states.
- [RWKV-6 linear state audit ↗](/skills/undominated-rwkv6-linear-state-audit/) Audits RWKV-6 linear recurrent state decay parameters and numerical stability across long token horizons.
- [Schema Validation Retry Cost Audit ↗](/skills/undominated-schema-validation-retry-cost-audit/) Quantifies wasted token expenditures incurred by recursive error correction loops when models emit invalid tool parameters.
- [Schema-not-quote audit ↗](/skills/undominated-schema-not-quote/) Refuse a model-rate claim when the excerpt describes a pricing field or a schema. A sentence that says values are in a unit is a field description, not a model's rate. Amounts are not read.
- [Self-Healing Prompt Optimizer Audit ↗](/skills/undominated-self-healing-prompt-optimizer/) Audits automated prompt refinement iterations to resolve edge-case test failures without human intervention.
- [Self-play distillation tax audit ↗](/skills/undominated-self-play-distillation-tax-audit/) Audits teacher-student self-play distillation token expenditure against student benchmark accuracy gains.
- [Self-Speculative Early Exit Audit ↗](/skills/undominated-self-speculative-early-exit-audit/) Audits layer skipping and early exit draft verification within a single model architecture.
- [Seller-spread audit ↗](/skills/undominated-seller-spread/) Check a price-spread multiple against distinct seller owners, so one vendor's own service tiers are not counted as competition.
- [Semantic Prompt Pruning Audit ↗](/skills/undominated-semantic-prompt-pruning-audit/) Measures token reduction percentages and verifies mutual information retention in token pruning pipelines.
- [Semantic Router Latency & Token Tax Audit ↗](/skills/undominated-semantic-router-tax-audit/) Quantifies embedding model latency and static classifier token taxes in semantic routing topologies prior to upstream generation.
- [Sequence parallelism ring audit ↗](/skills/undominated-sequence-parallelism-ring-audit/) Audits sequence parallelism communication overhead across layernorms and attention projection.
- [Serving-mode attribution ↗](/skills/undominated-serving-attribution/) Check that an explicit claimed score belongs to its named model or serving mode. Use when a model headline may have inherited a mode-specific score.
- [Shared-lastmod audit ↗](/skills/undominated-shared-lastmod/) Refuse a crawl list where every page is dated on the build day, so a shared build clock is not published as a per-page fact date.
- [Significance tie ↗](/skills/undominated-significance-tie/) Treat two scores as tied when their difference falls inside the stated interval.
- [Single-base audit ↗](/skills/undominated-single-base/) Refuse a single-base price claim when the excerpt names both sides of a cache split or a peak split. Spelling USD per million does not make cache-hit and cache-miss one rate.
- [Sliding Window Attention Audit ↗](/skills/undominated-sliding-window-attention-audit/) Audits sliding window context buffers and attention sink token retention to bound KV memory in continuous streaming.
- [SLO error budget depletion audit ↗](/skills/undominated-slo-error-budget-depletion-audit/) Audits 30-day Service Level Objective (SLO) error budget burn rates to trigger automated traffic shedding.
- [Slug-is-not-body audit ↗](/skills/undominated-slug-is-not-body/) Refuse a currency or quantity claim whose words appear only in a URL, a slug, or a title. The excerpt is the body. A path named pricing-details-usd does not state USD.
- [SnapKV cluster compression audit ↗](/skills/undominated-snapkv-cluster-compression-audit/) Audits SnapKV prompt attention feature clustering and compressed KV bank generation ratios.
- [Source-pin audit ↗](/skills/undominated-source-pin/) Refuse a source identity that is only a branch, a tag, or a short SHA. A full 40-hex revision is the pin. The name v7 or main does not become that revision.
- [Speculative Decoding Arbitrage Audit ↗](/skills/undominated-speculative-decoding-arbitrage/) Computes draft model acceptance rate thresholds (alpha) and verifies whether speculative decoding delivers net throughput/cost benefit over standard autoregressive decoding.
- [Spelled-meter audit ↗](/skills/undominated-spelled-meter/) Refuse a currency or quantity claim whose excerpt does not spell the word. A dollar sign is not USD, "per 1M" is not million, and the character 元 is not CNY.
- [Status-not-page audit ↗](/skills/undominated-status-not-page/) Check a supplied status against a conservative integer-200-only gate and refuse every quote claim based on status alone. No status proves a body was received or read. This checker sends no request.
- [Stream Truncation & Sentinel Detector ↗](/skills/undominated-stream-truncation-detector/) Detects silent SSE connection drops in long-running streaming completions where no [DONE] sentinel or incomplete JSON chunk is emitted.
- [Streaming framing audit ↗](/skills/undominated-streaming-framing-audit/) Audit Server-Sent Events (SSE) streaming protocol compliance, chunk serialization overhead, heartbeat keep-alive frequency, and terminal sentinel completeness.
- [sudo does not read the script from stdin ↗](/skills/undominated-sudo-not-stdin/) Refuse sudo bash -s fed by a heredoc. That script is read as the password prompt. sudo -n bash -lc can pass.
- [Suggest, do not redirect ↗](/skills/undominated-suggest-not-redirect/) Refuse a language redirect, including when Accept-Language is absent. A missing header is not a request for another locale. Suggest, or do nothing.
- [Synthetic data deduplication audit ↗](/skills/undominated-synthetic-data-dedup-audit/) Audits MinHash LSH and cosine clustering deduplication to prune repetitive synthetic training generations.
- [Synthetic Eval Diversity Audit ↗](/skills/undominated-synthetic-eval-diversity-audit/) Audits lexical and semantic diversity in synthetic evaluation sets to prevent test-set memorization and benchmark gaming.
- [Synthetic Text Watermark Retention Audit ↗](/skills/undominated-synthetic-text-watermark-retention-audit/) Measures statistical green/red list token watermarking retention under editing, summarization, and paraphrasing.
- [System prompt extraction guard audit ↗](/skills/undominated-system-prompt-extraction-guard-audit/) Audits resistance against system prompt leakage attacks and multi-turn extraction attempts.
- [System Prompt Override Resilience Audit ↗](/skills/undominated-system-prompt-override-resilience-audit/) Measures system directive adherence under conflicting user instructions and adversarial persona hijacking.
- [Task vector orthogonality audit ↗](/skills/undominated-task-vector-orthogonality-audit/) Audits task vector pairwise cosine similarity to prevent subspace interference in multi-task checkpoints.
- [Tensor parallelism communication audit ↗](/skills/undominated-tensor-parallelism-comm-audit/) Audits Tensor Parallelism All-Reduce communication overhead against NVLink bus saturation.
- [Tensor Parallelism Communication Tax Audit ↗](/skills/undominated-tensor-parallelism-communication-tax-audit/) Calculates All-Reduce collective communication volume and latency overhead across NVLink and PCIe interconnects to prevent negative TP scaling.
- [Test-Time Compute ROI Audit ↗](/skills/undominated-test-time-compute-roi-audit/) Calculates cost-per-accuracy return curves for Best-of-N sampling, search depth scaling, and verifier reranking vs base model upgrading.
- [Test-time search budget audit ↗](/skills/undominated-test-time-search-budget-audit/) Audits test-time compute search budgets to ensure marginal accuracy gains justify token expenditure.
- [Throughput benchmark audit ↗](/skills/undominated-throughput-benchmark-audit/) Audit throughput and latency claims (tokens/second, TTFT, concurrency, batch sizes) to ensure apples-to-apples comparisons and detect deceptive single-user vs batched measurements.
- [TIES merging trim elect audit ↗](/skills/undominated-ties-merging-trim-elect-audit/) Audits TIES-Merging parameter trimming threshold and sign consensus across fine-tuned task vectors.
- [Time-window rate ↗](/skills/undominated-time-window/) Refuse an off-peak rate published as the all-day rate.
- [Token blowout circuit breaker audit ↗](/skills/undominated-token-blowout-circuit-breaker-audit/) Audits runaway loop detection and trips circuit breaker when token expenditures exceed budget ceilings.
- [Tokenizer density audit ↗](/skills/undominated-tokenizer-density-audit/) Audit tokenizer vocabulary density, tokens-per-word / tokens-per-byte expansion ratios, and real effective text processing costs.
- [Tool allowlist ↗](/skills/undominated-tool-allowlist/) Decide whether a saved MCP permission map fits a task allowlist. A consistent refusal is a pass, not an error to paper over.
- [Tool schema tax audit ↗](/skills/undominated-tool-schema-tax-audit/) Calculate the hidden static token overhead imposed by injecting JSON schema and OpenAPI tool definitions into prompt payloads on every turn.
- [Tool Selection Recall Audit ↗](/skills/undominated-tool-selection-recall-audit/) Audits tool routing accuracy across large tool inventories and detects hallucinated function invocations.
- [Tree Speculative Decoding Audit ↗](/skills/undominated-tree-speculative-decoding-audit/) Evaluates tree-based draft candidate verification (Medusa/Eagle-2) to verify branch acceptance probabilities.
- [TTFT jitter audit ↗](/skills/undominated-ttft-jitter-audit/) Audit Time-To-First-Token variance, queuing delays, cold-start penalization, and tail latency distributions (p50, p95, p99).
- [Ulysses all-to-all bandwidth audit ↗](/skills/undominated-ulysses-alltoall-bandwidth-audit/) Audits DeepSpeed Ulysses All-to-All transpose communication overhead versus interconnect saturation.
- [Unrated sentinel ↗](/skills/undominated-unrated-sentinel/) Keep a missing score out of a ranked list, so unrated is not scored zero and a scored row is not dropped in silence.
- [Upstream freshness budget ↗](/skills/undominated-freshness-budget/) Measure each upstream source against its own declared staleness budget, so a cache nobody refetched cannot pass for current.
- [Vector Reranking Latency Tax Audit ↗](/skills/undominated-vector-reranking-latency-tax-audit/) Calculates cross-encoder reranking latency overhead and cost versus top-k bi-encoder retrieval recall.
- [Verifier Consensus Cost Audit ↗](/skills/undominated-verifier-consensus-cost-audit/) Calculates token expenditures and marginal certainty of majority voting consensus across parallel reasoning traces.
- [Video frame subsampling audit ↗](/skills/undominated-video-frame-subsampling-audit/) Audits spatio-temporal video token subsampling to prune static background tokens in long video streams.
- [WebGPU browser inference audit ↗](/skills/undominated-webgpu-browser-inference-audit/) Audits in-browser WebGPU execution shader compilation latency and first-token response times.
- [Withdrawal residue ↗](/skills/undominated-withdrawal-residue/) Check an explicitly observed withdrawn numeric field and its named dependents for leftover values. Use after a source value has been removed from a snapshot.
- [Withheld provider names ↗](/skills/undominated-withheld-provider/) Check a supplied publication denylist by exact provider-name matching. A pass does not approve a provider or establish that the supplied list is complete.
- [Workstation GPU Serving Audit ↗](/skills/undominated-workstation-gpu-serving-audit/) Calculates local inference throughput and hardware payback periods for desktop RTX workstations versus cloud API spend.
- [Zero Data Retention policy audit ↗](/skills/undominated-zdr-policy-audit/) Audit provider Zero Data Retention (ZDR) claims against published Terms of Service, abuse monitoring windows, logging exceptions, and training opt-out guarantees.

02 / THE SELECTION

## Find a fit. Read the reasoning.

Alphabetical by default. Every match is shown. Compare up to three before opening a full review.

 Filter these results Task Every category Agent deployment Agent development Agent Frameworks Agent integration Agent memory AI application development AI evaluation AKS GPU diagnosis AKS incident diagnosis AKS incident matching AKS packet capture Analytics engineering Analytics pipelines API design API frameworks API inventory API management App Service deployment Application deployment Application observability Autonomous review loop Azure compliance Azure cost analysis Azure cost forecasting Azure cost governance Azure cost optimization Azure deployment Azure deployment checks Azure portal navigation Azure SDKs Azure upgrades Azure Web PubSub Billing Browser extension connectivity Browser testing Browser verification Caching CI and delivery Claude Code automation CLAUDE.md maintenance Cloud access preflight Cloud architecture diagrams Cloud development Cloud inventory Cloud migration Cloud operations Cloud provider integrations Cloud security Cloud Security Code correctness Code editing Code review Container sandboxes Containers Content moderation Creative production Data and analytics Data and research Data engineering Data pipelines Database adapters Database engineering Database migrations Database review Database setup Databases Delivery automation Dependency reduction Deployment Deployment readiness Design and interfaces Developer Tools Development tooling Development workflow Device provisioning Discord access control Discord channel setup Document translation Documentation Documentation and knowledge Documentation editing Documents Evidence and evaluation Framework development Frontend session diagnosis Git branches Git commits Git workflow Grafana alerting Grafana app scaffolding Grafana Cloud administration Grafana Cloud cost control Grafana Cloud k6 Grafana dashboards Grafana datasource provisioning Grafana MCP access Grafana OSS administration Identity and access Image analysis Image building iMessage access control iMessage channel setup Infrastructure Infrastructure development Java migration k6 documentation k6 trend reporting Kubernetes model serving Kusto graph queries Kusto graph visualization Language understanding Languages and tooling Localization Loki label governance Machine learning Machine Learning MCP configuration Metrics Metrics cost control Migration Mobile development Model deployment Model development Model evaluation Model fine-tuning Model training Native modules Network migration Observability On-call routing Package Management Package manager auditing Payments Performance Planning and delivery Private connectivity Product selection Prometheus cost analysis Pull request repair Pull requests Realtime voice Release engineering Release preparation Research and documentation Research and evidence Research publishing Review queue Safety Sandbox configuration Sandbox development Sandbox kits Sandbox security Search and retrieval Security Security and privacy Security review Skill review loop Software architecture Spaces Speech transcription Substrate pallet audit Synthetic and load testing Telegram access control Telegram channel setup Telemetry export Testing Testing and reliability Text analytics Text translation TON contract audit Web development Web frameworks Web Frameworks Web performance Website load testing Publisher Every publisher Addy Osmani addyosmani affaan-m Amazon Web Services Anthropic Arize AI Astral Axiom, Inc. Braintrust Buf Technologies cloudflare Cloudflare Cockroach Labs Confident AI Confluent Cube Datadog Labs dbt Labs dbt-labs Deno Land Inc. docker Docker DuckDB Effectful Technologies elastic Elastic expo Expo FastAPI Functional Software, Inc. dba Sentry getsentry GitHub community GitHub community (awesome-copilot) Google Google Labs / Stitch Google LLC grafana Grafana Grafana Labs hashicorp HashiCorp Hugging Face huggingface Infisical Inc. Jesse Vincent Jesse Vincent / Superpowers JetBrains LangChain Matt Pocock microsoft Microsoft MLflow mongodb MongoDB MotherDuck Neon OpenAI Pinecone PlanetScale Prisma Promptfoo Pulumi Qdrant redis Redis, Inc. Redpanda Remotion Replicate Sentry Stripe Supabase Superpowers SurrealDB Svelte Temporal Technologies Timescale Together AI Trail of Bits trailofbits Turso Undominated.ai Vercel vLLM project Weaviate Weights & Biases Yusuke Wada Documented host Every host Agent Skills hosts Antigravity ChatGPT Claude Code Claude Desktop Claude.ai Cline Codex Cursor Gemini CLI GitHub Copilot GitHub Copilot CLI Grok Build Kimi Code Kiro MCP clients Not established OpenCode VS Code Windsurf Order Name · A–Z Name · Z–A Publisher · A–Z Review date · newest first
 Runtime, access and execution Runtime / platform Every environment Bash Cloudflare Workers Docker / containers macOS Node.js Not established Python / uv Rust toolchain Access described by source Every access scope Browser session Cloud account or infrastructure Credentials may be required Database access Host-controlled permissions Local files Not established Read-only scope documented Repository access Execution path Every execution path Host-defined HTTP endpoint Local process

Labels summarise reviewed source wording. A local process can still send data to external services. Read each review's prerequisites and permissions; these filters do not certify compatibility or enforce access.

**759** of 759 selected skills

 Reset filters Copy this view ↗

 Resource / purpose Our selection note Use & inspect Compare

Languages and tooling · GitHub community

### [.NET Timezone](/skills/github-dotnet-timezone/)

Resolves .NET timezone work through the right library first — TimeZoneConverter for cross-platform, NodaTime for recurring schedules and strict DST arithmetic — and ships both Windows and IANA identifiers on every answer, seven copy-paste code patterns, and the pitfall list from DateTimeKind.Unspecified to DST transitions that skip or repeat local times.

 timezone datetime dotnet

**Why we selected it**Routes every request through the right library before any code is written — TimeZoneConverter for cross-platform work, NodaTime when recurring schedules or strict DST rules are in play — instead of letting agents reach for TimeZoneInfo on the wrong platform.

**Weigh up**.NET-specific; the discipline transfers to other stacks but the APIs and libraries do not.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/github-dotnet-timezone/) Install command in review MIT
 Compare .NET Timezone Add

Data and analytics · dbt Labs

### [Adding a dbt unit test](/skills/dbt-labs-adding-dbt-unit-test/)

Writes a dbt unit test that mocks upstream inputs instead of querying production.

 dbt testing warehouses

**Why we selected it**The description requires mocked upstream inputs and expected outputs.

**Weigh up**Warehouse-specific type rules live in the skill references and were not executed here.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/dbt-labs-adding-dbt-unit-test/) Install command in review Apache-2.0
 Compare Adding a dbt unit test Add

Development workflow · addyosmani

### [Adversarial Decision Review](/skills/addyosmani-doubt-driven-development/)

Submit a bounded artifact and its contract to an independent reviewer before accepting a consequential decision.

 development-workflow addyosmani

**Why we selected it**The definition separates CLAIM from reviewer input, requires artifact-plus-contract only and warns against recursive persona orchestration.

**Weigh up**An adversarial prompt does not establish independence or expertise. The skill requires host delegation; self-questioning is explicitly a degraded fallback.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/addyosmani-doubt-driven-development/) Install command in review MIT
 Compare Adversarial Decision Review Add

Testing · Trail of Bits

### [AFL++](/skills/trailofbits-aflpp/)

Runs AFL++ as a multi-core campaign and forbids afl-system-config on a production or development machine because that script needs root and turns OS protections off.

 fuzzing afl c

**Why we selected it**afl-system-config and afl-persistent-config are called out as root scripts that disable OS security features.

**Weigh up**The security warning says not to fuzz on production systems or the development environment.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-aflpp/) Install command in review CC-BY-SA-4.0
 Compare AFL++ Add

Agent development · Anthropic

### [Agent Development for Claude Code Plugins](/skills/anthropic-agent-development/)

Explains how to write a Claude Code plugin agent file (frontmatter, trigger description, system prompt) and ships a Bash script that checks one agent file.

 claude-code plugin-dev agents

**Why we selected it**It sets the agent frontmatter rules: a name of 3-50 lowercase letters, numbers and hyphens, a required description, model (inherit, sonnet, opus or haiku) and color, and an optional tools list it says to keep to the minimum needed.

**Weigh up**Last commit touching plugins/plugin-dev/skills/agent-development at revision 41f32e40: 2026-04-28 (ce721c1f).

 Source reviewed

6 sources · 2026-10-21

[Read the full review ↗](/skills/anthropic-agent-development/) Upstream setup linked Apache-2.0
 Compare Agent Development for Claude Code Plugins Add

Model evaluation · Google

### [Agent Platform Eval Flywheel](/skills/google-agent-platform-eval-flywheel/)

Evaluates and iterates on Google Cloud Agent Platform models and agents, with a confirmation card before every billed evaluation run.

 google-cloud evaluation llm-as-judge

**Why we selected it**Evaluation, inference and scenario-generation calls need their own Yes/No confirmation for every run, asked in one turn and executed only after the reply.

**Weigh up**Setup tells the agent not to create a virtual environment and to pip install missing packages into the current environment.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/skills/google-agent-platform-eval-flywheel/) Install command in review Apache-2.0
 Compare Agent Platform Eval Flywheel Add

AI application development · Google

### [Agent Platform GenAI Inference](/skills/google-agent-platform-inference/)

Calls Gemini and third-party OpenMaaS models on Google Cloud Agent Platform, asking for model, project and region instead of defaulting.

 google-cloud inference openai-compatible

**Why we selected it**The file says never to guess, volunteer or default to a model, and to ask for the project ID and region rather than assume them.

**Weigh up**Region availability is checked with a live generateContent call to the exact model and region, which the file requires before answering region-specific requests.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/skills/google-agent-platform-inference/) Install command in review Apache-2.0
 Compare Agent Platform GenAI Inference Add

Kubernetes model serving · Microsoft

### [AI Runway AKS setup](/skills/microsoft-airunway-aks-setup/)

Pins Microsoft's AI Runway AKS setup skill, which requires confirmation before install, deployment, or GPU provisioning.

 microsoft aks ai-runway

**Why we selected it**No selected skills record uses this source path.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-airunway-aks-setup/) Install command in review MIT
 Compare AI Runway AKS setup Add

Cloud operations · Microsoft

### [AKS Automatic Readiness](/skills/microsoft-azure-kubernetes-automatic-readiness/)

Pins Microsoft's AKS Automatic readiness skill, which assesses a cluster or local manifests without changing the cluster and writes files only after an accepted diff.

 azure aks kubernetes

**Why we selected it**The first guardrail says the assessment never modifies cluster state and names kubectl apply and az aks update as forbidden.

**Weigh up**The resource was not executed, and no Azure API, CLI, or MCP tool was called.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-kubernetes-automatic-readiness/) Install command in review MIT
 Compare AKS Automatic Readiness Add

AKS GPU diagnosis · Microsoft

### [AKS GPU inference](/skills/microsoft-aks-gpu-inference/)

Pins Microsoft's AKS GPU and KAITO diagnosis skill, which stays on read-only evidence unless scaling, drain, deletion, or add-on changes are separately authorized.

 aks gpu kaito

**Why we selected it**The file requires the host to authorize shell, kubectl, and az against the bound target before any referenced pipeline, and it forbids routing kubectl through Azure MCP or around host policy.

**Weigh up**The resource was not executed.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-aks-gpu-inference/) Upstream setup linked MIT
 Compare AKS GPU inference Add

AKS incident matching · Microsoft

### [AKS known issues](/skills/microsoft-aks-known-issues/)

Pins Microsoft's AKS known-issue skill, which refuses a match unless every catalog qualifier is present and requires approval before any mutation.

 aks known-issues approval

**Why we selected it**The file says not to use the skill unless every qualifier for a catalog row is present, and it says codes are not matched as substrings.

**Weigh up**The resource was not executed.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-aks-known-issues/) Upstream setup linked MIT
 Compare AKS known issues Add

AKS packet capture · Microsoft

### [AKS network capture](/skills/microsoft-aks-network-capture/)

Pins Microsoft's AKS packet-capture skill, which will not claim a capture ran unless the host gate passes and which separates capture intent from debug-container consent.

 aks packet-capture authorization

**Why we selected it**The file says a governed Azure CLI tool does not authorize shell, kubectl, artifact storage, or packet capture, and it forbids routing kubectl through Azure MCP or adding an unapproved execution path.

**Weigh up**The resource was not executed.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-aks-network-capture/) Upstream setup linked MIT
 Compare AKS network capture Add

AKS incident diagnosis · Microsoft

### [AKS troubleshooting](/skills/microsoft-aks-troubleshooting/)

Pins Microsoft's live AKS troubleshooting skill, which does not restart, delete, cordon, drain, scale, upgrade, or reconfigure a resource unless remediation is explicitly requested.

 aks troubleshooting read-only

**Why we selected it**The file forbids restart, delete, cordon, drain, scale, upgrade, and reconfigure unless the user explicitly asks, and it says to propose a fix without applying it uninvited.

**Weigh up**The resource was not executed.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-aks-troubleshooting/) Upstream setup linked MIT
 Compare AKS troubleshooting Add

Security review · Trail of Bits

### [Algorand vulnerability scanner](/skills/trailofbits-algorand-vulnerability-scanner/)

Pins Trail of Bits' Algorand scanner, which treats a short or empty coverage table as an unfinished scan and does not let a clean Tealer run stand in for patterns it never examined.

 algorand teal pyteal

**Why we selected it**A coverage table with a missing row or an empty verdict must be reported as an incomplete scan, and not-applicable requires a reason rather than silence.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-algorand-vulnerability-scanner/) Install command in review CC-BY-SA-4.0
 Compare Algorand vulnerability scanner Add

Creative production · Anthropic

### [Algorithmic Art](/skills/anthropics-algorithmic-art/)

Creates original generative art with p5.js through a two-step method: author an algorithmic philosophy as a named movement with a manifesto, then express it as seeded-randomness sketches with an interactive parameter viewer.

 p5js generative-art creative-coding

**Why we selected it**Separates the aesthetic idea from its expression: an algorithmic philosophy is authored first as a named movement with a manifesto, and only then expressed as p5.js sketches that are 90% algorithm, 10% parameters.

**Weigh up**Aesthetics and process guidance, not a rendering-performance reference for large particle counts or shader work.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/anthropics-algorithmic-art/) Install command in review Apache-2.0
 Compare Algorithmic Art Add

AI application development · Amazon Web Services

### [Amazon Bedrock](/skills/aws-amazon-bedrock/)

Bedrock model invocation, Knowledge Bases, Guardrails and AgentCore guidance, with quota, prompt-caching and cost-tracking workflows.

 bedrock aws model-invocation

**Why we selected it**It requires setting maxTokens explicitly on every Converse or InvokeModel call, because an unset value defaults to the model maximum and reserves far more quota, a cause of ThrottlingException named in the file.

**Weigh up**Most procedures live in the references directory, which was not opened; the file says to read the relevant reference before responding.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/skills/aws-amazon-bedrock/) Install command in review Apache-2.0
 Compare Amazon Bedrock Add

Data engineering · dbt-labs

### [Answer Business Questions with dbt](/skills/dbt-labs-answering-natural-language-questions-with-dbt/)

Answer warehouse questions through existing semantic metrics before resorting to carefully scoped SQL.

 data-engineering dbt-labs

**Why we selected it**It answers a business question from the semantic layer before it writes SQL, and it stops suggesting changes at the semantic model.

**Weigh up**The skill is not for building, testing, or running dbt models.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/dbt-labs-answering-natural-language-questions-with-dbt/) Install command in review Apache-2.0
 Compare Answer Business Questions with dbt Add

AI application development · Anthropic

### [Anthropic Claude API](/skills/anthropics-claude-api/)

Routes Claude API work to language-specific SDK guidance and distinguishes self-hosted tool loops from managed agent execution.

 anthropic claude api

**Why we selected it**Explains the operational differences among a plain API call, a tool runner, managed agents and the separate Agent SDK.

**Weigh up**This is Anthropic-specific and its instructions can strongly influence model, SDK and architecture choices.

 Source reviewed

8 sources · 2026-10-14

[Read the full review ↗](/skills/anthropics-claude-api/) Install command in review Apache-2.0
 Compare Anthropic Claude API Add

Research and documentation · Anthropic

### [Anthropic Documentation Coauthoring](/skills/anthropics-doc-coauthoring/)

Guides a human and agent through audience discovery, section-by-section drafting and a separate-reader review of a substantial document.

 documentation rfc specifications

**Why we selected it**Starts with the audience, intended impact and missing context, then lets the author curate ideas before the agent drafts each section.

**Weigh up**Reader-model agreement is a spot check, not factual verification or a human usability study; the author still needs to verify facts and links.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/anthropics-doc-coauthoring/) Upstream setup linked Not established
 Compare Anthropic Documentation Coauthoring Add

Design and interfaces · Anthropic

### [Anthropic Frontend Design](/skills/anthropics-frontend-design/)

Builds a visual direction from the product’s audience and subject, then reviews typography, layout and interface copy against that brief.

 design typography frontend

**Why we selected it**Requires a compact design plan and a critique of generic choices before implementation.

**Weigh up**This is an opinionated design process, not a component library, usability study or automated accessibility audit.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/anthropics-frontend-design/) Install command in review Apache-2.0
 Compare Anthropic Frontend Design Add

Documents · Anthropic

### [Anthropic PDF Processing](/skills/anthropics-pdf/)

Separates PDF extraction, actual form-field filling and image-coordinate text annotations, with explicit field maps and rendered-output review.

 pdf forms ocr

**Why we selected it**Field discovery precedes filling, with field IDs, one-based page numbers and type-specific allowed values carried into the handoff.

**Weigh up**check_bounding_boxes.py reads authored JSON, not the PDF. It prints FAILURE messages without a failure exit status, caps diagnostics and does not validate page boundaries, text width or accessibility.

 Source reviewed

10 sources · 2026-10-15

[Read the full review ↗](/skills/anthropics-pdf/) Install command in review Anthropic custom terms
 Compare Anthropic PDF Processing Add

Documents · Anthropic

### [Anthropic PowerPoint Presentations](/skills/anthropics-pptx/)

Builds editable decks or adapts a template, separating content checks, structural validation and full-resolution visual review.

 powerpoint pptx slides

**Why we selected it**Separates editable native charts, source content and template structure rather than treating a slide image as an editable deck.

**Weigh up**LibreOffice font substitution can disagree with PowerPoint. Neither an XML pass nor a thumbnail grid proves readable full-size output or native PowerPoint fidelity.

 Source reviewed

8 sources · 2026-10-15

[Read the full review ↗](/skills/anthropics-pptx/) Install command in review Anthropic custom terms
 Compare Anthropic PowerPoint Presentations Add

Agent development · Anthropic

### [Anthropic Skill Creator](/skills/anthropics-skill-creator/)

Develops skills from realistic task fixtures and baseline comparisons, with separate trigger-description experiments and human output review.

 skills evaluation triggering

**Why we selected it**Separates activation experiments from task-output quality, preserving both a baseline and human feedback.

**Weigh up**Full comparisons require supported subagents and Claude CLI; reduced Claude.ai paths explicitly omit baseline benchmarking. A source review supplies neither benchmark results nor installation proof.

 Source reviewed

9 sources · 2026-10-15

[Read the full review ↗](/skills/anthropics-skill-creator/) Install command in review Apache-2.0
 Compare Anthropic Skill Creator Add

Documents · Anthropic

### [Anthropic Spreadsheets](/skills/anthropics-xlsx/)

Produces editable, formula-driven workbooks from specified inputs, with separate recalculation receipts and business-logic checks.

 excel xlsx formulas

**Why we selected it**Distinguishes formula expressions from cached calculated values, so a workbook handoff can include both rather than silently replacing formulas.

**Weigh up**Recalculation rewrites the workbook in place. Retain the original: --force can accept destructive external-link loss, and link detection is not exhaustive.

 Source reviewed

7 sources · 2026-10-15

[Read the full review ↗](/skills/anthropics-xlsx/) Install command in review Anthropic custom terms
 Compare Anthropic Spreadsheets Add

Browser testing · Anthropic

### [Anthropic Webapp Testing](/skills/anthropics-webapp-testing/)

Guides local browser checks with Playwright and includes a wrapper that starts development servers around an automation command.

 playwright browser local-development

**Why we selected it**Uses rendered-page reconnaissance before choosing selectors for dynamic applications.

**Weigh up**The server helper checks only whether a TCP port accepts a connection, not whether the expected application is healthy.

 Source reviewed

8 sources · 2026-10-14

[Read the full review ↗](/skills/anthropics-webapp-testing/) Install command in review Apache-2.0
 Compare Anthropic Webapp Testing Add

Documents · Anthropic

### [Anthropic Word Documents](/skills/anthropics-docx/)

Separates new Word-document generation from editing existing OOXML, with explicit checks for tables, comments and tracked changes.

 word docx tracked-changes

**Why we selected it**Documents the different create, edit and read paths instead of treating Word files as plain text.

**Weigh up**Restricted Anthropic terms apply; this is a source-available reference, not an open-source document package.

 Source reviewed

8 sources · 2026-10-15

[Read the full review ↗](/skills/anthropics-docx/) Install command in review Anthropic custom terms
 Compare Anthropic Word Documents Add

Development workflow · Addy Osmani

### [API and Interface Design](/skills/addyosmani-api-and-interface-design/)

Designs public interfaces so the right call is easy and a breaking change is explicit.

 api contracts design

**Why we selected it**The skill treats every observable behaviour as a commitment and tells the author to define the contract before the implementation.

**Weigh up**Error strategies must not be mixed across endpoints.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/addyosmani-api-and-interface-design/) Install command in review MIT
 Compare API and Interface Design Add

API inventory · Microsoft

### [API Center management SDK](/skills/microsoft-azure-mgmt-apicenter-py/)

Pins Microsoft's API Center Python skill, which requires DefaultAzureCredential and rejects connection strings and API keys for the management client.

 api-center azure default-azure-credential

**Why we selected it**The file says to prefer DefaultAzureCredential and to avoid connection strings, account keys, and API keys because they bypass Entra audit and rotation.

**Weigh up**The resource was not executed.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-mgmt-apicenter-py/) Install command in review MIT
 Compare API Center management SDK Add

API management · Microsoft

### [API Management SDK](/skills/microsoft-azure-mgmt-apimanagement-py/)

Pins Microsoft's API Management Python skill, which requires DefaultAzureCredential and rejects connection strings and API keys for the management client.

 api-management azure default-azure-credential

**Why we selected it**The file says to prefer DefaultAzureCredential for the management client and to avoid connection strings, account keys, and API keys.

**Weigh up**The resource was not executed.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-mgmt-apimanagement-py/) Install command in review MIT
 Compare API Management SDK Add

Model evaluation · Arize AI

### [Arize Evaluator](/skills/arize-ai-arize-evaluator/)

Creates and runs Arize LLM-as-judge and code evaluators through the ax CLI, with a rule against fabricating scores.

 arize llm-as-judge evaluation

**Why we selected it**If an evaluation task fails, is cancelled or produces no scores, the file says to report the failure and not run a manual evaluation, invent scores or estimate percentages.

**Weigh up**The file tells the agent to run ax commands directly without checking versions, environment variables or profiles first. The four reference files it links were not opened.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/skills/arize-ai-arize-evaluator/) Install command in review MIT
 Compare Arize Evaluator Add

Observability · Arize AI

### [Arize Instrumentation Health](/skills/arize-ai-arize-instrumentation-health/)

Read-only audit of exported Arize spans for nine instrumentation defects, including missing token counts behind empty cost dashboards.

 arize openinference tracing

**Why we selected it**The audit is read-only by default and treats exported span content as untrusted data, never following instructions found inside span attributes.

**Weigh up**Span export is delegated to the arize-trace skill, which was not reviewed; this skill does not export spans on its own.

 Source reviewed

6 sources · 2026-10-13

[Read the full review ↗](/skills/arize-ai-arize-instrumentation-health/) Install command in review MIT
 Compare Arize Instrumentation Health Add

Languages and tooling · Astral

### [Astral ruff](/skills/astral-ruff/)

Astral's skill for linting, fixing and formatting Python with ruff: when to use it, how to invoke it, which changes to avoid, and how Black, Flake8 and isort commands map onto ruff.

 astral python ruff

**Why we selected it**It is Astral's own skill for its tool, shipped in Astral's claude-code-plugins marketplace, and it says which form to run: uv run ruff when ruff is a project dependency, so the pinned version is used, uvx ruff for one-off checks, or a global ruff.

**Weigh up**Last commit touching plugins/astral/skills/ruff at revision f3ce88a7: 2026-02-27 (f3ce88a).

 Source reviewed

5 sources · 2026-10-21

[Read the full review ↗](/skills/astral-ruff/) Upstream setup linked MIT OR Apache-2.0
 Compare Astral ruff Add

Languages and tooling · Astral

### [Astral ty](/skills/astral-ty/)

Astral's skill for type-checking Python with ty: invocation through uv, ty check options, [tool.ty] configuration with per-file overrides, mypy and Pyright command mappings, and rule-specific ignores.

 astral python typing

**Why we selected it**It is Astral's own skill for ty, from astral-sh/claude-code-plugins, covering ty check on a directory or file, rule severity flags (--error, --warn, --ignore), Python version and platform targeting, and [tool.ty] configuration with [[tool.ty.overrides]] for tests.

**Weigh up**Last commit touching plugins/astral/skills/ty at revision f3ce88a7: 2026-02-27 (f3ce88a).

 Source reviewed

5 sources · 2026-10-21

[Read the full review ↗](/skills/astral-ty/) Upstream setup linked MIT OR Apache-2.0
 Compare Astral ty Add

Package Management · Astral

### [Astral uv Python Workflow](/skills/astral-uv/)

Establishes disciplined uv workflows across standalone scripts, lockfile-managed projects, and ephemeral CLI tool execution.

 astral uv python

**Why we selected it**The skill picks one uv workflow from scripts, projects, tools, or the pip interface instead of mixing them.

**Weigh up**The skill says not to use uv in projects managed by other tools, not to call pip inside a uv project, and not to run python directly there.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/astral-uv/) Install command in review MIT
 Compare Astral uv Python Workflow Add

Testing · Trail of Bits

### [Atheris](/skills/trailofbits-atheris/)

Sets up a Python fuzz harness, including C extensions, instead of treating a unit test as a fuzzer.

 fuzzing python atheris

**Why we selected it**The description names TestOneInput and AddressSanitizer.

**Weigh up**CC-BY-SA-4.0 applies to an adaptation you redistribute.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-atheris/) Install command in review CC-BY-SA-4.0
 Compare Atheris Add

Security review · Trail of Bits

### [Audit Augmentation](/skills/trailofbits-trailmark-audit-augmentation/)

Overlays external findings — SARIF static-analysis results, weAudit annotation files and Trailmark 0.4.x binary-analysis exports — onto a Trailmark code graph by file and line overlap and builds severity-based subgraphs.

 sarif static-analysis graph

**Why we selected it**Maps SARIF results, weAudit annotations and v0.4 binary-analysis exports onto Trailmark graph nodes by file and line overlap and builds severity-based subgraphs.

**Weigh up**Binary-graph import (engine.augment_binary) needs Trailmark 0.4.0+; SARIF and weAudit import are v0.2-safe.

 Source reviewed

5 sources · 2026-10-22

[Read the full review ↗](/skills/trailofbits-trailmark-audit-augmentation/) Upstream setup linked CC-BY-SA-4.0
 Compare Audit Augmentation Add

Development tooling · trailofbits

### [Authenticated GitHub CLI Workflow](/skills/trailofbits-gh-cli/)

Prefer authenticated GitHub CLI reads and scoped clones when inspecting GitHub resources.

 development-tooling trailofbits

**Why we selected it**The hook denies an entire batched fetch when one GitHub URL matches; the shim blocks contents API patterns and some unscoped temporary clones, while cleanup validates the session identifier.

**Weigh up**Installing the skill directory alone does not activate the separate Claude plugin hooks or PATH shim. Hook matching covers selected tools and URL forms; it is not a complete network policy. Session cleanup recursively removes its clone directory.

 Source reviewed

9 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-gh-cli/) Install command in review CC-BY-SA-4.0
 Compare Authenticated GitHub CLI Workflow Add

Infrastructure development · HashiCorp

### [AWS AMI builder](/skills/hashicorp-aws-ami-builder/)

Builds an AMI with Packer's amazon-ebs builder, filters the source AMI instead of hardcoding one, and warns that the build spends AWS money.

 packer ami aws

**Why we selected it**The template pins the hashicorp/amazon plugin and selects the newest Canonical Ubuntu AMI with an owner filter rather than an AMI id.

**Weigh up**The skill does not build an image for a cloud other than AWS.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/hashicorp-aws-ami-builder/) Install command in review MPL-2.0
 Compare AWS AMI builder Add

Content moderation · Microsoft

### [Azure AI Content Safety for Python](/skills/microsoft-azure-ai-contentsafety-py/)

Pins Microsoft's Python Content Safety skill, which keeps new code on Entra credentials and can stop analysis when a blocklist matches.

 content-safety moderation blocklist

**Why we selected it**New code is told to use DefaultAzureCredential, and AzureKeyCredential is limited to an existing keyed deployment that has not been migrated to Entra ID.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-ai-contentsafety-py/) Install command in review MIT
 Compare Azure AI Content Safety for Python Add

Content moderation · Microsoft

### [Azure AI Content Safety REST SDK for TypeScript](/skills/microsoft-azure-ai-contentsafety-ts/)

Microsoft's TypeScript guide to the @azure-rest/ai-content-safety REST client: scoring text and images for hate, sexual, violence and self-harm severity, managing custom blocklists, and folding the results into one allow-or-block decision.

 content-safety moderation blocklist

**Why we selected it**It warns that ContentSafetyClient is a function, not a class, and checks isUnexpected() after each call whose response body it reads.

**Weigh up**Both install lines Microsoft prints for this skill, `npx skills add microsoft/skills --skill azure-sdk-typescript` and `/plugin install azure-sdk-typescript@skills`, install the whole azure-sdk-typescript plugin rather than the Content Safety skill alone.

 Source reviewed

6 sources · 2026-10-21

[Read the full review ↗](/skills/microsoft-azure-ai-contentsafety-ts/) Upstream setup linked MIT
 Compare Azure AI Content Safety REST SDK for TypeScript Add

Content moderation · Microsoft

### [Azure AI Content Safety SDK for Java](/skills/microsoft-azure-ai-contentsafety-java/)

Microsoft's Java guide to com.azure:azure-ai-contentsafety at 1.1.0-beta.1: text and image harm analysis with ContentSafetyClient, and blocklist management with BlocklistClient.

 content-safety moderation blocklist

**Why we selected it**It pairs ContentSafetyClient for analysis with BlocklistClient for blocklist create or update, list, get, item add, item list, item remove and delete.

**Weigh up**Both install lines Microsoft prints for this skill, `npx skills add microsoft/skills --skill azure-sdk-java` and `/plugin install azure-sdk-java@skills`, install the whole azure-sdk-java plugin rather than the Content Safety skill alone.

 Source reviewed

6 sources · 2026-10-21

[Read the full review ↗](/skills/microsoft-azure-ai-contentsafety-java/) Upstream setup linked MIT
 Compare Azure AI Content Safety SDK for Java Add

Document translation · Microsoft

### [Azure AI Document Translation for Python](/skills/microsoft-azure-ai-translation-document-py/)

Pins Microsoft's Python document-translation skill, which uses Entra for new clients and limits blob SAS permissions on source and target containers.

 document-translation blob-storage entra-id

**Why we selected it**The file says new code should use DefaultAzureCredential, avoid API keys, and set AZURE_TOKEN_CREDENTIALS in production to constrain the credential chain.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-ai-translation-document-py/) Install command in review MIT
 Compare Azure AI Document Translation for Python Add

Language understanding · Microsoft

### [Azure AI Language Conversations for Python](/skills/microsoft-azure-ai-language-conversations-py/)

Pins Microsoft's Python conversation-analysis skill, which tells new code to use token credentials and reserves API keys for unmigrated keyed deployments.

 conversational-language-understanding entra-id azure-ai

**Why we selected it**The file says new code should use DefaultAzureCredential, and AzureKeyCredential only for an existing keyed deployment that has not been migrated to Entra ID.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-ai-language-conversations-py/) Install command in review MIT
 Compare Azure AI Language Conversations for Python Add

Cloud development · microsoft

### [Azure AI Search for Python](/skills/microsoft-azure-search-documents-py/)

Create vector-capable indexes and combine keyword, vector and semantic queries.

 cloud-development microsoft

**Why we selected it**New code is told to use DefaultAzureCredential. An API key is only for a deployment that has not moved to Entra yet.

**Weigh up**setup_vector_index.py creates or updates an index in the named service. It does not upload documents.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-search-documents-py/) Install command in review MIT
 Compare Azure AI Search for Python Add

Text analytics · Microsoft

### [Azure AI Text Analytics for Python](/skills/microsoft-azure-ai-textanalytics-py/)

Pins Microsoft's Python text-analytics skill, which keeps new code on DefaultAzureCredential and reserves API keys for unmigrated keyed deployments.

 text-analytics entra-id python

**Why we selected it**The file says to prefer DefaultAzureCredential and to avoid connection strings and API keys because they bypass Entra audit and rotation.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-ai-textanalytics-py/) Install command in review MIT
 Compare Azure AI Text Analytics for Python Add

Text translation · Microsoft

### [Azure AI Text Translation for Python](/skills/microsoft-azure-ai-translation-text-py/)

Pins Microsoft's Python text-translation skill, which requires a custom subdomain for token auth and keeps the global endpoint on key plus region.

 text-translation entra-id python

**Why we selected it**The file says token-credential auth requires a custom subdomain, and that a global endpoint must stay on the key-based path until a custom subdomain exists.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-ai-translation-text-py/) Install command in review MIT
 Compare Azure AI Text Translation for Python Add

Speech transcription · Microsoft

### [Azure AI Transcription for Python](/skills/microsoft-azure-ai-transcription-py/)

Pins Microsoft's Python transcription skill, which prefers DefaultAzureCredential in production and says never to hardcode credentials.

 speech-to-text entra-id python

**Why we selected it**The file says two auth modes are supported, and that production code should prefer DefaultAzureCredential and never hardcode credentials.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-ai-transcription-py/) Install command in review MIT
 Compare Azure AI Transcription for Python Add

Image analysis · Microsoft

### [Azure AI Vision Image Analysis for Python](/skills/microsoft-azure-ai-vision-imageanalysis-py/)

Pins Microsoft's Python image-analysis skill, which keeps new code on DefaultAzureCredential and states image size and dimension limits.

 image-analysis entra-id python

**Why we selected it**The file says new code should use DefaultAzureCredential, avoid API keys, and constrain the production credential chain with AZURE_TOKEN_CREDENTIALS.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-ai-vision-imageanalysis-py/) Install command in review MIT
 Compare Azure AI Vision Image Analysis for Python Add

Realtime voice · Microsoft

### [Azure AI Voice Live for Python](/skills/microsoft-azure-ai-voicelive-py/)

Pins Microsoft's Python Voice Live skill, which uses async Entra credentials and says not to pair this SDK with sync clients.

 voice websocket entra-id

**Why we selected it**The file says the SDK is async-only and not to pair it with sync clients from other Azure SDKs in the same call path.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-ai-voicelive-py/) Install command in review MIT
 Compare Azure AI Voice Live for Python Add

Azure SDKs · microsoft

### [Azure App Configuration for Python](/skills/microsoft-azure-appconfiguration-py/)

Review key-value, label, feature-flag and snapshot operations for Azure App Configuration.

 azure-sdks microsoft

**Why we selected it**The retained reference scopes a snapshot by key and label and closes both async credential and client. Provider-based refresh and feature evaluation are separate application dependencies.

**Weigh up**The SDK stores flag configuration; it does not by itself evaluate targeting rules or refresh every application. azure-identity is an additional dependency, and require_envvar=True requires the credential-selection variable even in local development.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-appconfiguration-py/) Install command in review MIT
 Compare Azure App Configuration for Python Add

Azure deployment · Microsoft

### [Azure app onboard deploy](/skills/microsoft-deploy/)

Pins the app-onboard deploy phase, which requires a what-if preview and an approval gate before it changes Azure, then says to stop.

 azure deployment what-if

**Why we selected it**Preflight requires authentication, a mandatory what-if preview, RBAC, and the resource group before the deploy approval gate.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-deploy/) Install command in review MIT
 Compare Azure app onboard deploy Add

Deployment readiness · Microsoft

### [Azure app onboard prereq](/skills/microsoft-azure-app-onboard-prereq/)

Pins Microsoft's Azure app-onboard prerequisite skill, which forbids package-manager install, build, and test commands except a later per-command consent gate.

 microsoft azure readiness

**Why we selected it**No selected skills record uses this source path.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-app-onboard-prereq/) Install command in review MIT
 Compare Azure app onboard prereq Add

Cloud development · microsoft

### [Azure Blob Storage for Python](/skills/microsoft-azure-storage-blob-py/)

Upload, stream and manage blobs using explicit overwrite, metadata and delegated-access choices.

 cloud-development microsoft

**Why we selected it**Shared access signatures in this skill are user-delegation keys tied to Entra, not account keys.

**Weigh up**The samples call the storage account URL when executed. The skill does not create the storage account.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-storage-blob-py/) Install command in review MIT
 Compare Azure Blob Storage for Python Add

Cloud migration · Microsoft

### [Azure cloud migrate](/skills/microsoft-azure-cloud-migrate/)

Pins Microsoft's cross-cloud migration skill, which requires an assessment before code changes and forbids editing the source directory.

 azure migration assessment

**Why we selected it**The rules say to generate an assessment before any code migration and not to skip phases.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-cloud-migrate/) Install command in review MIT
 Compare Azure cloud migrate Add

Azure compliance · Microsoft

### [Azure compliance and security audit](/skills/microsoft-azure-compliance/)

Pins Microsoft's Azure compliance skill, which requires az login before an azqr or Key Vault expiration review and separates the report from remediation.

 azure compliance key-vault

**Why we selected it**The prerequisites require az login and permission to read resource configuration and Key Vault metadata before the scan.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-compliance/) Install command in review MIT
 Compare Azure compliance and security audit Add

Azure SDKs · microsoft

### [Azure Container Registry for Python](/skills/microsoft-azure-containerregistry-py/)

Review repository, tag and manifest operations with explicit deletion boundaries.

 azure-sdks microsoft

**Why we selected it**The cleanup reference checks last-updated time and empty tag lists before deleting by digest, but has no deployment-reference or rollback-artifact check.

**Weigh up**The source download_manifest example uses an API renamed to get_manifest in the SDK; verify the installed version before copying it. An old untagged manifest may still be used by digest, so age/tag filters do not prove safe deletion.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-containerregistry-py/) Install command in review MIT
 Compare Azure Container Registry for Python Add

Databases · microsoft

### [Azure Cosmos DB for Python](/skills/microsoft-azure-cosmos-py/)

Use Cosmos DB NoSQL clients for partition-aware document operations and parameterized queries.

 databases microsoft

**Why we selected it**Point reads are specified as needing both the item id and the partition key, and queries are supposed to be parameterized.

**Weigh up**The skill links scripts/setup_cosmos_container.py. That path returned HTTP 404 at revision fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb, so the advertised CLI is not in the tree.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-cosmos-py/) Install command in review MIT
 Compare Azure Cosmos DB for Python Add

Azure cost analysis · Microsoft

### [Azure cost analysis](/skills/microsoft-cost-analysis/)

Pins Microsoft's Azure cost-analysis skill, which refuses forecasts, pricing estimates, rightsizing, commitments, and budgets, and will not reshape cost results in a shell.

 azure cost-analysis aks

**Why we selected it**The description refuses forecasts, pricing estimates, rightsizing, commitments, and budgets, and the workflow says never to transform MCP results in a shell or interpreter.

**Weigh up**The resource was not executed.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-cost-analysis/) Upstream setup linked MIT
 Compare Azure cost analysis Add

Azure cost forecasting · Microsoft

### [Azure Cost Estimation](/skills/microsoft-cost-estimation/)

Pins Microsoft's Azure cost-estimation skill, which separates forecasts from hypothetical prices and refuses shell transforms and mixed currencies.

 azure-cost forecast pricing

**Why we selected it**The workflow refuses to reshape cost-tool results in a shell or interpreter and refuses to combine more than one currency.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-cost-estimation/) Install command in review MIT
 Compare Azure Cost Estimation Add

Azure cost optimization · Microsoft

### [Azure Cost Optimization](/skills/microsoft-cost-optimization/)

Pins Microsoft's cost-optimization skill, which may recommend a change and forbids deleting, resizing, purchasing, or deploying resources.

 azure-cost rightsizing commitments

**Why we selected it**The workflow limits the skill to recommendations and explicitly forbids delete, resize, purchase, and deploy.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-cost-optimization/) Install command in review MIT
 Compare Azure Cost Optimization Add

Cloud operations · Microsoft

### [Azure Deploy](/skills/microsoft-azure-deploy/)

Pins Microsoft's Azure deploy skill, which stops unless a separate validation skill has already marked the deployment plan validated.

 azure deployment azd

**Why we selected it**The file forbids the agent from marking a plan Validated and says to stop when that status or the Validation Proof section is missing.

**Weigh up**The resource was not executed, and no Azure API, CLI, or MCP tool was called.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-deploy/) Install command in review MIT
 Compare Azure Deploy Add

Cloud operations · Microsoft

### [Azure Enterprise Infra Planner](/skills/microsoft-azure-enterprise-infra-planner/)

Pins Microsoft's enterprise Azure infrastructure skill, which holds IaC and deployment until the user approves the plan and acknowledges deploy risk.

 azure bicep terraform

**Why we selected it**Phase 5 approval is required before IaC, and a plan that is not approved stops both generation and deployment.

**Weigh up**The resource was not executed, and no Azure API, CLI, or MCP tool was called.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-enterprise-infra-planner/) Install command in review MIT
 Compare Azure Enterprise Infra Planner Add

Azure SDKs · microsoft

### [Azure Event Grid Publishing for Python](/skills/microsoft-azure-eventgrid-py/)

Publish CloudEvents or Event Grid events with a correctly scoped endpoint and client.

 azure-sdks microsoft

**Why we selected it**The namespace reference supplies namespace_topic explicitly and uses CloudEvent; the async example closes credential and publisher independently.

**Weigh up**Publishing acceptance does not prove delivery or exactly-once handling. The namespace example publishes events and does not implement receive/acknowledge/reject consumers. Credential-chain options depend on azure-identity version.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-eventgrid-py/) Install command in review MIT
 Compare Azure Event Grid Publishing for Python Add

Cloud development · microsoft

### [Azure Event Hubs for Python](/skills/microsoft-azure-eventhub-py/)

Publish partitioned events and consume streams with explicit checkpoint ownership.

 cloud-development microsoft

**Why we selected it**Production checkpointing is a separate package plus a blob container, not a feature of the producer client alone.

**Weigh up**Sending with the helper publishes events to Azure. The skill does not create the namespace.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-eventhub-py/) Install command in review MIT
 Compare Azure Event Hubs for Python Add

Cloud development · microsoft

### [Azure Identity for Python](/skills/microsoft-azure-identity-py/)

Select and diagnose Entra credential chains across development, hosted workloads and delegated access.

 cloud-development microsoft

**Why we selected it**The package floor is Python 3.9, and the certificate class the file tells you to import is CertificateCredential, not ClientCertificateCredential.

**Weigh up**Getting a token calls the Entra authority for that cloud. The skill does not call the storage or compute API itself.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-identity-py/) Install command in review MIT
 Compare Azure Identity for Python Add

Cloud development · Microsoft

### [Azure Identity library for .NET](/skills/microsoft-azure-identity-dotnet/)

Microsoft's .NET guide to choosing an Azure.Identity credential: DefaultAzureCredential while developing, a specific managed identity in production, plus service principal, developer and sovereign-cloud options.

 identity entra-id default-azure-credential

**Why we selected it**Practice 1 keeps DefaultAzureCredential for development and builds a ManagedIdentityCredential from a user-assigned client ID for production, and the environment-based sample switches between the two on builder.Environment.IsProduction().

**Weigh up**Both install lines Microsoft prints, `npx skills add microsoft/skills --skill azure-sdk-dotnet` and `/plugin install azure-sdk-dotnet@skills`, install the whole azure-sdk-dotnet plugin, not this skill alone.

 Source reviewed

6 sources · 2026-10-21

[Read the full review ↗](/skills/microsoft-azure-identity-dotnet/) Upstream setup linked MIT
 Compare Azure Identity library for .NET Add

Cloud development · Microsoft

### [Azure Identity library for Rust](/skills/microsoft-azure-identity-rust/)

Microsoft's Rust guide to azure_identity, which has no DefaultAzureCredential: DeveloperToolsCredential for local work, ManagedIdentityCredential for Azure-hosted code and ClientSecretCredential for service principals.

 identity entra-id authentication

**Why we selected it**It states that the Rust SDK has no DefaultAzureCredential and marks `use azure_identity::DefaultAzureCredential;` as incorrect, pointing to DeveloperToolsCredential for local development and ManagedIdentityCredential for production.

**Weigh up**Both install lines Microsoft prints for this skill, `npx skills add microsoft/skills --skill azure-sdk-rust` and `/plugin install azure-sdk-rust@skills`, install the whole azure-sdk-rust plugin rather than the identity skill alone.

 Source reviewed

6 sources · 2026-10-21

[Read the full review ↗](/skills/microsoft-azure-identity-rust/) Upstream setup linked MIT
 Compare Azure Identity library for Rust Add

Cloud development · Microsoft

### [Azure Identity library for TypeScript](/skills/microsoft-azure-identity-ts/)

Microsoft's TypeScript guide to @azure/identity: DefaultAzureCredential gated on AZURE_TOKEN_CREDENTIALS, managed and workload identity, service principals, browser and device-code sign-in, and bearer-token providers.

 identity entra-id default-azure-credential

**Why we selected it**Practice 1 puts DefaultAzureCredential on local development and ManagedIdentityCredential or WorkloadIdentityCredential on production, and both DefaultAzureCredential samples pass requiredEnvVars: ["AZURE_TOKEN_CREDENTIALS"].

**Weigh up**Both install lines Microsoft prints for this skill, `npx skills add microsoft/skills --skill azure-sdk-typescript` and `/plugin install azure-sdk-typescript@skills`, install the whole azure-sdk-typescript plugin rather than the identity skill alone.

 Source reviewed

6 sources · 2026-10-21

[Read the full review ↗](/skills/microsoft-azure-identity-ts/) Upstream setup linked MIT
 Compare Azure Identity library for TypeScript Add

Cloud development · Microsoft

### [Azure Key Vault Certificates library for Rust](/skills/microsoft-azure-keyvault-certificates-rust/)

Microsoft's Rust guide to azure_security_keyvault_certificates: creating a self-signed X.509 certificate as a long-running operation, updating, listing and deleting certificates, and signing with a certificate's key through the Key Vault keys crate.

 key-vault certificates x509

**Why we selected it**It shows begin_create_certificate returning a Poller that is awaited directly, with a certificate policy for subject CN=example.com and issuer Self.

**Weigh up**Both install lines Microsoft prints for this skill, `npx skills add microsoft/skills --skill azure-sdk-rust` and `/plugin install azure-sdk-rust@skills`, install the whole azure-sdk-rust plugin rather than the certificates skill alone.

 Source reviewed

6 sources · 2026-10-21

[Read the full review ↗](/skills/microsoft-azure-keyvault-certificates-rust/) Upstream setup linked MIT
 Compare Azure Key Vault Certificates library for Rust Add

Cloud development · microsoft

### [Azure Key Vault for Python](/skills/microsoft-azure-keyvault-py/)

Manage versioned secrets, keys and certificates while separating retrieval, cryptography and lifecycle operations.

 cloud-development microsoft

**Why we selected it**Secret listing in the sample returns properties, and the comment says that is names only, not values.

**Weigh up**The clients talk to the vault URL when the code runs. The skill does not create the vault or grant RBAC.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-keyvault-py/) Install command in review MIT
 Compare Azure Key Vault for Python Add

Cloud development · Microsoft

### [Azure Key Vault Keys (Java)](/skills/microsoft-azure-security-keyvault-keys-java/)

Microsoft's Java guide to com.azure:azure-security-keyvault-keys: creating RSA, EC and Managed HSM symmetric keys, importing key material, rotating by policy, and encrypting, signing and wrapping through CryptographyClient.

 key-vault cryptography azure

**Why we selected it**It builds sync, async and cryptography clients and creates RSA keys of 2048 and 4096 bits, EC keys on P-256, P-384 and P-521, HSM-backed variants, and a symmetric key marked Managed HSM only.

**Weigh up**Both install lines Microsoft prints for this skill, `npx skills add microsoft/skills --skill azure-sdk-java` and `/plugin install azure-sdk-java@skills`, install the whole azure-sdk-java plugin rather than the Key Vault keys skill alone.

 Source reviewed

6 sources · 2026-10-21

[Read the full review ↗](/skills/microsoft-azure-security-keyvault-keys-java/) Upstream setup linked MIT
 Compare Azure Key Vault Keys (Java) Add

Cloud development · Microsoft

### [Azure Key Vault Keys SDK for .NET](/skills/microsoft-azure-security-keyvault-keys-dotnet/)

Microsoft's .NET guide to Azure.Security.KeyVault.Keys: creating RSA, EC and symmetric keys in Key Vault or Managed HSM, rotating them by policy, and running encrypt, wrap and sign operations through CryptographyClient.

 key-vault cryptography dotnet

**Why we selected it**It walks the key lifecycle in one file: create RSA, EC and Oct keys, list versions, update properties, delete and purge, back up and restore, rotate, and set a policy that rotates 30 days before a 90-day expiry.

**Weigh up**Both install lines Microsoft prints for this skill, `npx skills add microsoft/skills --skill azure-sdk-dotnet` and `/plugin install azure-sdk-dotnet@skills`, install the whole azure-sdk-dotnet plugin rather than the Key Vault keys skill alone.

 Source reviewed

6 sources · 2026-10-21

[Read the full review ↗](/skills/microsoft-azure-security-keyvault-keys-dotnet/) Upstream setup linked MIT
 Compare Azure Key Vault Keys SDK for .NET Add

Cloud development · Microsoft

### [Azure Key Vault Keys SDK for TypeScript](/skills/microsoft-azure-keyvault-keys-ts/)

Microsoft's TypeScript guide to @azure/keyvault-keys for creating, rotating and deleting Key Vault keys and for encrypt, sign and wrap operations through CryptographyClient; the same file also carries secret operations.

 key-vault cryptography typescript

**Why we selected it**It creates keys four ways (generic RSA, RSA with keySize 2048, EC on P-256, and with keyOps, tags and an expiry), rotates a key on demand and sets a policy that rotates P30D before a P90D expiry.

**Weigh up**Both install lines Microsoft prints for this skill, `npx skills add microsoft/skills --skill azure-sdk-typescript` and `/plugin install azure-sdk-typescript@skills`, install the whole azure-sdk-typescript plugin rather than the keys skill alone.

 Source reviewed

6 sources · 2026-10-21

[Read the full review ↗](/skills/microsoft-azure-keyvault-keys-ts/) Upstream setup linked MIT
 Compare Azure Key Vault Keys SDK for TypeScript Add

Cloud development · Microsoft

### [Azure Key Vault Secrets library for Rust](/skills/microsoft-azure-keyvault-secrets-rust/)

Microsoft's Rust guide to azure_security_keyvault_secrets: setting, reading, tagging, deleting and listing Key Vault secrets, with a structured error for a missing secret.

 key-vault secrets rust

**Why we selected it**It covers set, get, update properties (content type and tags), delete, and paged listing of secret properties with SecretClient.

**Weigh up**Both install lines Microsoft prints for this skill, `npx skills add microsoft/skills --skill azure-sdk-rust` and `/plugin install azure-sdk-rust@skills`, install the whole azure-sdk-rust plugin rather than the secrets skill alone.

 Source reviewed

6 sources · 2026-10-21

[Read the full review ↗](/skills/microsoft-azure-keyvault-secrets-rust/) Upstream setup linked MIT
 Compare Azure Key Vault Secrets library for Rust Add

Cloud development · Microsoft

### [Azure Key Vault Secrets SDK for TypeScript](/skills/microsoft-azure-keyvault-secrets-ts/)

Microsoft's TypeScript guide to @azure/keyvault-secrets for setting, reading, versioning, deleting, recovering and backing up Key Vault secrets; the same file also carries key and cryptography operations.

 key-vault secrets typescript

**Why we selected it**It walks a secret's lifecycle: set it with enabled, expiresOn, contentType and tags, read the latest or a given version, list names and versions, soft-delete, purge and recover.

**Weigh up**Both install lines Microsoft prints for this skill, `npx skills add microsoft/skills --skill azure-sdk-typescript` and `/plugin install azure-sdk-typescript@skills`, install the whole azure-sdk-typescript plugin rather than the secrets skill alone.

 Source reviewed

6 sources · 2026-10-21

[Read the full review ↗](/skills/microsoft-azure-keyvault-secrets-ts/) Upstream setup linked MIT
 Compare Azure Key Vault Secrets SDK for TypeScript Add

Cloud operations · Microsoft

### [Azure Kubernetes](/skills/microsoft-azure-kubernetes/)

Pins Microsoft's AKS cluster skill, which refuses to print secrets or subscription identifiers and sends application deployment to a different skill.

 azure aks kubernetes

**Why we selected it**The guardrails forbid requesting or printing secrets and forbid asking the user to paste subscription IDs.

**Weigh up**The resource was not executed, and no Azure API, CLI, or MCP tool was called.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-kubernetes/) Install command in review MIT
 Compare Azure Kubernetes Add

Azure portal navigation · Microsoft

### [Azure portal search links](/skills/microsoft-azure-search-nav/)

Pins Microsoft's portal-link skill, which signs in with Connect-AzAccount or device code and only builds links for resource types listed as enabled.

 azure-portal authentication deep-link

**Why we selected it**The file names authentication as Connect-AzAccount or device code with -UseDeviceAuthentication, and a 401 tells the operator to sign in again with the tenant that can access the subscription.

**Weigh up**The resource was not executed.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-search-nav/) Upstream setup linked MIT
 Compare Azure portal search links Add

Azure SDKs · microsoft

### [Azure Queue Storage for Python](/skills/microsoft-azure-storage-queue-py/)

Review queue send, receive, visibility and deletion operations for Python workers.

 azure-sdks microsoft

**Why we selected it**The reference distinguishes peek from receive, exposes dequeue_count/visibility behavior and shows clear_messages as a destructive operation; current service docs require the latest valid pop receipt.

**Weigh up**Visibility is not an exclusive-processing guarantee. update_message returns a new pop receipt; the repeated-update example must retain the latest result. Approximate queue length is not an exact backlog count.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-storage-queue-py/) Install command in review MIT
 Compare Azure Queue Storage for Python Add

Cloud inventory · Microsoft

### [Azure Resource Lookup](/skills/microsoft-azure-resource-lookup/)

Pins Microsoft's Azure resource lookup skill, which refuses deployment and change requests and treats Resource Graph as read-only.

 azure resource-graph inventory

**Why we selected it**The description says not to use the skill to deploy or change resources, and the constraints say never to mutate through Resource Graph.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-resource-lookup/) Install command in review MIT
 Compare Azure Resource Lookup Add

Cloud architecture diagrams · Microsoft

### [Azure Resource Visualizer](/skills/microsoft-azure-resource-visualizer/)

Pins Microsoft's Azure resource visualizer, which diagrams one resource group, keeps secret values out of the drawing, and does not modify or delete resources.

 azure mermaid architecture

**Why we selected it**The never-do list says not to modify or delete Azure resources and calls the analysis read-only.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-resource-visualizer/) Install command in review MIT
 Compare Azure Resource Visualizer Add

Cloud development · microsoft

### [Azure Service Bus for Python](/skills/microsoft-azure-servicebus-py/)

Implement queue and topic consumers with explicit settlement, sessions and dead-letter handling.

 cloud-development microsoft

**Why we selected it**The skill text prefers DefaultAzureCredential and says connection strings bypass Entra audit, but the admin script uses SERVICEBUS_CONNECTION_STRING first when that variable is set.

**Weigh up**The script can create and delete Service Bus entities through the management API. It does not process the application messages themselves.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-servicebus-py/) Install command in review MIT
 Compare Azure Service Bus for Python Add

Azure SDKs · microsoft

### [Azure Tables for Python](/skills/microsoft-azure-data-tables-py/)

Review partition-aware entity operations and transactions for Azure Tables.

 azure-sdks microsoft

**Why we selected it**The reference submits one transaction for a shared partition and handles TableTransactionError; the definition distinguishes service-level table operations from entity-level client operations.

**Weigh up**TokenCredential support differs by endpoint: the current SDK documentation supports it for Storage Tables, not universally for Cosmos Table endpoints. Upsert alone does not protect concurrent writers or make arbitrary workflows idempotent.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-data-tables-py/) Install command in review MIT
 Compare Azure Tables for Python Add

Azure upgrades · Microsoft

### [Azure upgrade](/skills/microsoft-azure-upgrade/)

Pins Microsoft's in-Azure upgrade skill, which requires an assessment and an explicit confirmation before the original app is deleted or stopped.

 azure upgrade functions

**Why we selected it**The catalogue has other Azure skills from this repository and not this plan, SKU, Java SDK, and Redis upgrade procedure.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-upgrade/) Install command in review MIT
 Compare Azure upgrade Add

Azure deployment checks · Microsoft

### [Azure validate](/skills/microsoft-azure-validate/)

Pins Microsoft's pre-deploy Azure check, which stops without an approved plan and will not run azd deploy itself.

 azure validation deployment

**Why we selected it**The catalogue does not already have this gate between azure-prepare and azure-deploy.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-validate/) Install command in review MIT
 Compare Azure validate Add

Infrastructure · hashicorp

### [Azure Verified Module Review](/skills/hashicorp-azure-verified-modules/)

Review Terraform module structure against the pinned AVM requirements guide.

 infrastructure hashicorp

**Why we selected it**The guide separates mandatory and advisory requirements, requires registry version pins for AVM references and constrains resource for_each identities.

**Weigh up**This skill is guidance, not AVM certification. Provider ranges and requirement identifiers must be checked against current AVM specifications before submission.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/hashicorp-azure-verified-modules/) Install command in review MPL-2.0
 Compare Azure Verified Module Review Add

Azure Web PubSub · Microsoft

### [Azure Web PubSub Service Python](/skills/microsoft-azure-messaging-webpubsubservice-py/)

Pins the Web PubSub service Python skill, which prefers DefaultAzureCredential and says to limit client tokens with roles.

 azure web-pubsub entra-id

**Why we selected it**The authentication block prefers DefaultAzureCredential and says connection strings and account or API keys bypass Entra audit and rotation.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-messaging-webpubsubservice-py/) Install command in review MIT
 Compare Azure Web PubSub Service Python Add

Documentation and knowledge · Sentry

### [Blog writing guide](/skills/getsentry-blog-writing-guide/)

Applies one publisher's voice rules, including a banned-language list, and does not pretend that voice is universal.

 writing voice editing

**Why we selected it**The voice rules are publisher-specific, including a banned-phrase list and a named-author requirement.

**Weigh up**The opening must state the problem or the conclusion, not company history.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-blog-writing-guide/) Install command in review Apache-2.0
 Compare Blog writing guide Add

AI evaluation · Braintrust

### [Braintrust Build Eval Dataset](/skills/braintrustdata-braintrust-build-eval-dataset/)

Draft or audit an evaluation dataset's population, label provenance, transform invariants and split lifecycle. This is a review procedure, not an executable dataset validator.

 datasets validation provenance

**Why we selected it**Adds dataset construction and audit before the catalogue's existing sample-size and scorer-validation stages; it requires population and label provenance rather than treating more rows as better evidence.

**Weigh up**Instructions do not mechanically validate data, enforce test-touch counts or prove a corpus uncontaminated. Sample-size calculations and scorer implementations are explicitly outside this skill.

 Source reviewed

8 sources · 2026-10-15

[Read the full review ↗](/skills/braintrustdata-braintrust-build-eval-dataset/) Upstream setup linked Apache-2.0
 Compare Braintrust Build Eval Dataset Add

AI evaluation · Braintrust

### [Braintrust Define Eval Release Gate](/skills/braintrustdata-braintrust-define-eval-release-gate/)

Translate completed, intact evaluation evidence into owned ship-or-hold rules. Separates improvement targets from non-negotiable guardrails; does not implement or activate CI.

 evaluation release-gates reliability

**Why we selected it**Consumes a scorer-validation verdict and confirmatory results to produce an explicit decision contract, a different job from constructing data or computing sample size.

**Weigh up**No statistical engine or CI implementation is shipped in the selected directory. A written gate is not an enforced deployment block.

 Source reviewed

7 sources · 2026-10-15

[Read the full review ↗](/skills/braintrustdata-braintrust-define-eval-release-gate/) Upstream setup linked Apache-2.0
 Compare Braintrust Define Eval Release Gate Add

AI evaluation · Braintrust

### [Braintrust Design Eval Experiment](/skills/braintrustdata-braintrust-design-eval-experiment/)

Prepare a comparison manifest before inference: freeze the serving path, tool permissions, pairing, treatment implementation and stopping rules. It does not run an experiment.

 evaluation reproducibility batch-inference

**Why we selected it**Makes batching, provider, region, cache state and decoding part of the controlled comparison instead of treating a model name as a reproducible configuration.

**Weigh up**No batch submission, retry implementation, quota enforcement or provider integration is supplied. The manifest is a plan, not a run receipt.

 Source reviewed

7 sources · 2026-10-15

[Read the full review ↗](/skills/braintrustdata-braintrust-design-eval-experiment/) Upstream setup linked Apache-2.0
 Compare Braintrust Design Eval Experiment Add

Browser verification · addyosmani

### [Browser Testing with DevTools](/skills/addyosmani-browser-testing-with-devtools/)

Inspect real browser behavior, network activity and rendering through Chrome DevTools MCP.

 browser-verification addyosmani

**Why we selected it**The source explicitly distinguishes isolated/dedicated profiles from attaching to a running profile and treats DOM, console and network output as untrusted data.

**Weigh up**Accessibility-tree inspection is not a screen-reader test. Browser content is untrusted; attaching to an existing authenticated profile expands access to unrelated sessions.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/addyosmani-browser-testing-with-devtools/) Install command in review MIT
 Compare Browser Testing with DevTools Add

Developer Tools · Buf Technologies

### [Buf Protocol Buffers Design and Toolchain](/skills/buf-protobuf/)

Official Buf skill for Protocol Buffers (.proto) design, buf.yaml toolchain configuration, Connect/gRPC service authoring, and breaking change prevention.

 buf protobuf grpc

**Why we selected it**Protovalidate constraints are required on fields, not left as a later cleanup.

**Weigh up**The skill says not to invent a style when the repo has none; ask which style to copy.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/buf-protobuf/) Install command in review Apache-2.0
 Compare Buf Protocol Buffers Design and Toolchain Add

Testing and reliability · GitHub community

### [Bug Receipt](/skills/github-bug-receipt/)

Creates an evidence-bearing defect or incident handoff that distinguishes verified, partial and blocked outcomes.

 debugging verification incident-handoff

**Why we selected it**Requires the observed baseline, root-cause evidence, changed artifacts and relevant checks to accompany a completion status.

**Weigh up**The validator checks supplied fields and status consistency; it cannot prove that a command actually ran or that a claimed observation is correct.

 Source reviewed

11 sources · 2026-10-15

[Read the full review ↗](/skills/github-bug-receipt/) Install command in review MIT
 Compare Bug Receipt Add

Development workflow · GitHub community (awesome-copilot)

### [Bug Reproduction Brief](/skills/github-bug-reproduction-brief/)

Reduce an uncertain bug report to an evidence-backed failing fixture before repair.

 development-workflow github

**Why we selected it**The workflow stops at a reproduction, labels second-hand evidence unverified and restores the last removed condition when minimization loses the failure.

**Weigh up**Two successful reproductions do not prove determinism; production writes and sensitive records should not be used simply to increase confidence.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/github-bug-reproduction-brief/) Install command in review MIT
 Compare Bug Reproduction Brief Add

Model evaluation · MLflow

### [Build a Scorer](/skills/mlflow-build-a-scorer/)

Turns user-defined failure criteria into a small scorer implementation and validation plan, then hands registration and evaluation runs to a separate workflow.

 mlflow llm-as-judge scorers

**Why we selected it**Routes each atomic criterion to code, a matching built-in or an LLM judge, with an explicit why-not-cheaper justification and at least one user-outcome check.

**Weigh up**This is scorer design, not an end-to-end evaluation runner. Phase 8 assigns dataset creation, registration, runs and result interpretation to agent-evaluation, with tracing gaps handed to instrumenting-with-mlflow-tracing.

 Source reviewed

7 sources · 2026-10-14

[Read the full review ↗](/skills/mlflow-build-a-scorer/) Install command in review Apache-2.0
 Compare Build a Scorer Add

AI application development · Anthropic

### [Build an MCP App (Interactive UI Widgets)](/skills/anthropic-build-mcp-app/)

Adds interactive UI widgets (forms, pickers, confirm dialogs, charts) to an MCP server: the tool declares a ui:// resource, the server serves the widget HTML, and the host renders it in a sandboxed iframe in the chat.

 mcp forms csp

**Why we selected it**It says when a widget is worth building (structured input Claude cannot infer, picking from a list, confirming a destructive or billable action, visual output, live progress) and when elicitation covers the need with no UI code.

**Weigh up**Last commit touching plugins/mcp-server-dev/skills/build-mcp-app at revision 41f32e40: 2026-04-28 (f4b5494f).

 Source reviewed

4 sources · 2026-10-21

[Read the full review ↗](/skills/anthropic-build-mcp-app/) Upstream setup linked Apache-2.0
 Compare Build an MCP App (Interactive UI Widgets) Add

AI application development · Anthropic

### [Build an MCP Server](/skills/anthropic-build-mcp-server/)

Interviews the developer about an MCP server before any code, recommends one deployment model and a tool-design pattern, then scaffolds a remote or local stdio server or hands off to the MCP app or MCPB skill.

 mcp tools oauth

**Why we selected it**Before any scaffolding it asks five questions (what the server connects to, who will use it, how many actions it exposes, whether a tool needs mid-call input or rich UI, and the upstream auth) and then recommends one of four paths: remote streamable HTTP, MCP app, MCPB or local stdio.

**Weigh up**Last commit touching plugins/mcp-server-dev/skills/build-mcp-server at revision 41f32e40: 2026-04-17 (b00abee2).

 Source reviewed

7 sources · 2026-10-22

[Read the full review ↗](/skills/anthropic-build-mcp-server/) Upstream setup linked Apache-2.0
 Compare Build an MCP Server Add

AI application development · Anthropic

### [Build an MCPB (Bundled Local MCP Server)](/skills/anthropic-build-mcpb/)

Packages a local stdio MCP server with its runtime and dependencies into a .mcpb zip archive with a manifest.json, so a user can install it without setting up Node or Python.

 mcp packaging bundles

**Why we selected it**It defines an MCPB in the source's own terms: a zip archive holding manifest.json, the server code with its bundled dependencies and an icon, which the host launches as a stdio MCP server, built with npx @anthropic-ai/mcpb pack.

**Weigh up**Last commit touching plugins/mcp-server-dev/skills/build-mcpb at revision 41f32e40: 2026-04-17 (b00abee2).

 Source reviewed

4 sources · 2026-10-21

[Read the full review ↗](/skills/anthropic-build-mcpb/) Upstream setup linked Apache-2.0
 Compare Build an MCPB (Bundled Local MCP Server) Add

Research and evidence · GitHub community

### [Build Evidence Map](/skills/github-build-evidence-map/)

Builds a structured map of claims, evidence and unresolved gaps, with a local validator for the map’s structure.

 evidence research decision-records

**Why we selected it**Preserves supporting, contradicting, qualifying and missing evidence as separate relationships instead of flattening a contested choice into confident prose.

**Weigh up**The bundled validator checks structure and declared excerpts; it does not establish that a source is true or that the excerpt supports the claim.

 Source reviewed

11 sources · 2026-10-15

[Read the full review ↗](/skills/github-build-evidence-map/) Install command in review MIT
 Compare Build Evidence Map Add

Data engineering · dbt-labs

### [Build the dbt Semantic Layer](/skills/dbt-labs-building-dbt-semantic-layer/)

Define semantic entities, dimensions and metrics using the specification supported by the project.

 data-engineering dbt-labs

**Why we selected it**It builds dbt semantic models and metrics, and it chooses the latest or legacy spec from the project that is already there.

**Weigh up**The skill does not finish when only one of the two validations has passed.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/dbt-labs-building-dbt-semantic-layer/) Install command in review Apache-2.0
 Compare Build the dbt Semantic Layer Add

Security · trailofbits

### [Burp Project Parser](/skills/trailofbits-burpsuite-project-parser/)

Extract and search captured Burp traffic while distinguishing empty results from parser startup failures.

 security trailofbits

**Why we selected it**Parsing is delegated to a local Burp Suite Professional process. The skill text says it does not parse .burp files itself.

**Weigh up**The shell script launches the local burpsuite_pro.jar headless. It does not ship Burp and it does not open a new scan against a host.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-burpsuite-project-parser/) Install command in review CC-BY-SA-4.0
 Compare Burp Project Parser Add

Security · trailofbits

### [C and C++ Security Review](/skills/trailofbits-c-review/)

Coordinate scoped native C/C++ security review and assemble findings with an explicit coverage ledger.

 security trailofbits

**Why we selected it**The declared tools are Workflow, AskUserQuestion, Bash, and Read, and the assemble step is a local Python script run with uv.

**Weigh up**Bash can still write files even though Write is not listed. The skill does not itself compile or execute the program under review as a test.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-c-review/) Upstream setup linked CC-BY-SA-4.0
 Compare C and C++ Security Review Add

Development workflow · GitHub community (awesome-copilot)

### [C# / TypeScript API Contract Drift](/skills/github-api-breaking-change-detector/)

Compare C# controller and DTO contracts with TypeScript or JavaScript consumers in both directions.

 development-workflow github

**Why we selected it**It compares C# controller and DTO changes with TypeScript or JavaScript callers and writes a report instead of a patch.

**Weigh up**The skill does not modify code.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/github-api-breaking-change-detector/) Install command in review MIT
 Compare C# / TypeScript API Contract Drift Add

Testing · Trail of Bits

### [cargo-fuzz](/skills/trailofbits-cargo-fuzz/)

Requires the nightly toolchain and a fuzz_target harness before a Rust fuzz run counts.

 fuzzing rust cargo

**Why we selected it**The description names the nightly toolchain requirement.

**Weigh up**CC-BY-SA-4.0 applies to an adaptation you redistribute.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-cargo-fuzz/) Install command in review CC-BY-SA-4.0
 Compare cargo-fuzz Add

Browser extension connectivity · Trail of Bits

### [Chrome MCP troubleshooting](/skills/trailofbits-chrome-mcp-troubleshooting/)

Pins the macOS Chrome skill that refuses to leave both Claude native hosts active and says a fix does not apply until Chrome and Claude Code restart.

 chrome mcp macos

**Why we selected it**The file says the two native hosts cannot be used at the same time and tells the operator to disable the one that is not in use.

**Weigh up**The resource was not executed.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-chrome-mcp-troubleshooting/) Install command in review CC-BY-SA-4.0
 Compare Chrome MCP troubleshooting Add

Delivery automation · addyosmani

### [CI and Delivery Automation](/skills/addyosmani-ci-cd-and-automation/)

Design quality gates, previews and staged deployment around a reproducible CI workflow.

 delivery-automation addyosmani

**Why we selected it**The guide separates feature deployment from flag release, includes flag cleanup and treats CI failure output as a bounded feedback loop for agents.

**Weigh up**Example action/runtime versions require refresh; pipeline success is limited to its checks. Production migrations and external side effects may not be reversible by code rollback.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/addyosmani-ci-cd-and-automation/) Install command in review MIT
 Compare CI and Delivery Automation Add

Research and documentation · Anthropic

### [Claude Academy guide](/skills/anthropics-academy-guide/)

Answers a Claude how-to first, then may name at most two Academy items copied from a fetched catalog.

 learning claude catalog

**Why we selected it**It answers a Claude how-to first, then may name at most two Academy items copied from a fetched catalog.

**Weigh up**The skill embeds no course list; a recommendation depends on fetching https://academy.claude.com/assets/data/catalog.json.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/anthropics-academy-guide/) Attributed definition available Apache-2.0
 Compare Claude Academy guide Add

Claude Code automation · Anthropic

### [Claude automation recommender](/skills/anthropic-claude-automation-recommender/)

Pins the Claude Code setup skill that recommends hooks, skills, and MCP servers and says this skill must not create or modify files.

 claude-code automations hooks

**Why we selected it**The skill says it is read-only, does not create or modify files, and tells the user to implement recommendations separately.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/anthropic-claude-automation-recommender/) Upstream setup linked Apache-2.0
 Compare Claude automation recommender Add

Security review · Anthropic

### [Claude Security](/skills/anthropic-claude-security/)

Runs Anthropic's Claude Security scans inside a Claude Code session: a whole-repository or scoped scan, a scan of a branch, pull request or commit, and suggested fixes as patch files the user applies.

 security-review vulnerability-research patches

**Why we selected it**The README calls it the in-your-session version of Anthropic's hosted Claude Security product: one skill that drives three jobs, scan codebase, scan changes and suggest patches, through the plugin's own scan workflow and agents.

**Weigh up**Proprietary licence. The LICENSE grants a limited, revocable licence "to install, run, and modify the Plugin for your internal use, solely with Claude Code or other Anthropic products and services", and, "Except as the Agreement expressly permits", forbids using "the Plugin or any part of it with, or to develop, any non-Anthropic product or service, including any competing product", as well as distributing or publishing it to any third party.

 Source reviewed

21 sources · 2026-10-22

[Read the full review ↗](/skills/anthropic-claude-security/) Install command in review Proprietary (Anthropic, PBC)
 Compare Claude Security Add

CLAUDE.md maintenance · Anthropic

### [CLAUDE.md improver](/skills/anthropic-claude-md-improver/)

Pins the CLAUDE.md skill that must print a quality report and wait for approval before it edits those files.

 claude-md audit confirmation

**Why we selected it**The skill says it can write CLAUDE.md files only after it presents a quality report and the user approves.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/anthropic-claude-md-improver/) Upstream setup linked Apache-2.0
 Compare CLAUDE.md improver Add

Agent development · Cloudflare

### [Cloudflare Agents SDK](/skills/cloudflare-agents-sdk/)

Guides stateful Cloudflare agent applications through current SDK documentation, persistence, scheduling and approval-aware tool flows.

 cloudflare agents durable-state

**Why we selected it**Treats installed SDK versions and current docs as the basis for implementation.

**Weigh up**This is specific to Cloudflare’s Agents SDK and runtime, not a general multi-provider agent framework.

 Source reviewed

8 sources · 2026-10-15

[Read the full review ↗](/skills/cloudflare-agents-sdk/) Install command in review Apache-2.0
 Compare Cloudflare Agents SDK Add

Analytics pipelines · Cloudflare

### [Cloudflare Basin](/skills/cloudflare-basin/)

Pins Cloudflare's Basin skill, which names the SQL auth token and says to check the installed Wrangler version before running the new basin commands.

 cloudflare basin wrangler

**Why we selected it**Basin SQL is tied to the WRANGLER_BASIN_SQL_AUTH_TOKEN variable and the REST path /basin-sql/query/{BUCKET}.

**Weigh up**The file names the SQL auth token and a pre-command version check. It does not show a delete, a dry-run, or a refusal to start a pipeline.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/cloudflare-basin/) Install command in review Apache-2.0
 Compare Cloudflare Basin Add

Cloud operations · Cloudflare

### [Cloudflare cf CLI](/skills/cloudflare-cf-cli/)

Pins Cloudflare's cf CLI skill, which tells an agent to search the local command index and to keep Wrangler when a Wrangler config is already present.

 cloudflare cli wrangler

**Why we selected it**The catalogue already has Wrangler, Workers, and Turnstile skills from this repository and not the cf CLI skill.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/cloudflare-cf-cli/) Install command in review Apache-2.0
 Compare Cloudflare cf CLI Add

Cloud development · Cloudflare

### [Cloudflare Durable Objects](/skills/cloudflare-durable-objects/)

Designs per-entity state and coordination with explicit persistence, concurrency and runtime-test guidance.

 cloudflare durable-objects sqlite

**Why we selected it**Defines where Durable Objects fit and where stateless Workers or independent requests fit better.

**Weigh up**A single coordination object can become a bottleneck; object boundaries must fit the workload.

 Source reviewed

8 sources · 2026-10-15

[Read the full review ↗](/skills/cloudflare-durable-objects/) Install command in review Apache-2.0
 Compare Cloudflare Durable Objects Add

Cloud development · Cloudflare

### [Cloudflare Email Service](/skills/cloudflare-email-service/)

Implements Cloudflare Email Sending and Email Routing: Workers send_email bindings, the REST API, inbound email() handlers, wrangler setup, and deliverability (SPF/DKIM/DMARC, bounces, suppression lists) — with the field-naming asymmetries between binding and REST spelled out.

 email transactional-email cloudflare-workers

**Why we selected it**Takes a retrieval-over-pre-training stance with named retrieval sources, the right posture for a 2025-launched product whose API surface is still moving.

**Weigh up**Cloudflare-platform-only: the binding, wrangler commands and REST endpoints are Cloudflare’s, not general SMTP or templating guidance.

 Source reviewed

7 sources · 2026-10-15

[Read the full review ↗](/skills/cloudflare-email-service/) Install command in review Apache-2.0
 Compare Cloudflare Email Service Add

Web Frameworks · Cloudflare

### [Cloudflare Migrate to vinext](/skills/cloudflare-migrate-to-vinext/)

Migrates Next.js applications to Cloudflare Workers via vinext (Vite-based Next.js reimplementation), handling ESM conversions and worker deployment.

 cloudflare vinext nextjs

**Why we selected it**Migration is defined as a package and config change, not an application rewrite.

**Weigh up**The file says not to rewrite next/* imports and not to copy webpack or Turbopack config into Vite.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/cloudflare-migrate-to-vinext/) Install command in review MIT
 Compare Cloudflare Migrate to vinext Add

Cloud security · cloudflare

### [Cloudflare One Architecture and Troubleshooting](/skills/cloudflare-cloudflare-one/)

Plan or troubleshoot Access, Gateway, device clients, private networks, DLP and CASB from the actual traffic path.

 cloud-security cloudflare

**Why we selected it**It is an architecture and troubleshooting map for Cloudflare One that refuses guessed API identifiers.

**Weigh up**The skill retrieves current docs and does not embed the live API schema.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/cloudflare-cloudflare-one/) Install command in review Apache-2.0
 Compare Cloudflare One Architecture and Troubleshooting Add

Network migration · Cloudflare

### [Cloudflare One migrations](/skills/cloudflare-one-migrations/)

Pins Cloudflare's One migration skill, which stages rules disabled and refuses placeholder DLP and unapproved deletion of stale rules.

 cloudflare zero-trust migration

**Why we selected it**The catalogue has the Cloudflare One product skill from this commit and not this migration assessment file.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/cloudflare-one-migrations/) Install command in review Apache-2.0
 Compare Cloudflare One migrations Add

Product selection · Cloudflare

### [Cloudflare product discovery](/skills/cloudflare-cloudflare/)

Pins Cloudflare's product-discovery skill, which blocks a new Wrangler setup, runs cf migrate only when asked, and says a version rollback does not restore resource data.

 cloudflare wrangler workers

**Why we selected it**A project that is not already on Wrangler must stay on cf: the file says not to install Wrangler or create a Wrangler configuration file, and to run cf migrate only when the user asks.

**Weigh up**The product table still names the wrangler skill for C3. The CLI section says that where the table names a Wrangler command or file, the cf equivalent is used instead of translating from memory.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/cloudflare-cloudflare/) Install command in review Apache-2.0
 Compare Cloudflare product discovery Add

Sandbox development · Cloudflare

### [Cloudflare Sandbox next](/skills/cloudflare-sandbox-next/)

Pins Cloudflare's sandbox-next skill, which stops on the stable package, refuses a mixed preview image, and keeps live credentials in the Worker.

 cloudflare sandbox containers

**Why we selected it**The file says to stop when the app uses the default @cloudflare/sandbox package, and not to mix an @next Worker package with a stable container image.

**Weigh up**Several different tasks in the retrieval table share the URL https://developers.cloudflare.com/sandbox/index.md, so the table does not by itself distinguish those pages.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/cloudflare-sandbox-next/) Install command in review Apache-2.0
 Compare Cloudflare Sandbox next Add

Cloud operations · Cloudflare

### [Cloudflare Sandbox preview migration](/skills/cloudflare-sandbox-migrate-to-next/)

Pins Cloudflare's stable-to-preview Sandbox migration, which refuses an unagreed production cutover and forbids invented APIs and live secrets in the sandbox environment.

 cloudflare sandbox workers

**Why we selected it**The catalogue has sandbox-stable from this commit and not the migration off that stable package.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/cloudflare-sandbox-migrate-to-next/) Install command in review Apache-2.0
 Compare Cloudflare Sandbox preview migration Add

Cloud development · cloudflare

### [Cloudflare Sandbox Stable SDK](/skills/cloudflare-sandbox-stable/)

Maintain existing stable Sandbox SDK applications without mixing preview package, image, command or terminal APIs.

 cloud-development cloudflare

**Why we selected it**It keeps stable @cloudflare/sandbox code on the stable command APIs and stops a half-applied move to @next.

**Weigh up**The skill is not a full SDK manual and does not vendor the command signatures.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/cloudflare-sandbox-stable/) Install command in review Apache-2.0
 Compare Cloudflare Sandbox Stable SDK Add

Security · Cloudflare

### [Cloudflare Turnstile Spin](/skills/cloudflare-turnstile-spin/)

Integrate a Turnstile widget with an existing frontend and server-side Siteverify, including secret-safe helpers and replay validation.

 turnstile bot-management captcha-migration

**Why we selected it**It wires Cloudflare Turnstile into an existing frontend and backend, with server-side siteverify and a token that is not pasted into chat.

**Weigh up**A pure-static site with no backend is out of scope, because siteverify needs a server.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/cloudflare-turnstile-spin/) Install command in review Apache-2.0
 Compare Cloudflare Turnstile Spin Add

Web performance · Cloudflare

### [Cloudflare Web Performance Audit](/skills/cloudflare-web-perf/)

Builds a performance review from browser traces, request details and relevant source instead of generic optimization advice.

 core-web-vitals devtools lighthouse

**Why we selected it**Starts by discovering available measurement tools and records measurements it could not collect.

**Weigh up**A lab trace does not establish real-user Core Web Vitals or prove a resource is unused in every interaction.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/cloudflare-web-perf/) Install command in review Apache-2.0
 Compare Cloudflare Web Performance Audit Add

Cloud development · Cloudflare

### [Cloudflare Workers Best Practices](/skills/cloudflare-workers-best-practices/)

Reviews Workers code against its configured runtime, focusing on request lifetime, state isolation, streaming and binding contracts.

 workers cloudflare streaming

**Why we selected it**Uses installed types and compatibility settings instead of assuming the newest package defines the current runtime.

**Weigh up**Workers-specific guidance is not interchangeable with a Node server checklist.

 Source reviewed

7 sources · 2026-10-15

[Read the full review ↗](/skills/cloudflare-workers-best-practices/) Install command in review Apache-2.0
 Compare Cloudflare Workers Best Practices Add

Performance · cloudflare

### [Cloudflare Workers Production Profiling](/skills/cloudflare-workers-profiling/)

Capture CPU or heap profiles for a specific deployed Worker or Durable Object and turn pprof evidence into a focused optimization proposal.

 performance cloudflare

**Why we selected it**It profiles deployed Workers and Durable Objects by capturing a pprof file and mapping hotspots back to source.

**Weigh up**The skill does not install cf and does not start a profile without the account, Worker, and deployed version.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/cloudflare-workers-profiling/) Install command in review Apache-2.0
 Compare Cloudflare Workers Production Profiling Add

Cloud operations · Cloudflare

### [Cloudflare Wrangler Workflow](/skills/cloudflare-wrangler/)

Runs Wrangler work in projects that already have a Wrangler configuration file, against the installed Wrangler version and an explicitly identified target.

 wrangler cloudflare deployment

**Why we selected it**Distinguishes local simulation from remote bindings so development commands are not assumed to be harmless.

**Weigh up**The skill authorizes no cloud action by itself; commands can deploy or mutate real resources.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/cloudflare-wrangler/) Install command in review Apache-2.0
 Compare Cloudflare Wrangler Workflow Add

Databases · Cockroach Labs

### [CockroachDB SQL](/skills/cockroachlabs-cockroachdb-sql/)

Cockroach Labs skill that turns a natural-language request into CockroachDB SQL, applies the relevant rule files with 00-fundamental-principles.md first, and tells the agent to run EXPLAIN on every generated query when a cluster connection is available.

 sql schema explain

**Why we selected it**SKILL.md marks plan validation as mandatory: when connected, it tells the agent to run EXPLAIN on every generated query, fix and re-run it after a parsing or syntax error, and include the EXPLAIN output in the response.

**Weigh up**The skill directory skills/cockroachdb-query-and-schema-design/cockroachdb-sql last changed in a commit dated 2026-07-22, which is also the date of the pinned revision.

 Source reviewed

9 sources · 2026-10-21

[Read the full review ↗](/skills/cockroachlabs-cockroachdb-sql/) Upstream setup linked Apache-2.0
 Compare CockroachDB SQL Add

Autonomous review loop · Trail of Bits

### [Code improver](/skills/trailofbits-code-improver/)

Pins the generic review loop that will not choose a reviewer, will not start on an unconfirmed scope, and will not commit.

 review workflow scope

**Why we selected it**The user must name the reviewer, there is no default, and a missing name is a question rather than a guess.

**Weigh up**The resource was not executed.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-code-improver/) Install command in review CC-BY-SA-4.0
 Compare Code improver Add

Security review · Trail of Bits

### [CodeQL](/skills/trailofbits-codeql/)

Drives a CodeQL scan and warns that each Bash call is a fresh shell, so state must be written to files.

 codeql static-analysis security

**Why we selected it**A heading states that each Bash call is a fresh shell.

**Weigh up**CC-BY-SA-4.0 applies to adaptations you redistribute.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-codeql/) Install command in review CC-BY-SA-4.0
 Compare CodeQL Add

Documentation · getsentry

### [Collaborative Document Drafting](/skills/getsentry-doc-coauthoring/)

Build a substantial document through context gathering, section refinement and reader testing.

 documentation getsentry

**Why we selected it**The workflow offers a freeform alternative, separates context from refinement and uses a reader without the original conversation to find hidden assumptions.

**Weigh up**A fresh-model reading test detects ambiguities but cannot verify factual claims or stakeholder agreement. The fixed image-access assumption depends on the actual host.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-doc-coauthoring/) Install command in review Apache-2.0
 Compare Collaborative Document Drafting Add

Agent development · Anthropic

### [Command Development for Claude Code](/skills/anthropic-command-development/)

Explains how to write Claude Code slash-command files: frontmatter fields, $ARGUMENTS and positional arguments, @file references, inline Bash and plugin command patterns.

 claude-code plugin-dev prompts

**Why we selected it**It covers the five command frontmatter fields it names (description, allowed-tools, model, argument-hint, disable-model-invocation) together with $ARGUMENTS, $1/$2 positional arguments, @file references and inline Bash.

**Weigh up**Last commit touching plugins/plugin-dev/skills/command-development at revision 41f32e40: 2026-03-17 (6b70f99f).

 Source reviewed

5 sources · 2026-10-21

[Read the full review ↗](/skills/anthropic-command-development/) Upstream setup linked Apache-2.0
 Compare Command Development for Claude Code Add

Model evaluation · Replicate

### [Compare Replicate Models](/skills/replicate-compare-models/)

Shortlists Replicate models and compares them on measured cost, prediction time, output quality and input schema.

 replicate model-selection inference-cost

**Why we selected it**It tells the agent to run a few predictions and read the metrics field for actual cost and predict_time instead of assuming them.

**Weigh up**Test predictions are billed, and the file asks for no cost confirmation before running them.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/skills/replicate-compare-models/) Install command in review Apache-2.0
 Compare Compare Replicate Models Add

Security review · Trail of Bits

### [Constant-time analysis](/skills/trailofbits-constant-time-analysis/)

Routes a timing review by language and says when not to use the analyzer.

 cryptography timing side-channels

**Why we selected it**The description names secret-dependent branches and division on secrets.

**Weigh up**CC-BY-SA-4.0 applies to an adaptation you redistribute.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-constant-time-analysis/) Install command in review CC-BY-SA-4.0
 Compare Constant-time analysis Add

Testing · trailofbits

### [Constant-Time Runtime Testing](/skills/trailofbits-constant-time-testing/)

Design statistical and dynamic tests for secret-dependent timing in cryptographic implementations.

 testing trailofbits

**Why we selected it**The file is a handbook for measuring a running cryptographic implementation, and it sends static compiler inspection to a different plugin.

**Weigh up**There is no allowed-tools list and no bundled runner. Links to papers and tools are references. The file does not vendor dudect or Timecop.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-constant-time-testing/) Install command in review CC-BY-SA-4.0
 Compare Constant-Time Runtime Testing Add

Development workflow · Addy Osmani

### [Constraint-driven development](/skills/addyosmani-constraint-driven-development/)

Writes the quality bar down and watches the diff for a weakened gate.

 quality constraints ratchet

**Why we selected it**The quality bar is a CONSTRAINTS.md file with a tool behind each number, not a verbal standard.

**Weigh up**The interview must not run in CI, /loop, or other non-interactive contexts.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/addyosmani-constraint-driven-development/) Install command in review MIT
 Compare Constraint-driven development Add

Agent development · Addy Osmani

### [Context engineering](/skills/addyosmani-context-engineering/)

Orders agent context as a hierarchy instead of dumping the repository into the prompt.

 context agents instructions

**Why we selected it**It orders context in five levels, from rules files to conversation history, and says what to load at each level and when.

**Weigh up**Its thresholds (trim at 75% of the window, about 2,000 lines of focused context per task) are the author's guidance, not measurements this review checked.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/addyosmani-context-engineering/) Install command in review MIT
 Compare Context engineering Add

Planning and delivery · GitHub community

### [Conventional Branch](/skills/github-conventional-branch/)

Creates and validates Git branches against the Conventional Branch specification — feature/, bugfix/, hotfix/, release/, chore/ — with a validation ruleset, an invalid-example table, trunk detection and a mapping to Conventional Commits.

 git branching branch-naming

**Why we selected it**Turns branch naming from a style argument into a validation ruleset — lowercase only, no consecutive hyphens, dots only in release/ version descriptions — with an invalid-example table that shows each rule being broken.

**Weigh up**The Conventional Branch specification is a community convention, not something git enforces. The skill ships no linter or hook, so names are checked only while the agent runs.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/github-conventional-branch/) Install command in review MIT
 Compare Conventional Branch Add

Planning and delivery · Matt Pocock

### [Conversation to Specification](/skills/mattpocock-to-spec/)

Turns an already-discussed change into a repository-aware specification for the configured issue tracker.

 specification planning github

**Why we selected it**Uses existing project context, glossary and architecture decisions before synthesizing requirements.

**Weigh up**This is synthesis after discussion, not a discovery interview or a check that every stakeholder requirement is present.

 Source reviewed

16 sources · 2026-10-15

[Read the full review ↗](/skills/mattpocock-to-spec/) Install command in review MIT
 Compare Conversation to Specification Add

Web performance · Addy Osmani

### [Core Web Vitals](/skills/addyosmani-core-web-vitals/)

Diagnoses LCP, INP and CLS from field evidence first — CrUX p75 with a labelled origin fallback, then a browser trace — and routes to per-metric references, with explicit rules against claiming field improvement from a lab run.

 core-web-vitals lcp inp

**Why we selected it**Measurement discipline is the spine: CrUX p75 first with a labelled fallback when page-level data is missing, trace analysis of only the failing metric's insights, and re-measurement after the fix with field verification explicitly deferred until new user data exists.

**Weigh up**Cross-links the sibling performance skill's references (../performance/references/MEASUREMENT.md and RUM.md); installing core-web-vitals alone leaves those two links dangling.

 Source reviewed

7 sources · 2026-10-15

[Read the full review ↗](/skills/addyosmani-core-web-vitals/) Install command in review MIT
 Compare Core Web Vitals Add

Azure cost governance · Microsoft

### [Cost Governance](/skills/microsoft-cost-governance/)

Pins Microsoft's cost-governance skill, which requires a confirmed scope and amount before a budget write and keeps the existing budget on conflict.

 azure-cost budget confirmation

**Why we selected it**Budget setup is a write, and the file requires confirmed scope, amount, thresholds, and recipients before that write.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-cost-governance/) Install command in review MIT
 Compare Cost Governance Add

Testing · Trail of Bits

### [Coverage analysis](/skills/trailofbits-coverage-analysis/)

Turns an uncovered region into the next harness or seed change, instead of treating a long run as done.

 fuzzing coverage llvm

**Why we selected it**The description says to use it when a fuzzer plateaus.

**Weigh up**CC-BY-SA-4.0 applies to an adaptation you redistribute.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-coverage-analysis/) Install command in review CC-BY-SA-4.0
 Compare Coverage analysis Add

Web performance · Microsoft

### [CPU Profile Analysis](/skills/microsoft-cpu-profile-analysis/)

Walks an agent through analyzing V8 CPU profiles (.cpuprofile) and Chrome DevTools trace files: parsing large files safely, reconstructing call trees from sampling data, measuring self versus total time, and comparing code paths.

 profiling cpu-profile flamegraph

**Why we selected it**Sets out the sampling-profiler basics before any tooling: self versus total time, idle/program/GC samples, and that a function missing from the samples is expected rather than suspicious.

**Weigh up**Sampling data is statistical, not exact: the skill itself warns that per-function attribution is approximate and marker-based region detection tolerates gaps.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-cpu-profile-analysis/) Install command in review MIT
 Compare CPU Profile Analysis Add

Security review · Trail of Bits

### [Crypto Protocol Diagram](/skills/trailofbits-trailmark-crypto-protocol-diagram/)

Extracts a cryptographic protocol's message flow from source, an RFC, a paper, pseudocode, a ProVerif model or a Tamarin model, writes it as an annotated Mermaid sequence diagram in a Markdown file and prints an ASCII version.

 cryptography protocol mermaid

**Why we selected it**Produces a Mermaid sequenceDiagram in a Markdown file, plus an ASCII diagram printed inline, from protocol source code or a spec: RFC, paper, pseudocode, prose, ProVerif (.pv) or Tamarin (.spthy).

**Weigh up**It diagrams protocol flow; for formal verification its SKILL.md points to mermaid-to-proverif.

 Source reviewed

5 sources · 2026-10-22

[Read the full review ↗](/skills/trailofbits-trailmark-crypto-protocol-diagram/) Upstream setup linked CC-BY-SA-4.0
 Compare Crypto Protocol Diagram Add

Data and analytics · Cube

### [Cube build model](/skills/cube-cube-build-model/)

Cube's skill for authoring and changing a Cube semantic model in YAML on a dev-mode branch, through the Cube MCP tools or the Cube CLI, with validation, commit, and publishing only on an explicit request.

 analytics data-models metrics

**Why we selected it**Spells out the write loop for both paths: seven Cube MCP tool steps (startDataModelEdit, read, writeDataModelFile with its recompile and validationError, getDataModelChanges, searchDataModel and runQuery on the same branchName, commitDataModelChanges, then mergeToDefaultBranch only on an explicit publish request) and an eight-step CLI dev-mode block that ends with build-status --wait and exit-dev-mode.

**Weigh up**The skill directory skills/cube-build-model last changed in a commit dated 2026-09-23 (git log at the pin), the same date as the pinned revision 5e5ef13c.

 Source reviewed

5 sources · 2026-10-21

[Read the full review ↗](/skills/cube-cube-build-model/) Upstream setup linked Apache-2.0
 Compare Cube build model Add

AI application development · Datadog Labs

### [Datadog LLM Observability Instrumentation](/skills/datadog-labs-dd-instrument-llmo/)

Instruments a Python or Node.js/Next.js backend with Datadog LLM Observability, auditing session-ID plumbing and persisting the dependency before reporting.

 llm-observability instrumentation ddtrace

**Why we selected it**Runs detection before editing: runtime, LLM framework, app framework, existing instrumentation, and the manifest to persist into are all identified in Phase 1.

**Weigh up**Edits source and dependency manifests, so every change needs review and a test run before it ships.

 Source reviewed

8 sources · 2026-10-15

[Read the full review ↗](/skills/datadog-labs-dd-instrument-llmo/) Install command in review MIT
 Compare Datadog LLM Observability Instrumentation Add

Model evaluation · Datadog Labs

### [Datadog Trace RCA](/skills/datadog-labs-agent-observability-trace-rca/)

Root-causes production AI failures from LLM traces through phased span analysis, then recommends prompt, tool, routing or retrieval changes quoted from the trace evidence.

 eval root-cause-analysis llm-traces

**Why we selected it**Structures the analysis as explicit phases from input resolution through open and axial coding to recommendations, instead of offering generic debugging advice.

**Weigh up**Requires either the Datadog LLMO MCP toolset or the pup CLI with usable authentication and existing LLM Observability traces.

 Source reviewed

7 sources · 2026-10-15

[Read the full review ↗](/skills/datadog-labs-agent-observability-trace-rca/) Install command in review MIT
 Compare Datadog Trace RCA Add

Data engineering · dbt-labs

### [dbt Analytics Engineering](/skills/dbt-labs-using-dbt-for-analytics-engineering/)

Build and revise transformations with source profiling, explicit lineage and targeted validation.

 data-engineering dbt-labs

**Why we selected it**It builds and changes dbt models with a shell limited to dbt and jq, and it requires dbt show before the work is called done.

**Weigh up**The allowed shell is dbt and jq, not an unrestricted Bash.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/dbt-labs-using-dbt-for-analytics-engineering/) Install command in review Apache-2.0
 Compare dbt Analytics Engineering Add

Analytics engineering · dbt Labs

### [dbt Core to v2 migration triage](/skills/dbt-labs-migrating-dbt-core-to-v2/)

Pins dbt Labs' v2 migration triage, which asks before a credential check and forbids edits until autofix changes have been reviewed.

 dbt migration credentials

**Why we selected it**The catalogue has other dbt skills from this repository, including upgrading-dbt, and not this Core-to-v2 triage procedure.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/dbt-labs-migrating-dbt-core-to-v2/) Install command in review Apache-2.0
 Compare dbt Core to v2 migration triage Add

Databases · dbt Labs

### [dbt Documentation Maintenance](/skills/dbt-labs-maintaining-dbt-documentation/)

Audits descriptions in a dbt manifest and drafts missing model or column documentation in the project’s existing style.

 dbt documentation sql

**Why we selected it**Uses dbt’s resolved manifest rather than guessing YAML layout, and clearly limits column coverage to columns declared in that manifest.

**Weigh up**The audit measures nonempty descriptions, not their correctness or every physical warehouse column; imported model nodes can also appear in a manifest.

 Source reviewed

9 sources · 2026-10-15

[Read the full review ↗](/skills/dbt-labs-maintaining-dbt-documentation/) Install command in review Apache-2.0
 Compare dbt Documentation Maintenance Add

MCP configuration · dbt Labs

### [dbt MCP server configuration](/skills/dbt-labs-configuring-dbt-mcp-server/)

Pins dbt Labs' MCP setup skill, which keeps tokens out of committed config and leaves SQL and codegen off until their flags are changed.

 dbt mcp token

**Why we selected it**Configuration that may be committed must use environment-variable references, and the file says never to log, display, or echo token values.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/dbt-labs-configuring-dbt-mcp-server/) Install command in review Apache-2.0
 Compare dbt MCP server configuration Add

Data engineering · dbt-labs

### [dbt State Reuse](/skills/dbt-labs-using-dbt-state/)

Configure and investigate server-backed reuse decisions separately from manifest selectors and deferral.

 data-engineering dbt-labs

**Why we selected it**It explains dbt State as a paid server that can skip or clone a node, and it separates that from state:modified.

**Weigh up**dbt State is not local and is not free.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/dbt-labs-using-dbt-state/) Install command in review Apache-2.0
 Compare dbt State Reuse Add

Infrastructure development · Pulumi

### [Debug a Failed Pulumi Operation](/skills/pulumi-pulumi-debug-failed-operation/)

Reads the diagnostics Pulumi already recorded for a failed update or preview and places the fix in the program, state or environment.

 pulumi infrastructure-as-code debugging

**Why we selected it**It reads the recorded engine events with pulumi api instead of re-running the failed operation, and confirms the stack and version with the user before reading further.

**Weigh up**The file only describes records read from Pulumi Cloud through pulumi api, and its commands need jq.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/pulumi-pulumi-debug-failed-operation/) Install command in review Apache-2.0
 Compare Debug a Failed Pulumi Operation Add

Model evaluation · Confident AI

### [DeepEval](/skills/confident-ai-deepeval/)

Confident AI's skill for adding a committed pytest eval suite to an AI agent, RAG pipeline, chatbot or LLM app: it reuses the user's dataset or else generates goldens with deepeval generate, runs deepeval test run and changes the app between rounds based on the failures.

 evaluations eval testing

**Why we selected it**Confident AI publishes it in confident-ai/deepeval at skills/deepeval, with frontmatter license Apache-2.0, author Confident AI and version 1.0.0, ten reference files and four templates: single-turn tracing, single-turn no tracing, multi-turn end to end, and shared metric lists.

**Weigh up**The skills/deepeval directory last changed in a commit dated 2026-05-21; the pinned revision 59a4f00a is dated 2026-10-16.

 Source reviewed

11 sources · 2026-10-21

[Read the full review ↗](/skills/confident-ai-deepeval/) Upstream setup linked Apache-2.0
 Compare DeepEval Add

Development workflow · Deno Land Inc.

### [Deno](/skills/denoland-deno/)

Deno's own skill for Deno 2.9+ projects that keep package.json, commit deno.lock, and do not run npm lifecycle scripts unless they are approved.

 deno typescript javascript

**Why we selected it**The catalogue has no Deno skill.

**Weigh up**This review did not execute the skill or run Deno.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/denoland-deno/) Install command in review MIT
 Compare Deno Add

Security · GitHub community

### [Dependabot](/skills/github-dependabot/)

Configures and manages Dependabot end to end: ecosystem detection across 25+ package managers, monorepo glob directories, grouped and multi-ecosystem updates, cooldown periods, ignore and allow rules, and PR command etiquette including the January 2026 deprecations.

 dependabot dependencies supply-chain

**Why we selected it**Covers the configuration surface teams actually trip on: plural directories with globs for monorepos versus the glob-less singular directory, grouped updates by type and name pattern, and cooldown periods that delay adopting freshly released versions.

**Weigh up**GitHub-product-specific: Renovate, GitLab dependency bots and other updaters share concepts but not this configuration surface.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/github-dependabot/) Install command in review MIT
 Compare Dependabot Add

Cloud operations · Microsoft

### [Deploy to AKS](/skills/microsoft-azure-kubernetes-app-deploy/)

Pins Microsoft's skill for deploying an existing web app to a running AKS cluster, which requires az login and refuses to provision the cluster.

 azure aks kubernetes

**Why we selected it**The workflow line requires an existing AKS cluster, az login, and a configured kubectl before deployment.

**Weigh up**The resource was not executed, and no Azure API, CLI, or MCP tool was called.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-kubernetes-app-deploy/) Install command in review MIT
 Compare Deploy to AKS Add

Software architecture · addyosmani

### [Deprecation and Migration Planning](/skills/addyosmani-deprecation-and-migration/)

Plan incremental retirement of APIs, systems and database schema with consumer migration evidence.

 software-architecture addyosmani

**Why we selected it**The guide distinguishes advisory from compulsory deprecation and assigns migration responsibility to infrastructure owners rather than merely announcing a deadline.

**Weigh up**A rollback deployment cannot undo arbitrary data loss; zero observed traffic does not prove no offline or external consumer remains.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/addyosmani-deprecation-and-migration/) Install command in review MIT
 Compare Deprecation and Migration Planning Add

Data pipelines · Confluent

### [Developing Kafka Python client](/skills/confluent-developing-kafka-python-client/)

Confluent skill that scaffolds a confluent-kafka-python producer, consumer or both, or adds Schema Registry to existing Python code, for Confluent Cloud, local Docker or WarpStream, after a confirmation step its instructions require.

 streaming python confluent

**Why we selected it**SKILL.md tells the agent that Schema Registry is non-negotiable in every project, to register schemas in an explicit register_schema() step, and to configure serializers with auto.register.schemas=False and use.latest.version=True.

**Weigh up**The skill directory skills/developing-kafka-python-client last changed in a commit dated 2026-08-24; the pinned revision is dated 2026-10-06. SKILL.md metadata says version 1.0.0.

 Source reviewed

9 sources · 2026-10-21

[Read the full review ↗](/skills/confluent-developing-kafka-python-client/) Upstream setup linked Apache-2.0
 Compare Developing Kafka Python client Add

Testing and reliability · Matt Pocock

### [Diagnosing Bugs](/skills/mattpocock-diagnosing-bugs/)

A debugging procedure that establishes a reproducible symptom, tests competing explanations and preserves a regression check.

 debugging reproduction regression-tests

**Why we selected it**Requires a red-capable reproduction before edits, so an apparent improvement has a concrete behavior to compare against.

**Weigh up**The included human-in-the-loop shell script is an editable single-line-input template, not a ready-made test runner or secret-redaction tool.

 Source reviewed

10 sources · 2026-10-15

[Read the full review ↗](/skills/mattpocock-diagnosing-bugs/) Install command in review MIT
 Compare Diagnosing Bugs Add

Security review · Trail of Bits

### [Diagramming Code](/skills/trailofbits-trailmark-diagramming-code/)

Turns a Trailmark code graph into Mermaid diagrams: call graphs, class hierarchies, module-dependency maps, containment diagrams, complexity heatmaps and attack-surface data-flow views.

 mermaid visualization call-paths

**Why we selected it**Emits call graphs, class hierarchies, module-dependency maps, containment diagrams, complexity heatmaps and data-flow views as Mermaid from a Trailmark graph.

**Weigh up**The native `trailmark diagram` command needs Trailmark 0.4.0+; on older builds the skill runs its bundled scripts/diagram.py.

 Source reviewed

5 sources · 2026-10-22

[Read the full review ↗](/skills/trailofbits-trailmark-diagramming-code/) Upstream setup linked CC-BY-SA-4.0
 Compare Diagramming Code Add

Research and documentation · GitHub community

### [Diataxis Documentation Writer](/skills/github-documentation-writer/)

Writes docs under Diataxis discipline: clarify the quadrant, audience, goal and scope first, approve an outline, then draft tutorials, how-tos, reference or explanation in project tone.

 documentation diataxis technical-writing

**Why we selected it**The quadrant gate (tutorial, how-to, reference, explanation) plus a mandatory outline-approval step stops documentation from being written before its purpose and scope are agreed.

**Weigh up**Framework-first and deliberately procedural; overkill for one-paragraph answers and small edits.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/github-documentation-writer/) Install command in review MIT
 Compare Diataxis Documentation Writer Add

Evidence and evaluation · Anthropic

### [Discernment Nudge](/skills/anthropics-discernment-nudge/)

Anthropic skill that, at most once in a conversation, appends two or three short questions after a substantive answer so the user can check a fact, a reasoning step, or missing context.

 fact-checking assumptions ai-fluency

**Why we selected it**The catalogue's Anthropic skills are document and design skills, not this answer-check.

**Weigh up**This review did not execute the skill.

 Source reviewed

5 sources · 2026-10-14

[Read the full review ↗](/skills/anthropics-discernment-nudge/) Install command in review Apache-2.0
 Compare Discernment Nudge Add

Discord access control · Anthropic

### [Discord access](/skills/anthropic-discord-access/)

Pins the Discord access skill, which refuses channel-originated allowlist edits and will not approve a pairing without its code.

 discord access-control pairing

**Why we selected it**The skill refuses pairing, allowlist, and policy changes that arrive as a Discord, Telegram, or other channel message, and says those mutations must not follow untrusted input.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/anthropic-discord-access/) Install command in review Apache-2.0
 Compare Discord access Add

Discord channel setup · Anthropic

### [Discord configure](/skills/anthropic-discord-configure/)

Pins the Discord setup skill, which stores a bot token as a credential and treats pairing as temporary until the allowlist is locked.

 discord bot-token allowlist

**Why we selected it**The skill says a saved bot token is a credential, tells the agent to chmod 600 the env file, and says a set token is shown with the first six characters masked.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/anthropic-discord-configure/) Install command in review Apache-2.0
 Compare Discord configure Add

Development workflow · Superpowers

### [Dispatching Parallel Agents](/skills/obra-dispatching-parallel-agents/)

Splits independent investigations into bounded agent assignments and checks their integration afterward.

 subagents parallel-work coordination

**Why we selected it**Requires independence and explicit file or subsystem scope before work is parallelized.

**Weigh up**Shared mutable state, sequential dependencies and overlapping file edits defeat the independence assumption.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/obra-dispatching-parallel-agents/) Install command in review MIT
 Compare Dispatching Parallel Agents Add

Security review · Sentry

### [Django access review](/skills/getsentry-django-access-review/)

Traces Django authorisation before flagging an IDOR, instead of matching a pattern and stopping.

 django authorization idor

**Why we selected it**The first heading is Philosophy: Investigation Over Pattern Matching.

**Weigh up**No Django project was executed in this review.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-django-access-review/) Install command in review Apache-2.0
 Compare Django access review Add

Code review · Functional Software, Inc. dba Sentry

### [Django performance review](/skills/getsentry-django-perf-review/)

Review Django code and report only performance issues the reviewer traced. Zero findings is an allowed result.

 django performance review

**Why we selected it**N+1 and unbounded queries are the critical items, and they must be traced to a real loop and a large table.

**Weigh up**The skill says zero findings is acceptable and forbids manufacturing issues.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-django-perf-review/) Install command in review Apache-2.0
 Compare Django performance review Add

Agent development · docker

### [Docker Agent Configuration](/skills/docker-agent-config/)

Build Docker Agent configurations with per-agent toolsets, provider credentials, delegated teams and bounded autonomy.

 agent-development docker

**Why we selected it**It writes a Docker Agent agent.yaml, including models, toolsets, and sub-agents, and it does not cover running or serving the agent.

**Weigh up**The skill does not cover docker agent run, serve, or share.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/docker-agent-config/) Install command in review Apache-2.0
 Compare Docker Agent Configuration Add

Agent deployment · Docker

### [Docker Agent deploy](/skills/docker-agent-deploy/)

Pins Docker's agent serve, share, and eval skill, which refuses a non-loopback listener that has no auth token.

 docker agent mcp

**Why we selected it**The catalogue has docker-agent-run and docker-agent-config from this repository and not the serve, share, and eval skill.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/docker-agent-deploy/) Install command in review Apache-2.0
 Compare Docker Agent deploy Add

Agent development · Docker

### [Docker Agent run](/skills/docker-agent-run/)

Pins Docker's skill for docker agent run, including the safety modes and the exception that a local stdio MCP server stays outside the sandbox VM.

 docker agents sandbox

**Why we selected it**The catalogue has Docker's agent-config and sandbox-credential skills and not this run skill.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/docker-agent-run/) Install command in review Apache-2.0
 Compare Docker Agent run Add

Containers · Docker

### [Docker Build Strategies](/skills/docker-docker-build-strategies/)

Teaches Docker BuildKit multi-stage builds, target execution, cache mount typing, and minimal distroless runtime patterns.

 docker buildkit dockerfile

**Why we selected it**Prescribes explicit BuildKit cache mounts (--mount=type=cache,target=/root/.cache) and discrete build targets instead of invalidating entire layers on unrelated changes.

**Weigh up**The build helper was inspected but not executed; the multi-stage and layer-caching reference guides were not re-reviewed.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/docker-docker-build-strategies/) Install command in review Apache-2.0
 Compare Docker Build Strategies Add

Containers · Docker

### [Docker Compose Patterns](/skills/docker-docker-compose-patterns/)

Establishes production patterns for compose.yaml: strict healthcheck dependencies, curl sidecars for scratch images, and secret masking.

 docker docker-compose orchestration

**Why we selected it**Enforces condition: service_healthy on depends_on stanzas to prevent premature service crashes on unready databases and backends.

**Weigh up**Compose-managed volume deletion requires scoped confirmation; external volumes follow the standalone guardrails.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/docker-docker-compose-patterns/) Install command in review Apache-2.0
 Compare Docker Compose Patterns Add

Safety · Docker

### [Docker destructive guardrails](/skills/docker-docker-destructive-guardrails/)

States what a destructive Docker command will remove and waits for an explicit yes, except one narrow container cleanup.

 docker cli safety

**Why we selected it**Prune, kill, image, network, builder, context, and standalone volume deletes stay on the confirmation rule, including when the request is only to clean up.

**Weigh up**Docker stop interrupts a process but does not remove its container; the skill treats it separately from removal tiers.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/docker-docker-destructive-guardrails/) Install command in review Apache-2.0
 Compare Docker destructive guardrails Add

Containers · docker

### [Docker Project Foundations](/skills/docker-project-foundations/)

Create the first Dockerfile, Compose stack and dockerignore with local-port and build-secret boundaries.

 containers docker

**Why we selected it**It creates a first Dockerfile, compose.yaml, and .dockerignore, and it mounts npm credentials instead of copying them into the image.

**Weigh up**The skill says not to use it for a mature Docker setup that only needs a small edit.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/docker-project-foundations/) Install command in review Apache-2.0
 Compare Docker Project Foundations Add

Sandbox configuration · Docker

### [Docker Sandboxes environment file](/skills/docker-docker-sandboxes-env/)

Pins Docker's sbxenv skill, which treats sbx env plan as a no-change preview and will not default to auto-approving host lifecycle commands.

 docker sandboxes sbxenv

**Why we selected it**sbx env plan is described as printing the apply set and changing nothing, while create and run require approval before they do any work. The file says never to default to -y for a file or kit that has not been reviewed.

**Weigh up**A failing preRemove is only a warning. Removal can still stop afterwards when the destroy plan no longer matches. Those are different gates.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/docker-docker-sandboxes-env/) Install command in review Apache-2.0
 Compare Docker Sandboxes environment file Add

Sandbox kits · Docker

### [Docker Sandboxes kits](/skills/docker-docker-sandboxes-kits/)

Pins Docker's kit-spec skill, which forbids secret kit arguments and says a schema check does not prove composition or that a host is blocked.

 docker sandboxes kits

**Why we selected it**The file forbids passing a secret as a kit argument, keeps OAuth off mixin kits, and calls token passthrough a security downgrade.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/docker-docker-sandboxes-kits/) Install command in review Apache-2.0
 Compare Docker Sandboxes kits Add

Container sandboxes · Docker

### [Docker Sandboxes lifecycle](/skills/docker-sandboxes-lifecycle/)

Pins Docker's local sbx lifecycle skill, which requires a dry-run before prune and forbids mounting a secrets file into the sandbox.

 docker sandboxes sbx

**Why we selected it**The catalogue already has Docker's destructive-guardrails and network-credentials skills and not this lifecycle file.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/docker-sandboxes-lifecycle/) Install command in review Apache-2.0
 Compare Docker Sandboxes lifecycle Add

Sandbox security · docker

### [Docker Sandboxes Network and Credentials](/skills/docker-sandboxes-network-credentials/)

Configure standalone sbx egress policy and service credentials while distinguishing proxy sentinels, OAuth passthrough and host-side secret resolution.

 sandbox-security docker

**Why we selected it**It separates Docker Sandboxes egress policy from credential injection, and storing a secret does not open the network.

**Weigh up**Egress policy does not protect a credential that has already left the sandbox.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/docker-sandboxes-network-credentials/) Install command in review Apache-2.0
 Compare Docker Sandboxes Network and Credentials Add

Documentation and knowledge · Addy Osmani

### [Documentation and ADRs](/skills/addyosmani-documentation-and-adrs/)

Records an architecture decision with a status, instead of leaving the reason in chat.

 adr documentation decisions

**Why we selected it**Before creating an ADR it asks the agent to find and match the repository's existing convention (location, numbering, headings) and to surface conflicting conventions.

**Weigh up**An ADR is not evidence the decision was correct.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/addyosmani-documentation-and-adrs/) Install command in review MIT
 Compare Documentation and ADRs Add

Documentation · GitHub community (awesome-copilot)

### [Documentation Drift Audit](/skills/github-docs-sync-audit/)

Compare documentation claims with repository code and configuration using a bounded evidence report.

 documentation github

**Why we selected it**docs_drift.py checks command names, filesystem links and regex-derived env references; the definition requires manual confirmation and separates inferred gaps from confirmed drift.

**Weigh up**The helper is heuristic: it merges package scripts across a repository, approximates imports and returns zero despite findings. It reads complete local env-file text even though only variable names are reported.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/github-docs-sync-audit/) Install command in review MIT
 Compare Documentation Drift Audit Add

Databases · DuckDB

### [DuckDB read file](/skills/duckdb-read-file/)

DuckDB's read-file skill: one DuckDB CLI command that picks a reader by file extension and returns a file's schema, row count and first 20 rows, for local paths or HTTPS, S3, GCS and Azure URLs.

 duckdb parquet sql

**Why we selected it**DuckDB publishes it in duckdb/duckdb-skills as one skill of the duckdb-skills Claude Code plugin (plugin.json version 0.2.4, license MIT); LICENSE is the MIT text with "Copyright 2018-2025 Stichting DuckDB Foundation".

**Weigh up**The skills/read-file directory last changed in a commit dated 2026-03-30; the pinned revision 7feda8e0 is dated 2026-04-14.

 Source reviewed

5 sources · 2026-10-21

[Read the full review ↗](/skills/duckdb-read-file/) Upstream setup linked MIT
 Compare DuckDB read file Add

Security · trailofbits

### [DWARF Debug Information](/skills/trailofbits-dwarf-expert/)

Inspect DWARF symbols, types, line tables and address mappings using tool-specific commands.

 security trailofbits

**Why we selected it**The skill reads DWARF with local dumpers and, when the standard matters, tells the agent to look up dwarfstd.org rather than answer from memory.

**Weigh up**allowed-tools includes WebSearch and WebFetch, so a standards lookup is a network call. The file does not attach a debugger or decompile the whole binary.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-dwarf-expert/) Install command in review CC-BY-SA-4.0
 Compare DWARF Debug Information Add

Release engineering · Expo

### [EAS Update](/skills/expo-eas-update/)

Publishes an Expo OTA update only after the channel, environment, runtime and native-build boundary are explicit.

 expo ota eas

**Why we selected it**Publishing is treated as a remote mutation that needs an explicit project, channel, environment, platform, runtime, and message.

**Weigh up**The file says EAS Update has plan allowances and that publishing can affect installed apps.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/expo-eas-update/) Install command in review MIT
 Compare EAS Update Add

Migration · Effectful Technologies

### [Effect v3 to v4](/skills/effect-ts-effect-v3-to-v4/)

Migrates Effect v3 to v4 by searching the generated reference one symbol at a time, and forbids a compatibility shim.

 effect typescript migration

**Why we selected it**package.json is fixed before the type-check, merged packages are removed, and every remaining Effect package shares one version.

**Weigh up**The two clones are unpinned main and the v3 branch. An existing .repos/effect must be the canonical Effect-TS/effect repo at version 4.x, or it is deleted. This review did not clone either repo.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/effect-ts-effect-v3-to-v4/) Install command in review MIT
 Compare Effect v3 to v4 Add

Observability · elastic

### [Elasticsearch Cluster Health](/skills/elastic-elasticsearch-cluster-health/)

Triage unassigned Elasticsearch shards through allocation evidence.

 observability elastic

**Why we selected it**The process separates reassignment triggers such as NODE_LEFT from the decider currently blocking allocation and treats missing valid primary copies explicitly.

**Weigh up**Not applicable to Serverless cluster APIs. Green allocation status does not establish application health, and the most likely cause remains a diagnosis to validate.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/elastic-elasticsearch-cluster-health/) Install command in review Apache-2.0
 Compare Elasticsearch Cluster Health Add

Observability · Elastic

### [Elasticsearch ES|QL](/skills/elastic-esql/)

Pins Elastic's ES|QL skill, which routes queries through the elastic CLI and refuses to treat a Serverless build number as a feature gate.

 elasticsearch esql observability

**Why we selected it**The catalogue has Elastic's LLM observability skill and not this ES|QL skill from the same repository.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/elastic-esql/) Install command in review Apache-2.0
 Compare Elasticsearch ES|QL Add

Data pipelines · elastic

### [Elasticsearch File Ingest](/skills/elastic-elasticsearch-ingest/)

Load CSV or JSON into Elasticsearch with explicit mapping and bulk-result checks.

 data-pipelines elastic

**Why we selected it**The definition distinguishes CSV rows, JSON arrays and NDJSON and forbids sending raw arrays as one bulk document; index-to-index migration is outside this skill.

**Weigh up**A successful bulk HTTP response can contain failed items. Document counts alone cannot prove content equivalence, especially when IDs overwrite existing documents.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/elastic-elasticsearch-ingest/) Install command in review Apache-2.0
 Compare Elasticsearch File Ingest Add

Search and retrieval · elastic

### [Elasticsearch Index Mapping Design](/skills/elastic-elasticsearch-index-design/)

Design index field types and storage settings from concrete access patterns.

 search-and-retrieval elastic

**Why we selected it**The workflow separates full-text, exact-match and retrieve-only fields and calls out flattened fields as an alternative to unbounded dynamic mappings.

**Weigh up**Changing existing field types requires a new index/reindex strategy; Serverless manages shard and replica settings. Type choices need actual precision and retention requirements.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/elastic-elasticsearch-index-design/) Install command in review Apache-2.0
 Compare Elasticsearch Index Mapping Design Add

Search and retrieval · elastic

### [Elasticsearch Query DSL Optimization](/skills/elastic-elasticsearch-query-optimization/)

Use query profiles and mappings to investigate slow Elasticsearch searches.

 search-and-retrieval elastic

**Why we selected it**The workflow profiles before recommending infrastructure changes and distinguishes query-clause cost from aggregation cost.

**Weigh up**Profile timings add overhead and omit parts of end-to-end latency. Removing a leading wildcard changes matching unless the intended contract permits it; wildcard-field behavior needs version-specific evidence.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/elastic-elasticsearch-query-optimization/) Install command in review Apache-2.0
 Compare Elasticsearch Query DSL Optimization Add

Data pipelines · elastic

### [Elasticsearch Reindex Planning](/skills/elastic-elasticsearch-reindex/)

Prepare destination mappings and verify asynchronous local or remote reindex operations.

 data-pipelines elastic

**Why we selected it**The definition separates local slicing from remote query partitioning and requires explicit destination preparation and post-copy settings restoration.

**Weigh up**Reindex does not copy mappings or continuously synchronize later writes. Disabling replicas or refresh changes availability/visibility; counts need concurrent-write and ID-collision context.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/elastic-elasticsearch-reindex/) Install command in review Apache-2.0
 Compare Elasticsearch Reindex Planning Add

Search and retrieval · elastic

### [Elasticsearch Search Relevance](/skills/elastic-elasticsearch-search-relevance/)

Choose deterministic query rules or organic ranking changes from mappings and example searches.

 search-and-retrieval elastic

**Why we selected it**The decision table separates pinned/excluded documents from multi_match and analyzer tuning and warns against simulating deterministic pinning with extreme boosts.

**Weigh up**Top-hit inspection for one query is not a relevance benchmark. Query-rule availability and rule-query wiring depend on version and deployment.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/elastic-elasticsearch-search-relevance/) Install command in review Apache-2.0
 Compare Elasticsearch Search Relevance Add

Security review · Trail of Bits

### [Entry-point analyzer](/skills/trailofbits-entry-point-analyzer/)

Lists state-changing smart-contract entry points and their access class, and excludes view functions, exploit writing, and non-contract code.

 smart-contracts audit entry-points

**Why we selected it**When NOT to Use sends vulnerability hunting, exploit proofs, gas work, and non-contract code elsewhere.

**Weigh up**The skill does not detect vulnerabilities and tells the reader to use a different audit skill for that.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-entry-point-analyzer/) Install command in review CC-BY-SA-4.0
 Compare Entry-point analyzer Add

API design · JetBrains

### [Error Model Validation Architect](/skills/jetbrains-error-model-validation-architect/)

Turns ad-hoc exception handling into a deliberate public error contract: an explicit taxonomy across eight failure categories, status-code mapping rules, machine-readable codes separated from human messages, framework exception coverage, and a logging rule that keeps internal detail out of client payloads.

 error-handling error-taxonomy http-status-codes

**Why we selected it**Forces an explicit error taxonomy before any code — at minimum eight categories from malformed request to downstream dependency failure — and forbids collapsing every non-success outcome into one generic envelope.

**Weigh up**The worked context is Kotlin plus Spring (Bean Validation targets, @ControllerAdvice, security entry points); the taxonomy method transfers, the framework specifics do not.

 Source reviewed

6 sources · 2026-10-13

[Read the full review ↗](/skills/jetbrains-error-model-validation-architect/) Install command in review MIT (upstream Kotlin backend agent skills)
 Compare Error Model Validation Architect Add

Model evaluation · LangChain

### [Eval Engineering](/skills/langchain-ai-eval-engineering/)

Turns an agent repository and traces into reviewed task specs, verifiers and Harbor runs, with a cost confirmation before scored runs.

 agent-evals benchmark-design harbor

**Why we selected it**Before a scored model run, the file requires confirming the model, trial count, judge, timeout and maximum expected cost with the user, unless that run plan was already authorized.

**Weigh up**The workflow routes to twelve reference documents, multi-turn simulation code and two scripts in the skill directory. Only SKILL.md was read for this review.

 Source reviewed

3 sources · 2026-10-13

[Read the full review ↗](/skills/langchain-ai-eval-engineering/) Install command in review MIT
 Compare Eval Engineering Add

Development workflow · getsentry

### [Evidence-Based Skill Writing](/skills/getsentry-skill-writer/)

Choose a skill structure, preserve source adaptation decisions and iterate against working and holdout examples.

 development-workflow getsentry

**Why we selected it**SKILL.md is a router: each bundled reference is loaded only for the step that needs it, not all at once.

**Weigh up**quick_validate.py needs Python 3.12 and pyyaml, and it is invoked with uv. A passing run does not mean the new skill does the task.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-skill-writer/) Install command in review Apache-2.0
 Compare Evidence-Based Skill Writing Add

Mobile development · expo

### [Expo Data Fetching](/skills/expo-expo-data-fetching/)

Design Expo network flows with distinct loading, error, empty and cached-content states.

 mobile-development expo

**Why we selected it**The definition explicitly distinguishes resolved empty data from missing data and keeps cached content visible when background refresh fails.

**Weigh up**Client-public environment values are bundled into the app. Retry examples require idempotency review, and offline-paused queries can have neither data nor an active loading flag.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/expo-expo-data-fetching/) Install command in review MIT
 Compare Expo Data Fetching Add

Mobile development · Expo

### [Expo Design System](/skills/expo-expo-design-system/)

Builds a token theme (color, spacing, typography, radius, shadow, motion) plus variant/size/state component conventions inside an Expo app, with grep-based drift audits and a named gallery of AI-generated-looking anti-patterns.

 design-system design-tokens react-native

**Why we selected it**Adopt-before-you-build rule: extend an existing styling library in its own idiom and never introduce a second token system beside it, so adoption cannot become drift.

**Weigh up**What looks native (palettes, HIG rules, controls) is delegated to the sibling expo-native-ui skill; this skill governs where values live, not which values to pick.

 Source reviewed

7 sources · 2026-10-15

[Read the full review ↗](/skills/expo-expo-design-system/) Install command in review MIT
 Compare Expo Design System Add

Mobile development · expo

### [Expo Development Clients](/skills/expo-expo-dev-client/)

Build a native-capable Expo development client for device and simulator testing.

 mobile-development expo

**Why we selected it**The source separates custom native dependencies from Expo Go use and distinguishes a development client from production store submission.

**Weigh up**EAS/TestFlight availability and billing depend on account and plan; the source cloud-build price generalization is not a current quote. iOS device archives and simulator artifacts are different build targets.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/expo-expo-dev-client/) Install command in review MIT
 Compare Expo Development Clients Add

Mobile development · expo

### [Expo DOM Components](/skills/expo-expo-dom/)

Use isolated DOM components to bring selected web UI into native Expo apps.

 mobile-development expo

**Why we selected it**The definition separates serializable props from async native-action callbacks and documents different web and native rendering paths.

**Weigh up**A webview adds memory and bridge overhead; native routing hooks that require synchronous state must be evaluated in the parent. Exposed native callbacks require input validation.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/expo-expo-dom/) Install command in review MIT
 Compare Expo DOM Components Add

Native modules · Expo

### [Expo Module Authoring](/skills/expo-expo-module/)

Scaffolds an Expo native module with an explicit slug, platform and feature set, then replaces the generated sample.

 expo swift kotlin

**Why we selected it**Scaffolding is delegated to create-expo-module, with local and standalone called out as different products.

**Weigh up**The description says not to use this skill to migrate an existing Swift module from the definition DSL to Expo Modules API 2.0 macros.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/expo-expo-module/) Install command in review MIT
 Compare Expo Module Authoring Add

Mobile development · Expo

### [Expo Router Navigation](/skills/expo-expo-router/)

Structure Expo routes, native stacks, previews and modal navigation.

 expo-router navigation native-tabs

**Why we selected it**The definition separates route files from reusable components and identifies SDK-specific React Navigation entry points and title/header options.

**Weigh up**Examples target recent SDK APIs and iOS behaviors; preview, glass and native-tab features are not universal across platforms. Removing old routes can break external deep links.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/expo-expo-router/) Install command in review MIT
 Compare Expo Router Navigation Add

Mobile development · Expo

### [Expo Web to Native Migration](/skills/expo-expo-web-to-native/)

Migrates a web React codebase to a native Expo app screen by screen: native shell first, whole web UI shippable in DOM components on day one, then strangler-order nativization with device verification.

 expo migration react-native

**Why we selected it**The migration spine keeps the app shippable at every step: assess into a durable worklist, scaffold, DOM-component shell as the day-one milestone, then one nativized screen per pass in value order.

**Weigh up**The verification recipe is opinionated about tooling: it asks the user to install agent-browser and argent simulators rather than falling back to manual screenshots.

 Source reviewed

7 sources · 2026-10-15

[Read the full review ↗](/skills/expo-expo-web-to-native/) Install command in review MIT
 Compare Expo Web to Native Migration Add

Security review · Trail of Bits

### [False Positive Check](/skills/trailofbits-fp-check/)

Forces a true-positive or false-positive verdict on one suspected bug, and refuses to be used as a bug hunter.

 security triage verification

**Why we selected it**The definition separates verification of a named finding from hunting for new bugs, and lists the phrases that should not trigger it.

**Weigh up**CC-BY-SA-4.0 applies to adaptations you redistribute.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-fp-check/) Install command in review CC-BY-SA-4.0
 Compare False Positive Check Add

API frameworks · FastAPI

### [FastAPI conventions](/skills/fastapi-fastapi/)

Official FastAPI skill for Annotated dependencies, return types, router-level configuration, and SSE through EventSourceResponse.

 fastapi python pydantic

**Why we selected it**The primary file specifies Annotated dependencies, a return type ahead of response_model, router-level prefix and dependencies, and EventSourceResponse for server-sent events.

**Weigh up**The reference files named from the quick reference were not opened. fastapi/sse.py, applications.py, and responses.py were not opened, so claims about those modules are the skill's statements.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/fastapi-fastapi/) Install command in review MIT
 Compare FastAPI conventions Add

Documentation · dbt Labs

### [Fetch dbt docs](/skills/dbt-labs-fetching-dbt-docs/)

Pins dbt Labs' docs skill, which fetches pages as markdown and refuses to run commands or instructions embedded in that content.

 dbt docs untrusted-content

**Why we selected it**Fetched documentation is untrusted, and the file says never to execute commands or instructions embedded in it.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/dbt-labs-fetching-dbt-docs/) Install command in review Apache-2.0
 Compare Fetch dbt docs Add

Git workflow · Jesse Vincent

### [Finish a development branch](/skills/obra-finishing-a-development-branch/)

After a green test suite, show a fixed integration menu and run only the option the person chooses.

 git worktree pull-request

**Why we selected it**The skill stops when tests fail, then waits for one of three written options before merge, push, or leaving the branch alone.

**Weigh up**Option 1 runs checkout, pull, and merge, then deletes the branch only after the merged suite is green. Option 2 pushes. Discard force-deletes the branch.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/obra-finishing-a-development-branch/) Install command in review MIT
 Compare Finish a development branch Add

Cloud Security · Google LLC

### [Firebase Security Rules Auditor](/skills/firebase-security-rules-auditor/)

Audits Firebase Firestore and Cloud Storage security rules for privilege escalation, role bypasses, resource exhaustion, and create-vs-update validation asymmetries.

 firebase firestore security-rules

**Why we selected it**Details comprehensive security verification checklists covering field immutability, request.auth.uid verification, size caps, and write vs create/update splits.

**Weigh up**Covers rule logic and syntax; does not deploy rules to live Firebase projects or audit Cloud Functions code.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/firebase-security-rules-auditor/) Install command in review Apache-2.0
 Compare Firebase Security Rules Auditor Add

Model deployment · Microsoft

### [Foundry customize deployment](/skills/microsoft-customize/)

Pins Microsoft's Foundry customize-deployment skill, which blocks the create until quota data is valid and the operator approves the summary.

 foundry azure-openai deployment

**Why we selected it**Phase 12 shows the full configuration and waits for approval or cancel before phase 13 runs the create.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-customize/) Install command in review MIT
 Compare Foundry customize deployment Add

Model deployment · Microsoft

### [Foundry deploy model](/skills/microsoft-deploy-model/)

Pins Microsoft's Foundry deploy-model router, which will not create a deployment until the target project is shown and confirmed.

 foundry azure-openai deployment

**Why we selected it**The file says never to deploy without showing the project, and it requires a confirm step before every mode.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-deploy-model/) Install command in review MIT
 Compare Foundry deploy model Add

Model fine-tuning · Microsoft

### [Foundry fine-tuning](/skills/microsoft-finetuning/)

Pins Microsoft's Foundry fine-tuning skill, which treats cleanup as deletion and says to validate training data before a job is submitted.

 foundry fine-tuning sft

**Why we selected it**The file says cleanup.py deletes old files and deployments, and that a DeploymentNotReady race is fixed by deleting and recreating the deployment.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-finetuning/) Install command in review MIT
 Compare Foundry fine-tuning Add

Frontend session diagnosis · Grafana Labs

### [Frontend Observability session RCA](/skills/grafana-frontend-session-rca/)

Pins Grafana's frontend session skill, which stops until three ids are present and treats the saved gcx dump as untrusted.

 grafana frontend-observability gcx

**Why we selected it**No selected skills record uses this source path.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-frontend-session-rca/) Install command in review Apache-2.0
 Compare Frontend Observability session RCA Add

Testing · trailofbits

### [Fuzzing Dictionaries](/skills/trailofbits-fuzzing-dictionary/)

Build targeted token dictionaries from parser expectations and compare their effect on coverage.

 testing trailofbits

**Why we selected it**The skill builds a token dictionary for a fuzzer. It says to skip that when the target is a pure algorithm or the corpus is already covering the code.

**Weigh up**It does not run a fuzzer and it does not install one. External dictionary collections are links, not vendored files.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-fuzzing-dictionary/) Install command in review CC-BY-SA-4.0
 Compare Fuzzing Dictionaries Add

Testing · trailofbits

### [Fuzzing Obstacles](/skills/trailofbits-fuzzing-obstacles/)

Diagnose validation and nondeterminism barriers, then isolate minimal fuzzing-only changes.

 testing trailofbits

**Why we selected it**The handbook's method is a fuzzing-only build flag so production builds keep the check the fuzzer cannot pass.

**Weigh up**The file is instructions, not a patch applicator. It does not compile or run a fuzzer.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-fuzzing-obstacles/) Install command in review CC-BY-SA-4.0
 Compare Fuzzing Obstacles Add

Creative production · GitHub community

### [Game Engine](/skills/github-game-engine/)

Builds web-based games and game engines with HTML5 Canvas, WebGL and JavaScript: game loops, physics and collision detection, controls, audio, plus five complete starter templates and nine reference documents.

 game-development html5-canvas webgl

**Why we selected it**Ships five complete starter templates and nine reference documents, so a working game exists before theory does — the paddle template is a full breakout build, not a skeleton.

**Weigh up**Web-only: no Unity, Unreal or Godot coverage, so native-engine work is out of scope.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/github-game-engine/) Install command in review MIT
 Compare Game Engine Add

AI application development · Google

### [Gemini API Development](/skills/google-gemini-gemini-api-dev/)

Gemini Interactions API patterns for Python and TypeScript, with a dated model list and deprecated-model rules.

 gemini llm-api interactions-api

**Why we selected it**The file states that interactions are stored by default, retained 55 days on the paid tier and 1 day on the free tier, and that store=False also disables previous_interaction_id and background runs.

**Weigh up**If a user asks for a deprecated model, the file tells the agent to use gemini-3.8-flash instead and note the substitution. Check for that note when a specific model was required.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/skills/google-gemini-gemini-api-dev/) Install command in review Apache-2.0
 Compare Gemini API Development Add

AI application development · Google

### [Gemini Live API Development](/skills/google-gemini-gemini-live-api-dev/)

Gemini Live API guidance for real-time audio, video and text over WebSockets, with stated session limits.

 gemini realtime-audio websockets

**Why we selected it**Its Limitations section states session ceilings without compression (15 minutes audio-only, 2 minutes audio plus video, about 10 minutes per connection) and points to context compression and session resumption.

**Weigh up**The quick-start authentication examples pass a literal API key placeholder to the client, including in JavaScript, which the file's own best practices advise against for browsers. Use ephemeral tokens in client code.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/skills/google-gemini-gemini-live-api-dev/) Install command in review Apache-2.0
 Compare Gemini Live API Development Add

Testing and reliability · Trail of Bits

### [Genotoxic](/skills/trailofbits-trailmark-genotoxic/)

Builds a Trailmark graph, runs a mutation-testing framework and, where supported, necessist, and uses survived mutants, unnecessary test statements and call-graph data to sort findings into false positives, missing unit tests and fuzzing targets.

 mutation-testing triage fuzzing

**Why we selected it**Builds a Trailmark graph, runs mutation testing and, where the language allows, necessist, then classifies survived mutants and unnecessary test statements as false positives, missing unit tests or fuzzing targets.

**Weigh up**It installs missing tools itself: `uv tool install trailmark`, a mutation framework per references/mutation-frameworks.md (sudo apt-get or dnf, brew, cargo install or go install …@latest), and `cargo install necessist`.

 Source reviewed

6 sources · 2026-10-22

[Read the full review ↗](/skills/trailofbits-trailmark-genotoxic/) Upstream setup linked CC-BY-SA-4.0
 Compare Genotoxic Add

CI and delivery · GitHub community (awesome-copilot)

### [GitHub Actions Efficiency Review](/skills/github-github-actions-efficiency/)

Find evidenced CI waste while preserving required validation and measuring actual impact.

 ci-and-delivery github

**Why we selected it**The reporting reference separates expected from measured savings, runner time from critical-path latency and cache-warmup or matrix changes from optimization effects.

**Weigh up**Static workflow inspection cannot prove cancellation, gating or savings. Undocumented matrix legs may still protect real users, so confirm compatibility commitments before removal.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/github-github-actions-efficiency/) Install command in review MIT
 Compare GitHub Actions Efficiency Review Add

CI and delivery · GitHub community (awesome-copilot)

### [GitHub Actions Runtime Upgrades](/skills/github-github-actions-runtime-upgrade-conventions/)

Upgrade deprecated action runtimes using compatible releases and immutable commit pins.

 ci-and-delivery github

**Why we selected it**The definition requires full-SHA uses references, preserved workflow behavior and verification of artifact/signing outputs and post-upgrade logs.

**Weigh up**Latest major does not imply compatibility with self-hosted runners or existing inputs. Local build success does not prove the upgraded action executes correctly on GitHub.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/github-github-actions-runtime-upgrade-conventions/) Install command in review MIT
 Compare GitHub Actions Runtime Upgrades Add

Security review · Sentry

### [GitHub Actions Security Review](/skills/getsentry-gha-security-review/)

Reviews GitHub Actions for an external attacker, and withholds a finding that has no entry point, payload and execution path.

 github-actions ci supply-chain

**Why we selected it**The attacker is someone without write access. workflow_dispatch input injection and push-only expression injection on protected branches are out of scope.

**Weigh up**The file treats ${{ }} in if:, with: and job or step env: as runtime evaluation rather than a shell sink. A later unquoted use of that variable can still be ordinary shell injection.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-gha-security-review/) Install command in review Apache-2.0
 Compare GitHub Actions Security Review Add

Planning and delivery · GitHub community

### [GitHub Release Workflow](/skills/github-github-release/)

Cuts a library release end to end: tag-derived versioning, code-diff-first SemVer analysis against commit intent, Keep a Changelog authoring, and a gated release-branch plus PR handoff.

 releases semver changelog

**Why we selected it**Version analysis prefers the code diff as primary signal with commit messages secondary, and states the reconciliation rule outright: on conflict the diff wins, with worked examples.

**Weigh up**Single-package GitHub repositories are assumed; monorepos and non-SemVer tag schemes fall outside the versioning logic.

 Source reviewed

7 sources · 2026-10-15

[Read the full review ↗](/skills/github-github-release/) Install command in review MIT
 Compare GitHub Release Workflow Add

Development workflow · GitHub community (awesome-copilot)

### [GitHub Secret Scanning Operations](/skills/github-secret-scanning/)

Configure GitHub secret detection and triage exposure with credential rotation and explicit bypass decisions.

 development-workflow github

**Why we selected it**It configures GitHub secret scanning and push protection, and it treats rotation as the first remediation step.

**Weigh up**The skill does not scan the working tree itself; pre-commit scanning is a separate plugin and MCP tool.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/github-secret-scanning/) Install command in review MIT
 Compare GitHub Secret Scanning Operations Add

Design and interfaces · Google Labs / Stitch

### [Google Stitch Design-System Extraction](/skills/google-labs-code-extract-design-md/)

Reads frontend source and theme files to draft a structured DESIGN.md for design-system documentation or later Stitch use.

 design-systems design-tokens css

**Why we selected it**It writes a DESIGN.md by reading stylesheets, theme files, and component source, and it says no build or runtime is required.

**Weigh up**The skill does not build or render the application, and it does not call Stitch unless the user wants the document pushed.

 Source reviewed

10 sources · 2026-10-15

[Read the full review ↗](/skills/google-labs-code-extract-design-md/) Upstream setup linked Apache-2.0
 Compare Google Stitch Design-System Extraction Add

Development workflow · Hugging Face

### [Gradio App Builder](/skills/huggingface-huggingface-gradio/)

A Gradio reference and example collection for building Python interfaces, event-driven layouts and chat demos.

 gradio python demos

**Why we selected it**Connects component signatures and event listeners to complete examples covering forms, streaming and chat interfaces.

**Weigh up**The static signatures are a source snapshot, not a version compatibility guarantee; check current Gradio documentation and your installed package.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/huggingface-huggingface-gradio/) Install command in review Apache-2.0
 Compare Gradio App Builder Add

Spaces · Hugging Face

### [Gradio LoRA Space Builder](/skills/huggingface-huggingface-lora-space-builder/)

Pins Hugging Face's LoRA Space skill, which tries a public read before asking for a token and waits for one approval before a private publish.

 huggingface lora gradio

**Why we selected it**An unauthenticated read comes first. A token is requested only when no valid cached token can read a private or gated repo.

**Weigh up**This review did not execute the resource.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/huggingface-huggingface-lora-space-builder/) Upstream setup linked Apache-2.0
 Compare Gradio LoRA Space Builder Add

Grafana alerting · Grafana Labs

### [Grafana alerting and IRM](/skills/grafana-alerting-irm/)

Pins Grafana's alerting and IRM skill, which requires a bearer token, checks the receiver before live routing, and silences notifications without stopping evaluation.

 grafana alerting silences

**Why we selected it**No selected skills record uses this source path.

**Weigh up**The resource was not executed.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-alerting-irm/) Install command in review Apache-2.0
 Compare Grafana alerting and IRM Add

Observability · Grafana Labs

### [Grafana Alloy](/skills/grafana-alloy/)

Write a Grafana Alloy pipeline, validate it before running it, and treat an unhealthy component on the local UI as the failure.

 alloy opentelemetry logs

**Why we selected it**The file runs alloy fmt and alloy validate before alloy run, then reads the local component API for any health state other than healthy.

**Weigh up**The config-syntax reference was inspected; components.md and collection-patterns.md remain outside this review. alloy fmt, alloy validate, and alloy run were not executed.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-alloy/) Install command in review Apache-2.0
 Compare Grafana Alloy Add

Observability · grafana

### [Grafana App Admission Control](/skills/grafana-admission-control/)

Implement validators and mutators for Grafana app resources before persistence.

 observability grafana

**Why we selected it**It separates grafana-app-sdk validation, which cannot change the object, from mutation, which can.

**Weigh up**A validator cannot modify the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-admission-control/) Install command in review Apache-2.0
 Compare Grafana App Admission Control Add

Observability · grafana

### [Grafana App Reconciler Logic](/skills/grafana-reconciler-logic/)

Implement scoped resource reconciliation and status updates with explicit event and finalizer behavior.

 observability grafana

**Why we selected it**It implements a grafana-app-sdk TypedReconciler that skips an unchanged generation and writes status with UpdateObject.

**Weigh up**The skill does not use client.Update for status.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-reconciler-logic/) Install command in review Apache-2.0
 Compare Grafana App Reconciler Logic Add

Grafana app scaffolding · grafana

### [Grafana App SDK concepts](/skills/grafana-app-sdk-concepts/)

Pins Grafana's app-sdk concepts skill, which asks before adding an operator and deletes unkept files in the in-repo scaffold.

 grafana app-sdk scaffold

**Why we selected it**No selected skills record uses this source path.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-app-sdk-concepts/) Install command in review Apache-2.0
 Compare Grafana App SDK concepts Add

Metrics cost control · grafana

### [Grafana Cloud Adaptive Metrics](/skills/grafana-adaptive-metrics/)

Pins Grafana's Adaptive Metrics skill, which separates a write bearer key from query basic auth and deletes a rule to roll back.

 grafana adaptive-metrics cardinality

**Why we selected it**No selected skills record uses this source path.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-adaptive-metrics/) Install command in review Apache-2.0
 Compare Grafana Cloud Adaptive Metrics Add

Grafana Cloud administration · grafana

### [Grafana Cloud Admin](/skills/grafana-admin/)

Pins Grafana's cloud admin skill, which labels stack deletion as destructive and checks a new token on the org endpoint.

 grafana admin rbac

**Why we selected it**No selected skills record uses this source path.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-admin/) Install command in review Apache-2.0
 Compare Grafana Cloud Admin Add

Application observability · grafana

### [Grafana Cloud Application Observability](/skills/grafana-app-observability/)

Pins Grafana's app observability skill, which requires publisher scopes and treats Faro 401 and 404 as different failures.

 grafana apm faro

**Why we selected it**No selected skills record uses this source path.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-app-observability/) Install command in review Apache-2.0
 Compare Grafana Cloud Application Observability Add

Grafana Cloud cost control · grafana

### [Grafana Cloud Cost Management](/skills/grafana-cost-management/)

Pins Grafana's cost-management skill, which says to preview Adaptive Metrics rules before apply and to disable or delete them to roll back.

 grafana cost adaptive-metrics

**Why we selected it**No selected skills record uses this source path.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-cost-management/) Install command in review Apache-2.0
 Compare Grafana Cloud Cost Management Add

Prometheus cost analysis · grafana

### [Grafana Cloud dpm-finder](/skills/grafana-dpm-finder/)

Pins Grafana's dpm-finder skill, which checks a metrics-read key before the scan and skips metrics that return HTTP 422.

 grafana prometheus dpm

**Why we selected it**No selected skills record uses this source path.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-dpm-finder/) Install command in review Apache-2.0
 Compare Grafana Cloud dpm-finder Add

Cloud provider integrations · grafana

### [Grafana Cloud Integrations](/skills/grafana-cloud-integrations/)

Pins Grafana's cloud integrations skill, which scopes provider credentials and refuses in-place edits of provisioned dashboards.

 grafana aws azure

**Why we selected it**No selected skills record uses this source path.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-cloud-integrations/) Install command in review Apache-2.0
 Compare Grafana Cloud Integrations Add

Grafana Cloud k6 · Grafana Labs

### [Grafana Cloud k6 investigation](/skills/grafana-k6-cloud-investigate-test/)

Pins Grafana's Cloud k6 investigation skill, which reads with authenticated gcx and forbids using the script-update command as a way to discover URLs.

 grafana k6 gcx

**Why we selected it**No selected skills record uses this source path.

**Weigh up**The resource was not executed.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-k6-cloud-investigate-test/) Install command in review Apache-2.0
 Compare Grafana Cloud k6 investigation Add

Grafana MCP access · grafana

### [Grafana Cloud MCP setup](/skills/grafana-assistant-mcp/)

Pins Grafana's MCP setup skill, which defaults agents to --disable-write and a Viewer token.

 grafana mcp disable-write

**Why we selected it**No selected skills record uses this source path.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-assistant-mcp/) Install command in review Apache-2.0
 Compare Grafana Cloud MCP setup Add

Private connectivity · Grafana Labs

### [Grafana Cloud private connectivity](/skills/grafana-private-connectivity/)

Pins Grafana's private connectivity skill, which limits AWS PrivateLink to one region unless peering exists and rejects a public DNS answer.

 grafana privatelink dns

**Why we selected it**No selected skills record uses this source path.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-private-connectivity/) Install command in review Apache-2.0
 Compare Grafana Cloud private connectivity Add

Synthetic and load testing · Grafana Labs

### [Grafana Cloud testing](/skills/grafana-testing/)

Pins Grafana's Cloud testing skill, which runs a local k6 smoke test before a cloud launch and pairs check creation with a rollback.

 grafana synthetic-monitoring k6

**Why we selected it**No selected skills record uses this source path.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-testing/) Install command in review Apache-2.0
 Compare Grafana Cloud testing Add

Observability · grafana

### [Grafana CUE Kind Definitions](/skills/grafana-cue-kind-definition/)

Define versioned resource schemas and generate matching app types from CUE.

 observability grafana

**Why we selected it**It scaffolds a grafana-app-sdk kind in CUE and regenerates clients instead of editing pkg/generated.

**Weigh up**Generated Go and TypeScript files are overwritten and must not be hand-edited.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-cue-kind-definition/) Install command in review Apache-2.0
 Compare Grafana CUE Kind Definitions Add

Grafana dashboards · Grafana Labs

### [Grafana dashboard authoring](/skills/grafana-dashboarding/)

Pins Grafana's dashboard JSON skill, which checks the payload locally before POST and sends it with a dashboards write token and overwrite set.

 grafana dashboards overwrite

**Why we selected it**No selected skills record uses this source path.

**Weigh up**The resource was not executed.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-dashboarding/) Install command in review Apache-2.0
 Compare Grafana dashboard authoring Add

Grafana datasource provisioning · Grafana Labs

### [Grafana datasource provisioning](/skills/grafana-datasources-provisioning/)

Pins Grafana's datasource provisioning skill, which asks before generating a file, refuses inline secrets and pasted tokens, and defaults query access to the server proxy.

 grafana datasources provisioning

**Why we selected it**No selected skills record uses this source path.

**Weigh up**The resource was not executed.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-datasources-provisioning/) Install command in review Apache-2.0
 Compare Grafana datasource provisioning Add

Observability · Grafana

### [Grafana Fleet Management](/skills/grafana-fleet-management/)

Pins Grafana's Alloy fleet skill, which validates a pipeline locally before the Fleet Management API and keeps the cloud API key in an environment variable.

 grafana alloy fleet-management

**Why we selected it**The catalogue has Grafana Alloy, Loki, and Prometheus skills and not this Fleet Management remote-config skill.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-fleet-management/) Install command in review Apache-2.0
 Compare Grafana Fleet Management Add

Observability · Grafana Labs

### [Grafana Loki](/skills/grafana-loki/)

Pins Grafana's Loki skill for LogQL stream selectors, parsers, and the push and read paths it names.

 loki logql observability

**Why we selected it**The catalogue has Grafana Alloy, PromQL, and Mimir skills and not this Loki skill.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-loki/) Install command in review Apache-2.0
 Compare Grafana Loki Add

Observability · Grafana Labs

### [Grafana Mimir](/skills/grafana-mimir/)

Stand up Grafana Mimir for long-term Prometheus metrics, with the demo's single replica called out and the tenant header required once multitenancy is on.

 mimir prometheus metrics

**Why we selected it**The monolithic demo sets replication_factor to 1, and the file says filesystem storage is only for development.

**Weigh up**The Docker example uses grafana/mimir:latest, which is not a pinned image. The Helm example names mimir-distributed 6.0.6; that chart version was not checked against the chart repository.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-mimir/) Install command in review Apache-2.0
 Compare Grafana Mimir Add

On-call routing · Grafana Labs

### [Grafana OnCall and IRM](/skills/grafana-oncall-irm/)

Pins Grafana's OnCall and IRM skill, which previews a routing template before a live alert and authenticates schedule calls with a token.

 grafana oncall irm

**Why we selected it**No selected skills record uses this source path.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-oncall-irm/) Install command in review Apache-2.0
 Compare Grafana OnCall and IRM Add

Grafana OSS administration · Grafana Labs

### [Grafana OSS configuration](/skills/grafana-grafana-oss/)

Pins Grafana's OSS skill, which authenticates API checks with a bearer token, separates 401 from 403, and shows a service-account token with no expiry.

 grafana oss bearer-token

**Why we selected it**No selected skills record uses this source path.

**Weigh up**The resource was not executed.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-grafana-oss/) Install command in review Apache-2.0
 Compare Grafana OSS configuration Add

Observability · Grafana Labs

### [Grafana Pyroscope](/skills/grafana-pyroscope/)

Select SDK or Alloy profiling and inspect service-specific CPU, allocation and contention profiles.

 pyroscope profiling observability

**Why we selected it**It instruments an application for Grafana Pyroscope, either against a local server on port 4040 or Grafana Cloud with a numeric user and API key.

**Weigh up**The skill does not grant Cloud access; it requires a numeric Pyroscope user and an API key.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-pyroscope/) Install command in review Apache-2.0
 Compare Grafana Pyroscope Add

Observability · Grafana Labs

### [Grafana Tempo](/skills/grafana-tempo/)

Local and Helm setup notes plus TraceQL for a Tempo tracing backend.

 tempo traceql tracing

**Why we selected it**The file separates a localhost Docker Compose check from a Helm install and names the object-storage bucket as configuration, not as a secret in the command.

**Weigh up**The Docker example clones github.com/grafana/tempo with no revision, and the Helm example pins chart version 1.61.3. Neither command was run.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-tempo/) Install command in review Apache-2.0
 Compare Grafana Tempo Add

Security review · Trail of Bits

### [Graph Evolution](/skills/trailofbits-trailmark-graph-evolution/)

Diffs Trailmark code graphs built at two source snapshots (commits, tags or directories) to surface new attack paths, blast-radius growth, taint changes and privilege-boundary shifts that a text diff does not show.

 diff-review blast-radius graph

**Why we selected it**Diffs Trailmark graphs at two snapshots (commits, tags or directories) to surface new attack paths, blast-radius growth, taint and privilege-boundary changes.

**Weigh up**An empty `trailmark diff` can mean the wrong language rather than no change, because --language defaults to python; the skill says to pass it explicitly and re-run.

 Source reviewed

5 sources · 2026-10-22

[Read the full review ↗](/skills/trailofbits-trailmark-graph-evolution/) Upstream setup linked CC-BY-SA-4.0
 Compare Graph Evolution Add

Testing · Trail of Bits

### [Harness writing](/skills/trailofbits-harness-writing/)

Designs a libFuzzer or cargo-fuzz harness that accepts every input size, stays deterministic, and does not put unrelated formats in one target.

 fuzzing harness rust

**Why we selected it**The harness must accept empty, tiny, huge, and malformed inputs; crashes in the system under test are the signal, crashes in the harness are not.

**Weigh up**The arbitrary crate is described as having no reverse serialization, so hand-built byte strings for a specific struct are a poor fit.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-harness-writing/) Install command in review CC-BY-SA-4.0
 Compare Harness writing Add

Web performance · Microsoft

### [Heap Snapshot Analysis](/skills/microsoft-heap-snapshot-analysis/)

Investigates memory leaks from V8 heap snapshots: parsing multi-hundred-megabyte .heapsnapshot files, comparing before/after object deltas, and tracing retainer paths while skipping the weak edges and debugger artifacts that produce false suspects.

 memory-leaks heap-snapshot allocation-tracing

**Why we selected it**Bakes anti-bias discipline into the workflow: the analyst is told to start fresh and ignore prior investigation notes so stale suspects cannot steer the current analysis.

**Weigh up**The retention-pattern catalogue (RowCache, HoverService, ObjectMutationLog) is VS Code-specific; the method transfers, the named suspects do not.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-heap-snapshot-analysis/) Install command in review MIT
 Compare Heap Snapshot Analysis Add

Model development · Hugging Face

### [hf-mem Memory Estimate](/skills/huggingface-hf-mem/)

Guides metadata-based estimates for model weight memory and optional KV-cache scenarios without first downloading the weight tensors.

 vram gguf safetensors

**Why we selected it**Keeps an exact GGUF choice, context length, batch size and cache dtype visible in the estimation workflow.

**Weigh up**hf-mem describes itself as experimental; its estimate is not a measured peak allocation or a guarantee that a serving workload fits.

 Source reviewed

5 sources · 2026-10-14

[Read the full review ↗](/skills/huggingface-hf-mem/) Attributed definition available Apache-2.0
 Compare hf-mem Memory Estimate Add

Web frameworks · Yusuke Wada

### [Hono](/skills/honojs-hono/)

Inline Hono reference that chains routes for the RPC client, generates Cloudflare binding types, and snapshots a route before changing it.

 hono routing typescript

**Why we selected it**RPC types require chained routes. Binding types are generated (npm run typecheck in cf CLI projects, cf-typegen or wrangler types in wrangler projects), and the file says not to install @cloudflare/workers-types.

**Weigh up**The CLI install is @hono/cli@next, with a TODO to switch at the 1.0 release; the README Requirements line names @hono/cli without @next. That package was not installed and npx hono --help was not run. Live pages on hono.dev, which the file tells the agent to fetch with curl, were not fetched.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/skills/honojs-hono/) Install command in review MIT
 Compare Hono Add

Agent development · Anthropic

### [Hook Development for Claude Code Plugins](/skills/anthropic-hook-development/)

Explains how to write Claude Code plugin hooks, prompt-based and command-based, with their event list, input and output JSON and exit codes, and ships Bash utilities to validate, lint and test them.

 claude-code plugin-dev hooks

**Why we selected it**It separates prompt hooks, which it recommends and lists for Stop, SubagentStop, UserPromptSubmit and PreToolUse, from command hooks for deterministic checks, and gives the hook input JSON, output JSON and exit codes (0 success, 2 blocking error fed back to Claude).

**Weigh up**Last commit touching plugins/plugin-dev/skills/hook-development at revision 41f32e40: 2026-02-05 (2438937b).

 Source reviewed

10 sources · 2026-10-22

[Read the full review ↗](/skills/anthropic-hook-development/) Upstream setup linked Apache-2.0
 Compare Hook Development for Claude Code Plugins Add

Machine learning · huggingface

### [Hugging Face API Tool Builder](/skills/huggingface-tool-builder/)

Create reusable CLI scripts that inspect Hub API shapes and compose metadata requests into JSON/NDJSON pipelines.

 machine-learning huggingface

**Why we selected it**It builds a reusable script against the Hugging Face HTTP API and tells that script to send HF_TOKEN as a bearer header.

**Weigh up**The skill creates a script; it is not itself an API client that this review ran.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/huggingface-tool-builder/) Install command in review Apache-2.0
 Compare Hugging Face API Tool Builder Add

Cloud access preflight · Hugging Face

### [Hugging Face AWS Context Discovery](/skills/huggingface-hf-cloud-aws-context-discovery/)

Establish the selected AWS profile, region and caller before a cloud workflow. Useful input to credential-scoped execution, but not an authorization check or a sandbox.

 aws credentials identity

**Why we selected it**Captures which account and region a future inference or evaluation job would actually use instead of assuming a default from the model or task name.

**Weigh up**The source's SSO warnings are heuristics, not permission evidence. An ARN pattern cannot prove that IAM writes are forbidden or allowed; inspect the applicable policies separately.

 Source reviewed

6 sources · 2026-10-14

[Read the full review ↗](/skills/huggingface-hf-cloud-aws-context-discovery/) Upstream setup linked Apache-2.0
 Compare Hugging Face AWS Context Discovery Add

Data and research · Hugging Face

### [Hugging Face Dataset Workflows](/skills/huggingface-huggingface-datasets/)

Discovers a Hub dataset's subsets, splits, rows and parquet shards, while separating read-only exploration from optional repository creation and uploads.

 datasets hugging-face parquet

**Why we selected it**Requires resolving config and split before row work, making the sampling population explicit.

**Weigh up**The opening read-only scope does not cover later repository creation and upload examples. A private destination is still an external disclosure of the uploaded contents.

 Source reviewed

7 sources · 2026-10-14

[Read the full review ↗](/skills/huggingface-huggingface-datasets/) Install command in review Apache-2.0
 Compare Hugging Face Dataset Workflows Add

Machine learning · huggingface

### [Hugging Face Hub CLI](/skills/huggingface-hf-cli/)

Navigate the hf command surface for Hub repositories, local cache, datasets, jobs, buckets and endpoints.

 machine-learning huggingface

**Why we selected it**It is a command map for the hf CLI, including auth, jobs, spaces, and a secrets list that does not return secret values.

**Weigh up**The skill does not mount repositories; that is hf-mount, a different project.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/huggingface-hf-cli/) Install command in review Apache-2.0
 Compare Hugging Face Hub CLI Add

Model development · Hugging Face

### [Hugging Face LLM Trainer](/skills/huggingface-huggingface-llm-trainer/)

Prepares and submits managed training jobs with dataset checks, monitoring and explicit persistence of trained artifacts.

 fine-tuning trl hugging-face

**Why we selected it**Treats dataset shape, credentials and model persistence as prerequisites rather than leaving them until a job fails.

**Weigh up**The skill directs immediate job submission for training requests; make the target, hardware and spending scope explicit before invocation.

 Source reviewed

8 sources · 2026-10-13

[Read the full review ↗](/skills/huggingface-huggingface-llm-trainer/) Install command in review Apache-2.0
 Compare Hugging Face LLM Trainer Add

Model evaluation · Hugging Face

### [Hugging Face Local Model Evaluations](/skills/huggingface-huggingface-community-evals/)

Chooses a local evaluation framework and inference backend, starting with a small smoke run before scaling evaluation work.

 evaluations inspect-ai lighteval

**Why we selected it**Separates local GPU inference from a locally launched client that calls remote Inference Providers.

**Weigh up**The provider-backed helper still sends inference requests over the network; local script execution does not mean local inference.

 Source reviewed

7 sources · 2026-10-13

[Read the full review ↗](/skills/huggingface-huggingface-community-evals/) Install command in review Apache-2.0
 Compare Hugging Face Local Model Evaluations Add

Research publishing · Hugging Face

### [Hugging Face paper publisher](/skills/huggingface-huggingface-paper-publisher/)

Pins Hugging Face's paper skill, which requires a write token, separates a paper check from indexing, and says linking keeps existing README content.

 huggingface papers arxiv

**Why we selected it**The prerequisites require a write-access Hugging Face token, and a permission-denied result is explained as missing write access.

**Weigh up**This review did not execute the resource.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/huggingface-huggingface-paper-publisher/) Upstream setup linked Apache-2.0
 Compare Hugging Face paper publisher Add

Data and research · Hugging Face

### [Hugging Face Paper Reading](/skills/huggingface-huggingface-papers/)

Retrieves AI research-paper text and structured metadata, with fallbacks to the original arXiv page or PDF when Hub text is incomplete.

 papers arxiv literature-research

**Why we selected it**Separates paper text from metadata such as authors and linked code, models and datasets, helping a research task collect the right evidence.

**Weigh up**Hub indexing and HTML availability vary; confirm that the fetched text is the actual paper before summarizing methods or results.

 Source reviewed

6 sources · 2026-10-13

[Read the full review ↗](/skills/huggingface-huggingface-papers/) Install command in review Apache-2.0
 Compare Hugging Face Paper Reading Add

Development tooling · huggingface

### [Hugging Face Python Environment Setup](/skills/huggingface-hf-cloud-python-env-setup/)

Prepare an isolated Python environment for Hugging Face cloud tooling.

 development-tooling huggingface

**Why we selected it**setup_env.py chooses uv or venv and checks the interpreter version; check_versions.py prints NOT INSTALLED without making that a failing exit status.

**Weigh up**The setup helper deletes an existing environment directory when interpreter versions differ and upgrades requirements on reuse. The version-report helper returns success even for missing packages.

 Source reviewed

6 sources · 2026-10-14

[Read the full review ↗](/skills/huggingface-hf-cloud-python-env-setup/) Install command in review Apache-2.0
 Compare Hugging Face Python Environment Setup Add

Cloud operations · huggingface

### [Hugging Face SageMaker Deployment Planning](/skills/huggingface-hf-cloud-sagemaker-deployment-planner/)

Select a SageMaker deployment path from workload, traffic and model constraints.

 cloud-operations huggingface

**Why we selected it**The workflow discovers serving requirements before choosing infrastructure and hands off environment, IAM, image selection and production configuration explicitly.

**Weigh up**Latency and wake-up examples are planning assumptions, not measured guarantees. Sibling setup, IAM and deployment skills are separate dependencies and may not accompany a single-directory installation.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/huggingface-hf-cloud-sagemaker-deployment-planner/) Install command in review Apache-2.0
 Compare Hugging Face SageMaker Deployment Planning Add

Cloud operations · huggingface

### [Hugging Face SageMaker Deployment Templates](/skills/huggingface-hf-cloud-sagemaker-production-defaults/)

Review endpoint creation, scaling and alarm templates as one deployment plan.

 cloud-operations huggingface

**Why we selected it**_common.py waits for InService but does not test inference; deploy.py creates scaling/alarms after the endpoint, while teardown.py ignores several deletion results.

**Weigh up**Existing-model reuse is based on an exception message without comparing configuration. Deployment failures can leave billable resources; teardown can print completion despite failed deletions, and alarms without SNS do not notify.

 Source reviewed

6 sources · 2026-10-14

[Read the full review ↗](/skills/huggingface-hf-cloud-sagemaker-production-defaults/) Install command in review Apache-2.0
 Compare Hugging Face SageMaker Deployment Templates Add

Model training · Hugging Face

### [Hugging Face Sentence Transformer Training](/skills/huggingface-train-sentence-transformers/)

Routes embedding and reranker training to model-specific templates, dataset/loss checks and a before-and-after evaluation.

 embeddings reranking retrieval

**Why we selected it**Uses task-specific losses and evaluators instead of one generic fine-tuning recipe.

**Weigh up**The default full training template attempts a public Hub upload and uses Trackio reporting. Review publication, telemetry and data rights before running it with credentials.

 Source reviewed

6 sources · 2026-10-14

[Read the full review ↗](/skills/huggingface-train-sentence-transformers/) Install command in review Apache-2.0
 Compare Hugging Face Sentence Transformer Training Add

Deployment · Hugging Face

### [Hugging Face Spaces Operations](/skills/huggingface-spaces/)

Guides creating, building, debugging, and maintaining ML applications on Hugging Face Spaces across Gradio, Docker, and Static SDKs.

 huggingface spaces zerogpu

**Why we selected it**Details exact hardware tiers, ZeroGPU allocation constraints (@spaces.GPU), and quota limits (free vs Pro vs Enterprise orgs) without guessing.

**Weigh up**ZeroGPU is restricted to Gradio Spaces; Docker Spaces cannot use ZeroGPU dynamically.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/huggingface-spaces/) Install command in review Apache-2.0
 Compare Hugging Face Spaces Operations Add

Model development · Hugging Face

### [Hugging Face Trackio](/skills/huggingface-huggingface-trackio/)

Adds training metrics and diagnostic alerts, then retrieves run data through Trackio’s CLI or a local or hosted dashboard.

 experiments training-metrics alerts

**Why we selected it**Separates logging, alerting and retrieval into focused references, including a route from an alert to metrics around the relevant training step.

**Weigh up**The private flag only affects newly created Spaces; inspect an existing Space’s visibility before uploading metrics. Webhooks and remote synchronization send data outside the machine.

 Source reviewed

9 sources · 2026-10-13

[Read the full review ↗](/skills/huggingface-huggingface-trackio/) Install command in review Apache-2.0
 Compare Hugging Face Trackio Add

Machine Learning · Hugging Face

### [Hugging Face Transformers.js](/skills/huggingface-transformers-js/)

Runs state-of-the-art machine learning models directly in JavaScript and TypeScript with WebGPU and WebAssembly.

 huggingface transformers-js webgpu

**Why we selected it**Covers client-side and Node.js inference patterns with hardware acceleration (WebGPU) and broad fallback (WASM), eliminating Python server dependencies.

**Weigh up**WebGPU acceleration requires compatible browser versions and operating system GPU drivers; falls back to slower WASM when unsupported.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/huggingface-transformers-js/) Install command in review Apache-2.0
 Compare Hugging Face Transformers.js Add

Machine learning · huggingface

### [Hugging Face Vision Training](/skills/huggingface-vision-trainer/)

Prepare dataset-validated detection, classification or segmentation training jobs with explicit Hub persistence and job-secret handling.

 machine-learning huggingface

**Why we selected it**It submits object-detection, classification, or SAM training to Hugging Face Jobs and saves results on the Hub.

**Weigh up**The skill says not to poll a running job automatically.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/huggingface-vision-trainer/) Install command in review Apache-2.0
 Compare Hugging Face Vision Training Add

Machine learning · huggingface

### [Hugging Face ZeroGPU](/skills/huggingface-zerogpu/)

Design Gradio GPU handlers around process isolation, serialized state, dynamic duration and concurrent requests.

 machine-learning huggingface

**Why we selected it**It constrains Gradio Spaces on ZeroGPU: the real GPU exists only inside spaces.GPU, and CUDA tensors must not cross that boundary.

**Weigh up**Docker, Static, and Streamlit Spaces cannot schedule onto ZeroGPU.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/huggingface-zerogpu/) Install command in review Apache-2.0
 Compare Hugging Face ZeroGPU Add

iMessage access control · Anthropic

### [iMessage access](/skills/anthropic-imessage-access/)

Pins the iMessage access skill, which refuses channel-originated edits and defaults a missing policy file to allowlist because pairing would auto-reply.

 imessage access-control allowlist

**Why we selected it**The skill refuses access changes that arrive as an iMessage, Telegram, or Discord notification and will not approve a pairing unless the user supplies the code.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/anthropic-imessage-access/) Install command in review Apache-2.0
 Compare iMessage access Add

iMessage channel setup · Anthropic

### [iMessage configure](/skills/anthropic-imessage-configure/)

Pins the iMessage setup skill, which only reports status, checks Full Disk Access, and pushes pairing back toward an allowlist.

 imessage full-disk-access allowlist

**Why we selected it**If listing chat.db fails with Operation not permitted, the skill says Full Disk Access is not granted and the server cannot read that database.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/anthropic-imessage-configure/) Install command in review Apache-2.0
 Compare iMessage configure Add

Planning and delivery · GitHub community

### [Incident Post-Mortem](/skills/github-incident-postmortem/)

Walks a team from incident metadata through a reconstructed timeline, blameless 5-Whys root cause, quantified impact and owned action items, into a complete postmortem document with a common-mistakes table.

 postmortem incident blameless

**Why we selected it**The blameless principle is operational, not aspirational: a common-mistakes table rewrites 'Bob forgot to check the config' into 'the deploy checklist did not include config validation' and treats human error as a symptom, never a root cause.

**Weigh up**Single self-contained SKILL.md with no references; severity scales and SLA definitions must come from the team's own incident process.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/github-incident-postmortem/) Install command in review MIT
 Compare Incident Post-Mortem Add

Identity and access · Infisical Inc.

### [Infisical Access Control and Governance Guide](/skills/infisical-access-control/)

Infisical skill for deciding what a user or machine identity may do inside Infisical: org and project roles, granular secret permissions, ABAC, temporary access, approval policies and audit log streams.

 infisical access-control permissions

**Why we selected it**It separates describeSecret (seeing that a secret exists and its metadata) from readValue (seeing the value), and warns that the legacy read action grants both.

**Weigh up**Approval workflows and access requests are Enterprise tier on Infisical Cloud and need an enterprise license when self-hosted, per references/approvals-and-audit.md.

 Source reviewed

7 sources · 2026-10-21

[Read the full review ↗](/skills/infisical-access-control/) Upstream setup linked MIT
 Compare Infisical Access Control and Governance Guide Add

Security · Infisical Inc.

### [Infisical Agent Guide](/skills/infisical-agent/)

Infisical skill for configuring the Infisical Agent, a client daemon that authenticates, renews tokens and renders secrets into files through Go templates.

 infisical secrets sidecar

**Why we selected it**It covers the agent's YAML config, all 6 agent auth methods, sinks, polling and the template functions listSecrets, listSecretsByProjectSlug, getSecretByName and dynamicSecret.

**Weigh up**dynamicSecret needs its trailing principals argument for SSH dynamic secrets, which the skill marks as required.

 Source reviewed

6 sources · 2026-10-21

[Read the full review ↗](/skills/infisical-agent/) Upstream setup linked MIT
 Compare Infisical Agent Guide Add

Security · Infisical Inc.

### [Infisical API Skill](/skills/infisical-api/)

Infisical skill for calling the Infisical REST API directly: Universal Auth login, /api/v4/secrets CRUD and batch calls, projects and identities, pagination and rate limits.

 infisical api secrets

**Why we selected it**It states that /api/v4/secrets is not paginated and ignores offset and limit, while identities, memberships and certificates paginate and return { <resource>: [...], totalCount: n }.

**Weigh up**It covers the core secrets, projects and identities API; KMS, certificate, sync, rotation and App Connection endpoints are left to their own skills.

 Source reviewed

6 sources · 2026-10-21

[Read the full review ↗](/skills/infisical-api/) Upstream setup linked MIT
 Compare Infisical API Skill Add

Security · Infisical Inc.

### [Infisical App Connections Guide](/skills/infisical-app-connections/)

Infisical skill for creating App Connections, the stored credentials Infisical uses to authenticate out to third-party services for secret syncs, rotations, PKI and secret scanning.

 infisical credentials oauth

**Why we selected it**Two of its reference files are generated from the Infisical source by tools/generate-app-connection-refs.py: the API surface, and the exact method values and credential fields for all 83 connections.

**Weigh up**Only 16 connection types accept gatewayId; passing one to any other type is a validation error, not a no-op.

 Source reviewed

6 sources · 2026-10-21

[Read the full review ↗](/skills/infisical-app-connections/) Upstream setup linked MIT
 Compare Infisical App Connections Guide Add

Security · Infisical Inc.

### [Infisical Dynamic Secrets Guide](/skills/infisical-dynamic-secrets/)

Infisical skill for configuring dynamic secrets: short-lived credentials created per lease for databases, cloud IAM, SSH certificates, Kubernetes service accounts and other providers.

 infisical secrets credentials

**Why we selected it**It covers the providers its description lists, from PostgreSQL and Redis to AWS IAM, GCP IAM, Azure Entra ID, SSH certificates and TOTP.

**Weigh up**A database in a private network needs an Infisical Gateway, which the skill calls an Enterprise feature (Cloud Enterprise tier or self-hosted Enterprise license).

 Source reviewed

7 sources · 2026-10-21

[Read the full review ↗](/skills/infisical-dynamic-secrets/) Upstream setup linked MIT
 Compare Infisical Dynamic Secrets Guide Add

Infrastructure · Infisical Inc.

### [Infisical Gateway Guide](/skills/infisical-gateway/)

Infisical skill for deploying the Infisical Gateway and relays so that Infisical can reach private databases, directories, APIs and HSMs over outbound-only SSH reverse tunnels.

 infisical networking egress

**Why we selected it**It names the exact egress the gateway needs: TCP 2222 to the relay, TCP 443 to Infisical, and TCP 8443 platform-to-relay.

**Weigh up**Gateway is a paid Enterprise feature, and Gateway Pools are an Enterprise feature too.

 Source reviewed

7 sources · 2026-10-21

[Read the full review ↗](/skills/infisical-gateway/) Upstream setup linked MIT
 Compare Infisical Gateway Guide Add

Security · Infisical Inc.

### [Infisical KMS Guide](/skills/infisical-kms/)

Infisical skill for creating KMS keys and calling encrypt, decrypt, sign, verify and MAC operations with keys that stay inside Infisical.

 infisical cryptography aws

**Why we selected it**It fixes each key to one keyUsage (encrypt-decrypt, sign-verify or generate-verify-mac) and lists the operations each allows.

**Weigh up**Rotating a key adds a new version for new operations and does not re-encrypt existing ciphertext.

 Source reviewed

7 sources · 2026-10-21

[Read the full review ↗](/skills/infisical-kms/) Upstream setup linked MIT
 Compare Infisical KMS Guide Add

Containers · Infisical Inc.

### [Infisical Kubernetes Operator Guide](/skills/infisical-kubernetes-operator/)

Infisical skill for running the Infisical Kubernetes Operator: syncing secrets into Kubernetes Secrets and ConfigMaps, pushing secrets back to Infisical, and managing dynamic secret leases in-cluster.

 infisical kubernetes secrets

**Why we selected it**It makes the agent establish the CRD API version first: v1beta1 splits the work into InfisicalConnection, InfisicalAuth and InfisicalStaticSecret, while legacy v1alpha1 puts it all in one InfisicalSecret.

**Weigh up**The skill documents InfisicalDynamicSecret and InfisicalPushSecret only at v1alpha1, which it calls legacy and deprecating soon.

 Source reviewed

7 sources · 2026-10-21

[Read the full review ↗](/skills/infisical-kubernetes-operator/) Upstream setup linked MIT
 Compare Infisical Kubernetes Operator Guide Add

Security · Infisical Inc.

### [Infisical PKI](/skills/infisical-pki/)

Pins Infisical's certificate-management skill and its rule to send SSH certificates to a different skill.

 infisical pki certificates

**Why we selected it**The catalogue has Infisical secret scanning and not this PKI skill.

**Weigh up**This review did not execute the resource.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/infisical-pki/) Install command in review MIT
 Compare Infisical PKI Add

Identity and access · Infisical Inc.

### [Infisical Privileged Access Manager (PAM) Guide](/skills/infisical-pam/)

Infisical skill for brokering human and AI-agent sessions to databases, servers, Kubernetes clusters and cloud accounts through Infisical PAM, with recording and without handing over a credential.

 infisical access-control approval

**Why we selected it**It covers agentic access, infisical pam agentic access -- <agent>, which opens one local port per account and has the Gateway inject the real credential so none reaches the agent.

**Weigh up**PAM is a separate Infisical product with its own project type and is an Enterprise feature.

 Source reviewed

7 sources · 2026-10-21

[Read the full review ↗](/skills/infisical-pam/) Upstream setup linked MIT
 Compare Infisical Privileged Access Manager (PAM) Guide Add

Security · Infisical Inc.

### [Infisical Secret Rotation Guide](/skills/infisical-secret-rotation/)

Infisical skill for rotating credentials that already exist in a third-party system on a fixed interval and writing the new values back into Infisical secrets.

 infisical credentials secrets

**Why we selected it**It covers the rotation providers its description lists and makes the agent establish whether a provider is dual-phase or single-phase, because that changes the operational advice.

**Weigh up**Rotation is an Enterprise / paid feature, per references/rotation-overview.md.

 Source reviewed

7 sources · 2026-10-21

[Read the full review ↗](/skills/infisical-secret-rotation/) Upstream setup linked MIT
 Compare Infisical Secret Rotation Guide Add

Security · Infisical Inc.

### [Infisical secret scanning](/skills/infisical-secret-scanning/)

Infisical skill for scanning GitHub, GitLab, and Bitbucket history for leaked credentials, with GitHub tied to a github-radar connection and rotation required before history is rewritten.

 infisical secrets scanning

**Why we selected it**The catalogue has a Vault MCP server and no Infisical secret-scanning skill.

**Weigh up**This review did not execute the skill or infisical scan.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/infisical-secret-scanning/) Install command in review MIT
 Compare Infisical secret scanning Add

Security · Infisical Inc.

### [Infisical Secret Syncs Guide](/skills/infisical-secret-syncs/)

Infisical skill for configuring Secret Syncs that push secrets from an Infisical project to third-party destinations such as AWS Secrets Manager, GCP Secret Manager, Azure Key Vault, GitHub and Vercel.

 infisical secrets github

**Why we selected it**It gives the exact initial sync enum values, overwrite-destination, import-prioritize-source and import-prioritize-destination, and says names such as import-prioritize-infisical do not exist.

**Weigh up**Infisical is the source of truth: destination secrets not in Infisical may be overwritten depending on initial sync behaviour, and auto-sync is on by default.

 Source reviewed

7 sources · 2026-10-21

[Read the full review ↗](/skills/infisical-secret-syncs/) Install command in review MIT
 Compare Infisical Secret Syncs Guide Add

Infrastructure · Infisical Inc.

### [Infisical Self-Hosted Deployment](/skills/infisical-self-host/)

Infisical skill for deploying and running a self-hosted Infisical instance with Docker, Docker Compose or the Kubernetes Helm chart, including its PostgreSQL and Redis dependencies.

 infisical self-host docker

**Why we selected it**It states that ENCRYPTION_KEY cannot be recovered if lost and gives its format: openssl rand -hex 16 for standard deployments, a 256-bit base64 key from openssl rand -base64 32 with FIPS.

**Weigh up**PostgreSQL is the only supported database; the skill says to use 14+ and that Infisical is extensively tested on 16.

 Source reviewed

6 sources · 2026-10-21

[Read the full review ↗](/skills/infisical-self-host/) Upstream setup linked MIT
 Compare Infisical Self-Hosted Deployment Add

Identity and access · Infisical Inc.

### [Infisical SSO and User Provisioning Guide](/skills/infisical-sso/)

Infisical skill for connecting an identity provider for human login and SCIM user and group provisioning, including SSO enforcement and the /login/admin break-glass portal.

 infisical sso identity

**Why we selected it**It gives the prerequisite chain in order: email domain verification, then SAML or OIDC, then SCIM provisioning, then group mappings to roles.

**Weigh up**Only Google and GitHub SSO are free; SAML 2.0 and OIDC need the Cloud Pro tier, SCIM the Cloud Enterprise tier, and references/sso-setup.md lists LDAP login as Paid (Enterprise).

 Source reviewed

7 sources · 2026-10-21

[Read the full review ↗](/skills/infisical-sso/) Upstream setup linked MIT
 Compare Infisical SSO and User Provisioning Guide Add

Infrastructure development · Infisical Inc.

### [Infisical Terraform Provider](/skills/infisical-terraform/)

Infisical skill for the Infisical Terraform provider: provider authentication, ephemeral secret reads, data sources, project roles, access approval policies and Terraform Cloud OIDC.

 infisical terraform hcl

**Why we selected it**It says provider credentials go inside a nested auth attribute, auth = { universal = { client_id, client_secret } } or auth = { oidc = { identity_id, token_environment_variable_name } }, and that client_id, client_secret or identity_id set directly on the provider block fail at plan time.

**Weigh up**The infisical_secrets data source stores secret values in Terraform state, per references/resources-and-data-sources.md; only the ephemeral resource keeps them out, and it requires Terraform 1.10 or later.

 Source reviewed

7 sources · 2026-10-21

[Read the full review ↗](/skills/infisical-terraform/) Upstream setup linked MIT
 Compare Infisical Terraform Provider Add

Security · Infisical Inc.

### [Infisical User Setup Guide](/skills/infisical-setup/)

Infisical skill for getting secrets from Infisical into applications and platforms: the CLI, Docker, CI/CD, Kubernetes, the language SDKs and machine identity authentication.

 infisical secrets cli

**Why we selected it**Its references/agent-bootstrap.md tells an agent running the CLI how to log in, create and link a project, and import .env files without the interactive prompts that hang a subprocess.

**Weigh up**Following agent-bootstrap.md sends .env values to the user's Infisical project with infisical secrets set; the reference requires an explicit yes from the user first and tells the agent not to open, read or print the files.

 Source reviewed

7 sources · 2026-10-21

[Read the full review ↗](/skills/infisical-setup/) Upstream setup linked MIT
 Compare Infisical User Setup Guide Add

API design · JetBrains

### [Integration Resilience Engineer](/skills/jetbrains-integration-resilience-engineer/)

Designs resilient HTTP, messaging and scheduled integrations: timeout budgets derived from the caller’s SLO, retryable-versus-terminal failure classification, idempotency and deduplication, circuit breakers, DLQ behaviour, and distributed locking for scheduled jobs.

 retries idempotency circuit-breakers

**Why we selected it**Derives timeout budgets backward from the caller’s SLO and classifies every operation (read-only versus state-changing, idempotent versus not) before any retry policy is written.

**Weigh up**The worked context is Kotlin plus Spring; the design sequence and rules transfer, the framework-specific examples do not.

 Source reviewed

6 sources · 2026-10-13

[Read the full review ↗](/skills/jetbrains-integration-resilience-engineer/) Install command in review MIT (upstream Kotlin backend agent skills)
 Compare Integration Resilience Engineer Add

Documentation and knowledge · Anthropic

### [Internal Communications](/skills/anthropics-internal-comms/)

Formats source-backed team updates, internal newsletters and employee FAQs for a defined audience.

 communications status-updates faq

**Why we selected it**The main file is a router to four example formats rather than one generic memo voice.

**Weigh up**The skill says to follow the matching example file for formatting and content gathering; the root file does not contain those rules.

 Source reviewed

5 sources · 2026-10-14

[Read the full review ↗](/skills/anthropics-internal-comms/) Install command in review Apache-2.0
 Compare Internal Communications Add

Kusto graph visualization · Microsoft

### [IRQL graph visualization](/skills/microsoft-azure-kusto-irql-graph/)

Pins Microsoft's IRQL graph skill, which asks before deploying a missing stored graph function and will not invent joins or columns.

 kusto kql irql

**Why we selected it**Deploying a missing required graph function is a database alter, and the file says to ask for confirmation before that deploy.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-kusto-irql-graph/) Upstream setup linked MIT
 Compare IRQL graph visualization Add

Development workflow · getsentry

### [Iterate on Pull Requests](/skills/getsentry-iterate-pr/)

Resolve actionable CI failures and review feedback while reporting human merge gates separately.

 development-workflow getsentry

**Why we selected it**The loop fixes failing checks and high or medium review comments, then commits and pushes. It does not wait for human approval or a merge gate.

**Weigh up**fetch_pr_checks.py only reads gh. reply_to_thread.py posts review replies through GitHub's GraphQL API. Both need a logged-in gh.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-iterate-pr/) Install command in review Apache-2.0
 Compare Iterate on Pull Requests Add

Java migration · GitHub community (awesome-copilot)

### [Javax to Jakarta Namespace Migration](/skills/github-javax-to-jakarta-migration/)

Distinguish migrated Jakarta EE packages from javax packages that remain in the JDK.

 java-migration github

**Why we selected it**The definition explicitly exempts javax.sql, naming, crypto, net and other JDK APIs while mapping EE packages and checking residual imports after the migration.

**Weigh up**The listed dependency and descriptor versions are examples, not a compatibility matrix for every Tomcat/Jakarta target. Blind global replacement would corrupt JDK imports and miss reflection strings or descriptors.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/github-javax-to-jakarta-migration/) Install command in review MIT
 Compare Javax to Jakarta Namespace Migration Add

Testing and reliability · Grafana Labs

### [k6](/skills/grafana-k6/)

Writes a k6 script from a matching example, then validates it by running it rather than by reading it.

 k6 load-testing performance

**Why we selected it**The workflow is read example, adapt, save, validate, review, and it says to skip a todo list that would only mirror those steps.

**Weigh up**The validation table uses k6 run for browser scripts first; otherwise ramping-vus and arrival-rate scenarios use k6 inspect to avoid executing the entire load profile. Other rows run the script. This review did not execute any validation.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-k6/) Install command in review Apache-2.0
 Compare k6 Add

k6 documentation · Grafana Labs

### [k6 documentation](/skills/grafana-k6-docs/)

Pins Grafana's k6 documentation skill, which requires a confirmation before any git push and a clean k6 master run before commit.

 k6 documentation git

**Why we selected it**No selected skills record uses this source path.

**Weigh up**The resource was not executed.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-k6-docs/) Install command in review Apache-2.0
 Compare k6 documentation Add

Testing and reliability · Grafana Labs

### [k6 test maintenance](/skills/grafana-k6-test-maintenance/)

Treats a k6 edit as behaviour-aware change control, with a validation loop on every edit.

 k6 load-testing maintenance

**Why we selected it**The core-principle heading is behaviour-aware change control.

**Weigh up**Maintaining a script does not create a load measurement.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-k6-test-maintenance/) Install command in review Apache-2.0
 Compare k6 test maintenance Add

k6 trend reporting · Grafana

### [k6 trend analysis](/skills/grafana-k6-trend-analysis/)

Pins Grafana's k6 trend skill, which reports drift and headroom and refuses to apply script or threshold edits itself.

 grafana k6 trends

**Why we selected it**No selected skills record uses this source path.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-k6-trend-analysis/) Install command in review Apache-2.0
 Compare k6 trend analysis Add

Website load testing · Grafana

### [k6 website performance test](/skills/grafana-k6-perf-test-website/)

Pins Grafana's website k6 skill, which stops without a named workflow and will not design thresholds until functional tests exit cleanly.

 grafana k6 load-test

**Why we selected it**No selected skills record uses this source path.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-k6-perf-test-website/) Install command in review Apache-2.0
 Compare k6 website performance test Add

Kusto graph queries · Microsoft

### [Kusto Graph Semantics](/skills/microsoft-azure-kusto-graph/)

Pins Microsoft's Kusto graph skill, which requires the exact command and an explicit confirmation before a graph model or snapshot is created, altered, or dropped.

 kusto kql graph

**Why we selected it**Control commands that create, alter, or drop graph models and snapshots must be shown with cluster, database, and object, then explicitly confirmed.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-kusto-graph/) Upstream setup linked MIT
 Compare Kusto Graph Semantics Add

Model evaluation · LangChain

### [LangSmith Evaluator](/skills/langchain-ai-langsmith-evaluator/)

Builds LangSmith offline and online evaluators, with rules for name-based deletes and judge model configuration.

 langsmith llm-as-judge evaluation

**Why we selected it**The file warns that evaluator delete is name-based and removes every workspace rule with that display name, and says to run get first and never pass --yes unless the user asks.

**Weigh up**Setup installs the LangSmith CLI by piping an unpinned script from cli.langsmith.com to sh. That script was not inspected.

 Source reviewed

3 sources · 2026-10-13

[Read the full review ↗](/skills/langchain-ai-langsmith-evaluator/) Install command in review MIT
 Compare LangSmith Evaluator Add

Delivery automation · addyosmani

### [Launch and Rollback Planning](/skills/addyosmani-shipping-and-launch/)

Prepare a staged release with monitoring, ownership and rollback criteria.

 delivery-automation addyosmani

**Why we selected it**The checklist includes post-launch verification, expiring feature flags and an error-budget gate instead of treating successful deployment as the outcome.

**Weigh up**The fixed percentage thresholds and timing examples are templates, not statistically justified universal gates. Automated accessibility/security scans do not certify all behavior.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/addyosmani-shipping-and-launch/) Install command in review MIT
 Compare Launch and Rollback Planning Add

Testing · trailofbits

### [LibAFL Fuzzer Architecture](/skills/trailofbits-libafl/)

Design a custom fuzzer from observers, feedback, objectives, schedulers and executors.

 testing trailofbits

**Why we selected it**LibAFL is presented as a Rust library for a custom fuzzer when libFuzzer or AFL++ do not fit the target.

**Weigh up**Cloning and the rustup installer in the install section are network steps. This review did not run them, and the skill does not pin the LibAFL revision it clones.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-libafl/) Install command in review CC-BY-SA-4.0
 Compare LibAFL Fuzzer Architecture Add

Observability · Elastic

### [LLM and Agentic Observability](/skills/elastic-observability-llm-obs/)

Answers LLM latency, token, cost and call-chain questions from telemetry already in Elastic, and says so when cost is not instrumented.

 llm-observability esql token-cost

**Why we selected it**If no cost field exists, the file says to report that cost is not instrumented and never multiply token counts by a guessed per-token price.

**Weigh up**The time-series path needs Elasticsearch Stack 9.4 or Serverless; below that the file falls back to FROM with BUCKET, with a base floor of 8.11.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/skills/elastic-observability-llm-obs/) Install command in review Apache-2.0
 Compare LLM and Agentic Observability Add

Development workflow · GitHub community (awesome-copilot)

### [Local Web Application Testing](/skills/github-webapp-testing/)

Exercise a running web app with Playwright and retain browser evidence for failed flows.

 development-workflow github

**Why we selected it**It drives a local web app with Playwright, preferring the Playwright MCP server and falling back to a local Node install.

**Weigh up**Native mobile apps are out of scope.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/github-webapp-testing/) Install command in review MIT
 Compare Local Web Application Testing Add

Loki label governance · Grafana Labs

### [Loki label strategy evaluator](/skills/grafana-loki-label-analyzer/)

Pins Grafana's Loki label skill, which refuses to drop three correlation labels and will not ship an audit without its disclaimer.

 grafana loki labels

**Why we selected it**No selected skills record uses this source path.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-loki-label-analyzer/) Install command in review Apache-2.0
 Compare Loki label strategy evaluator Add

Device provisioning · Anthropic

### [M5Stack onboarding](/skills/anthropic-m5-onboard/)

Pins the M5 onboard skill, which will not guess a serial port or continue a native-USB flash until the user confirms download mode.

 m5stack esp32 cardputer

**Why we selected it**If more than one board is connected, the skill says to ask which port to target and not to guess, and a bare Cardputer must be asked apart from Cardputer-Adv because the wrong image boot-loops the device.

**Weigh up**This review did not execute the resource.

 Source reviewed

7 sources · 2026-10-15

[Read the full review ↗](/skills/anthropic-m5-onboard/) Install command in review Apache-2.0
 Compare M5Stack onboarding Add

Documentation and knowledge · Sentry

### [Maintaining AGENTS.md](/skills/getsentry-agents-md/)

Keeps agent instruction files short and points at existing docs instead of duplicating them.

 agents-md instructions repositories

**Why we selected it**The length cap and the symlink rule are explicit, so the file cannot grow into a second README.

**Weigh up**The file must stay at or under 100 lines, with a target under 60.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-agents-md/) Install command in review Apache-2.0
 Compare Maintaining AGENTS.md Add

Documentation · GitHub community (awesome-copilot)

### [Markdown to HTML Workflows](/skills/github-markdown-to-html/)

Choose a Markdown renderer and preserve document structure during HTML conversion.

 documentation github

**Why we selected it**The definition separates conversion, syntax-highlighting, math extensions and static-site tooling; it calls out sanitization and template execution settings as separate concerns.

**Weigh up**Examples span different tools and versions; stated full-compatibility percentages are not measured here. Markdown rendering does not sanitize untrusted HTML or guarantee safe publication.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/github-markdown-to-html/) Install command in review MIT
 Compare Markdown to HTML Workflows Add

Research and documentation · Anthropic

### [math-proof: siege](/skills/anthropic-math-proof-siege/)

Runs an hours-long, multi-round attack on one hard mathematics problem with judge and worker sub-agents and a bookkeeping script, ending in a proof.md whose Status section says what is and is not proved.

 proofs reasoning subagents

**Why we selected it**The orchestrating session does no mathematics: each step goes to a fresh math-proof-judge subagent and each query to a fresh worker that sees only that query and the problem, and the judge keeps a ledger of claims marked PROVED, REFUTED or OPEN.

**Weigh up**Last commit touching plugins/math-proof/skills/siege at revision 41f32e40: 2026-09-30 (aa5654b7).

 Source reviewed

7 sources · 2026-10-22

[Read the full review ↗](/skills/anthropic-math-proof-siege/) Setup example in review Apache-2.0
 Compare math-proof: siege Add

Research and documentation · Anthropic

### [math-proof: solo](/skills/anthropic-math-proof-solo/)

Works one hard mathematics problem in the current Claude Code session, writing each settled step to a notes file as it goes and ending with a self-contained proof.md.

 proofs reasoning claude-code

**Why we selected it**Its tool boundary is written down: the frontmatter disallows WebSearch, WebFetch and AskUserQuestion and pre-approves Read, Write, Edit, Glob, Grep and Bash only for mkdir, cp and cmp, and the body says to use the shell for nothing else.

**Weigh up**Last commit touching plugins/math-proof/skills/solo at revision 41f32e40: 2026-09-30 (aa5654b7).

 Source reviewed

3 sources · 2026-10-21

[Read the full review ↗](/skills/anthropic-math-proof-solo/) Setup example in review Apache-2.0
 Compare math-proof: solo Add

Web development · Matt Pocock

### [Matt Pocock Codebase Design](/skills/mattpocock-codebase-design/)

Evaluates module boundaries through caller complexity, dependency seams and alternative interface designs.

 architecture interfaces refactoring

**Why we selected it**Defines a deep module by what callers can accomplish through a small interface, rather than by its line count.

**Weigh up**The adapter and interface rules are design heuristics, not universal requirements; local substitutes do not prove production integration behavior.

 Source reviewed

16 sources · 2026-10-15

[Read the full review ↗](/skills/mattpocock-codebase-design/) Install command in review MIT
 Compare Matt Pocock Codebase Design Add

Research and documentation · Matt Pocock

### [Matt Pocock Domain Modeling](/skills/mattpocock-domain-modeling/)

Builds a project glossary (GLOSSARY.md) and short architecture decision records while testing domain terms against code and concrete edge cases.

 domain-modeling glossary architecture-decisions

**Why we selected it**Distinguishes canonical domain terms from implementation notes and uses conflicting examples to expose overloaded language.

**Weigh up**The root and bounded-context instructions do not fully agree on glossary and ADR placement; agree the target paths and numbering convention first.

 Source reviewed

16 sources · 2026-10-15

[Read the full review ↗](/skills/mattpocock-domain-modeling/) Install command in review MIT
 Compare Matt Pocock Domain Modeling Add

Research and documentation · Matt Pocock

### [Matt Pocock Grilling](/skills/mattpocock-grilling/)

Interviews the user through dependency-ordered decisions before the agent acts on a plan or idea.

 planning requirements decision-making

**Why we selected it**Only asks decisions whose prerequisites are settled, so answers do not depend on unanswered questions from the same round.

**Weigh up**The interview has no built-in round cap and can be too demanding for a small task; choose its scope deliberately.

 Source reviewed

15 sources · 2026-10-15

[Read the full review ↗](/skills/mattpocock-grilling/) Install command in review MIT
 Compare Matt Pocock Grilling Add

Agent development · Anthropic

### [MCP Integration for Claude Code Plugins](/skills/anthropic-mcp-integration/)

Explains how a Claude Code plugin bundles MCP servers, through .mcp.json or plugin.json, for stdio, SSE, HTTP and WebSocket servers, and how plugin commands pre-allow the resulting MCP tools.

 claude-code plugin-dev mcp

**Why we selected it**It covers both ways a plugin can bundle MCP servers, a dedicated .mcp.json at the plugin root or an mcpServers field in plugin.json, with configuration examples for stdio, SSE, HTTP and WebSocket servers.

**Weigh up**Last commit touching plugins/plugin-dev/skills/mcp-integration at revision 41f32e40: 2026-08-06 (088bee40).

 Source reviewed

6 sources · 2026-10-21

[Read the full review ↗](/skills/anthropic-mcp-integration/) Upstream setup linked Apache-2.0
 Compare MCP Integration for Claude Code Plugins Add

Data engineering · dbt-labs

### [Mermaid dbt Lineage](/skills/dbt-labs-creating-mermaid-dbt-dag/)

Render model lineage with explicit local, production or artifact provenance.

 data-engineering dbt-labs

**Why we selected it**It draws a Mermaid lineage diagram from dbt MCP, manifest.json, or parsed code, in that order.

**Weigh up**The skill asks for the model name instead of guessing it.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/dbt-labs-creating-mermaid-dbt-dag/) Install command in review Apache-2.0
 Compare Mermaid dbt Lineage Add

Security review · Trail of Bits

### [Mermaid to ProVerif](/skills/trailofbits-trailmark-mermaid-to-proverif/)

Reads a Mermaid sequence diagram of a cryptographic protocol and writes a ProVerif .pv model, with queries for secrecy, authentication and forward secrecy, that can be passed to the ProVerif verifier.

 cryptography formal-methods protocol

**Why we selected it**Translates a Mermaid sequenceDiagram, typically the output of crypto-protocol-diagram, into a ProVerif .pv model with queries for secrecy, authentication and forward secrecy.

**Weigh up**Its stated tools are Read, Write, Grep and Glob, with no Bash: it writes the .pv model and the user runs ProVerif on it.

 Source reviewed

5 sources · 2026-10-22

[Read the full review ↗](/skills/trailofbits-trailmark-mermaid-to-proverif/) Upstream setup linked CC-BY-SA-4.0
 Compare Mermaid to ProVerif Add

Billing · Stripe

### [Metronome](/skills/stripe-metronome/)

Stripe's Metronome skill for usage ingestion, contracts, and invoice sync, with confirmation required before writes because sandbox and production share one API host.

 metronome stripe usage-billing

**Why we selected it**The catalogue has stripe-pay and withholds two other Stripe skills; it has no Metronome skill.

**Weigh up**This review did not execute the skill or call api.metronome.com.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/stripe-metronome/) Install command in review MIT
 Compare Metronome Add

Agent Frameworks · Microsoft

### [Microsoft Agent Framework Azure AI](/skills/microsoft-agent-framework-azure-ai/)

Shows how to build a persistent Azure AI Foundry agent with the Python agent-framework SDK, DefaultAzureCredential, and hosted tools.

 microsoft azure-ai agent-framework

**Why we selected it**Authentication is pinned to DefaultAzureCredential rather than connection strings.

**Weigh up**The skill says to avoid connection strings and account keys.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-agent-framework-azure-ai/) Install command in review MIT
 Compare Microsoft Agent Framework Azure AI Add

Cloud operations · Microsoft

### [Microsoft Azure Cost Management](/skills/microsoft-azure-cost/)

Connects Azure cost reports to actual billing queries, utilization evidence and separately identified savings estimates.

 azure cost-management finops

**Why we selected it**Requires the total bill and service breakdown alongside optimization suggestions.

**Weigh up**Requires Azure billing/monitoring permissions and supporting CLI or MCP tools.

 Source reviewed

9 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-cost/) Install command in review MIT
 Compare Microsoft Azure Cost Management Add

Cloud operations · Microsoft

### [Microsoft Azure Diagnostics](/skills/microsoft-azure-diagnostics/)

Routes Azure incidents through resource health, recent changes, logs and service-specific troubleshooting guides.

 azure aks logs

**Why we selected it**Separates Container Apps, App Service, Functions, AKS, compute and messaging investigations, each routed to its own reference.

**Weigh up**The AKS helper selects Azure resources by arguments but uses the existing kubectl context; confirm both point to the same cluster.

 Source reviewed

9 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-diagnostics/) Install command in review MIT
 Compare Microsoft Azure Diagnostics Add

Research and documentation · Microsoft

### [Microsoft Docs Research](/skills/microsoft-microsoft-docs/)

Finds current Microsoft documentation with task-specific queries and retrieves full pages when excerpts are insufficient.

 microsoft azure dotnet

**Why we selected it**Asks for version, platform and task context in documentation searches.

**Weigh up**This is a retrieval workflow, not an implementation validator; official documentation still needs to match the installed version and target environment.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-microsoft-docs/) Install command in review MIT
 Compare Microsoft Docs Research Add

Identity and access · Microsoft

### [Microsoft Entra Agent ID](/skills/microsoft-entra-agent-id/)

Pins Microsoft's Entra Agent ID skill, which rejects Azure CLI tokens for these APIs and keeps the AgentID sidecar on localhost.

 entra agent-identity oauth

**Why we selected it**The catalogue has entra-app-registration from this plugin and not this Agent Identity blueprint skill.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-entra-agent-id/) Install command in review MIT
 Compare Microsoft Entra Agent ID Add

Identity and access · Microsoft

### [Microsoft Entra app registration](/skills/microsoft-entra-app-registration/)

Pins Microsoft's Entra app-registration skill, which sends Key Vault secret work elsewhere and says not to hardcode client secrets.

 microsoft entra oauth

**Why we selected it**The catalogue has Microsoft identity and Key Vault Python SDK skills and not this Entra app-registration procedure.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-entra-app-registration/) Install command in review MIT
 Compare Microsoft Entra app registration Add

Identity and access · Microsoft

### [Microsoft Entra Authentication Events SDK for .NET](/skills/microsoft-microsoft-azure-webjobs-extensions-authentication-events-dotnet/)

Microsoft's .NET guide to Azure Functions handlers for Entra ID custom authentication extensions: adding claims at token issuance, prefilling or validating sign-up attributes, and sending one-time passcodes through your own channel.

 entra-id claims authentication

**Why we selected it**It gives a handler for each of the four events it lists (OnTokenIssuanceStart, OnAttributeCollectionStart, OnAttributeCollectionSubmit and OnOtpSend), each returning the matching WebJobs response type.

**Weigh up**Both install lines Microsoft prints for this skill, `npx skills add microsoft/skills --skill azure-sdk-dotnet` and `/plugin install azure-sdk-dotnet@skills`, install the whole azure-sdk-dotnet plugin rather than the authentication events skill alone.

 Source reviewed

6 sources · 2026-10-21

[Read the full review ↗](/skills/microsoft-microsoft-azure-webjobs-extensions-authentication-events-dotnet/) Upstream setup linked MIT
 Compare Microsoft Entra Authentication Events SDK for .NET Add

Research and documentation · Microsoft

### [Microsoft Wiki Researcher](/skills/microsoft-wiki-researcher/)

Traces architecture and data flow through source code to produce an explanation with file references, diagrams and stated uncertainties.

 codebase-research architecture documentation

**Why we selected it**Requires code-reading before architectural claims and traces actual calls and data flow rather than trusting directory names.

**Weigh up**Its git command identifies the current branch, although the prose calls it the default branch; choose the actual revision and host-specific link format yourself.

 Source reviewed

7 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-wiki-researcher/) Install command in review MIT
 Compare Microsoft Wiki Researcher Add

Development workflow · Trail of Bits

### [Modern Python](/skills/trailofbits-modern-python/)

Sets up uv, ruff and ty, and says when not to migrate an existing Python toolchain.

 python uv ruff

**Why we selected it**The definition has an explicit When NOT to Use section, so a migration is not the default.

**Weigh up**CC-BY-SA-4.0 requires share-alike and attribution if you redistribute an adaptation.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-modern-python/) Install command in review CC-BY-SA-4.0
 Compare Modern Python Add

Web development · JetBrains

### [Modern Web Guidance](/skills/jetbrains-modern-web-guidance/)

Routes HTML, CSS and client-side JavaScript work through a searchable corpus of Chrome-authored best-practice guides — container queries, dialogs and popovers, view transitions, scroll-driven animation, forms and autofill, image priority — with Baseline browser-support policy rules for fallbacks.

 css container-queries forms

**Why we selected it**Turns modern-CSS and forms guidance into a queryable corpus instead of a fixed checklist: the agent searches an action-oriented phrase, gets scored matches with token counts, then retrieves only the guide it needs.

**Weigh up**The search workflow shells out to the modern-web-guidance npm package at runtime, so it needs network access and Node; the --skill-version flag only warns when the SKILL.md is stale, it does not pin the package version.

 Source reviewed

6 sources · 2026-10-07

[Read the full review ↗](/skills/jetbrains-modern-web-guidance/) Install command in review Apache-2.0
 Compare Modern Web Guidance Add

Data pipelines · mongodb

### [MongoDB Atlas Stream Processing](/skills/mongodb-atlas-stream-processing/)

Plan and operate Atlas streaming workspaces, connections and processors through MongoDB MCP.

 data-pipelines mongodb

**Why we selected it**The tool matrix separates discovery, creation, lifecycle changes and teardown; processor modification requires a stopped/created state and PrivateLink is project-scoped.

**Weigh up**This requires Atlas API credentials and matching streams tools; workspace teardown cascades. Source retention and billing descriptions must be rechecked for the chosen service version.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/mongodb-atlas-stream-processing/) Install command in review Apache-2.0
 Compare MongoDB Atlas Stream Processing Add

Database engineering · mongodb

### [MongoDB Connection Configuration](/skills/mongodb-connection/)

Review MongoDB client reuse, pool capacity and timeouts against workload and topology.

 database-engineering mongodb

**Why we selected it**The definition requires deployment and workload context before setting pool values and separates monitoring connections from per-server application pools.

**Weigh up**Connection-memory and setup-time examples are estimates; pool formulas do not model every driver/topology. Timeouts and retries need operation-specific semantics.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/mongodb-connection/) Install command in review Apache-2.0
 Compare MongoDB Connection Configuration Add

Agent integration · mongodb

### [MongoDB MCP Configuration](/skills/mongodb-mcp-setup/)

Configure MongoDB MCP access for a direct cluster, Atlas API or local Docker environment.

 agent-integration mongodb

**Why we selected it**The definition separates data-plane connection strings from Atlas administration credentials and explicitly tells the agent not to collect secret values.

**Weigh up**Presence of MDB_MCP_READ_ONLY alone does not prove true or enforced read-only mode. Client detection via environment variables is a heuristic, and broad Atlas owner roles may exceed the intended task.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/mongodb-mcp-setup/) Install command in review Apache-2.0
 Compare MongoDB MCP Configuration Add

Database engineering · mongodb

### [MongoDB Natural Language Queries](/skills/mongodb-natural-language-querying/)

Translate questions into MongoDB read queries using inspected schema, indexes and bounded samples.

 database-engineering mongodb

**Why we selected it**The workflow prefers find for simple retrieval, reserves aggregation for transformations/grouping, and explicitly excludes write pipelines and Atlas Search.

**Weigh up**Samples may contain sensitive data. The suggestion to replace field existence with not-equal-null changes semantics for fields that exist with null values; validate missing/null cases explicitly.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/mongodb-natural-language-querying/) Install command in review Apache-2.0
 Compare MongoDB Natural Language Queries Add

Databases · MongoDB

### [MongoDB query optimizer](/skills/mongodb-query-optimizer/)

Official MongoDB skill that limits itself to slow-query and index work and names the MCP tools it expects for explain, indexes, and Atlas Performance Advisor.

 mongodb indexes explain

**Why we selected it**The catalogue's MongoDB performance advisor is a GitHub Copilot agent, not this official skill.

**Weigh up**This review did not execute the skill or call MongoDB MCP tools.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/mongodb-query-optimizer/) Install command in review Apache-2.0
 Compare MongoDB query optimizer Add

Databases · MongoDB

### [MongoDB schema design](/skills/mongodb-schema-design/)

Pins MongoDB's schema-design skill, which separates read checks from writes and says write tools need an explicit yes.

 mongodb schema modeling

**Why we selected it**The catalogue has MongoDB's query-optimizer skill and not this schema-design skill.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/mongodb-schema-design/) Install command in review Apache-2.0
 Compare MongoDB schema design Add

Databases · MongoDB

### [MongoDB Search and AI](/skills/mongodb-mongodb-search-and-ai/)

Chooses between Atlas Search, Vector Search, Automated Embedding and hybrid search, and creates indexes only after explicit approval.

 mongodb vector-search hybrid-search

**Why we selected it**Index creation follows a fixed sequence: explain the configuration, show the JSON, ask for a name and get explicit approval before calling create-index.

**Weigh up**The file says never to recommend $regex or $text for search use cases, which steers toward Atlas Search features whose prerequisites sit in the reference files.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/skills/mongodb-mongodb-search-and-ai/) Install command in review Apache-2.0
 Compare MongoDB Search and AI Add

Telemetry export · Microsoft

### [Monitor OpenTelemetry exporter](/skills/microsoft-azure-monitor-opentelemetry-exporter-py/)

Pins Microsoft's Application Insights exporter skill, which uses Entra credentials for ingestion and requires an explicit telemetry shutdown.

 application-insights azure entra

**Why we selected it**The file says the connection string only identifies the Application Insights resource and that DefaultAzureCredential provides Entra authentication, and it says to use Entra instead of instrumentation keys.

**Weigh up**The resource was not executed.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-azure-monitor-opentelemetry-exporter-py/) Install command in review MIT
 Compare Monitor OpenTelemetry exporter Add

Databases · MotherDuck

### [MotherDuck Migration and Validation](/skills/motherduck-migrate-to-motherduck/)

Plans a staged warehouse migration with SQL translation, source-to-target reconciliation, a first cutover slice and a rollback path.

 migration duckdb data-validation

**Why we selected it**Separates planning with supplied schemas from validation against a connected database.

**Weigh up**The Python example imports repository-level scripts/_lib helpers; installing only the skill directory does not provide its full executable dependency tree.

 Source reviewed

9 sources · 2026-10-15

[Read the full review ↗](/skills/motherduck-migrate-to-motherduck/) Install command in review MIT
 Compare MotherDuck Migration and Validation Add

Security · MotherDuck

### [MotherDuck Security and Governance](/skills/motherduck-security-governance/)

Reviews where credentials live, which boundary isolates tenants, and how roles, share grants and published tables combine.

 database-access tenant-isolation service-accounts

**Why we selected it**Separates platform roles, share recipients and table/view exposure instead of treating all permissions as one control.

**Weigh up**This is an architectural review guide, not a compliance certification or a live permission audit.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/motherduck-security-governance/) Install command in review MIT
 Compare MotherDuck Security and Governance Add

Development workflow · GitHub community (awesome-copilot)

### [Multi-file Refactor Planning](/skills/github-refactor-plan/)

Plan a sequenced refactor with repository-specific dependencies, checks and recovery steps.

 development-workflow github

**Why we selected it**The workflow orders contracts/types before implementations and callers and requires rollback or recovery for the riskiest phases.

**Weigh up**The definition normally stops for plan review; existing explicit authorization to continue can override that checkpoint. A plan does not establish behavior preservation.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/github-refactor-plan/) Install command in review MIT
 Compare Multi-file Refactor Planning Add

Containers · GitHub community (awesome-copilot)

### [Multi-stage Dockerfile Design](/skills/github-multi-stage-dockerfile/)

Separate build dependencies from the runtime image and constrain the build context.

 containers github

**Why we selected it**The source separates dependency/build/test/runtime concerns and recommends copying only necessary outputs, ordering cache layers and removing build tools from the final image.

**Weigh up**Version tags are mutable and do not guarantee reproducibility; pin digests where required. Multi-stage structure alone does not keep secrets out of build cache or logs, and Alpine compatibility must be checked.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/github-multi-stage-dockerfile/) Install command in review MIT
 Compare Multi-stage Dockerfile Design Add

AI application development · Neon

### [Neon AI Gateway](/skills/neon-neon-ai-gateway/)

Adds multi-provider LLM calling through Neon's branch-scoped gateway with one credential, resolving model IDs against the live catalog instead of hardcoded lists.

 llm-gateway model-routing openai-compatible

**Why we selected it**Integrates with OpenAI, Anthropic, google-genai, Vercel AI SDK, and Mastra by changing only the base URL, with separate recommended and lower-level paths.

**Weigh up**Gateway availability and the served catalog are plan-gated; the skill's own Availability section says to check gating first.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/neon-neon-ai-gateway/) Install command in review Apache-2.0
 Compare Neon AI Gateway Add

Cloud development · Cloudflare

### [Next.js on Cloudflare](/skills/cloudflare-nextjs-on-cloudflare/)

Builds, migrates and deploys Next.js apps on Cloudflare Workers with vinext, holding the vinext-over-OpenNext default for new projects while preserving existing OpenNext setups and delegating setup to vinext's upstream skills.

 nextjs cloudflare-workers vinext

**Why we selected it**Takes a position with a preservation rule: vinext is the default for new Next.js projects on Workers, existing OpenNext setups are preserved during unrelated maintenance, and an explicit user choice always wins.

**Weigh up**A routing skill: the concrete setup and migration steps live in cloudflare/vinext's own skills, which must be installed separately for the full workflow.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/cloudflare-nextjs-on-cloudflare/) Install command in review Apache-2.0
 Compare Next.js on Cloudflare Add

Package manager auditing · Grafana

### [npm supply-chain audit](/skills/grafana-check-npm/)

Pins Grafana's package-manager audit, which is read-only, stops when package.json is missing, and stops again when every check passes.

 grafana npm pnpm

**Why we selected it**No selected skills record uses this source path.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-check-npm/) Install command in review Apache-2.0
 Compare npm supply-chain audit Add

Observability · Addy Osmani

### [Observability and instrumentation](/skills/addyosmani-observability-and-instrumentation/)

Requires a definition of working before adding a log line, and a check that the telemetry itself is real.

 logging metrics tracing

**Why we selected it**Telemetry starts from the questions an on-call engineer will ask, not from adding logs.

**Weigh up**Metrics labels must come from small fixed sets; user IDs and other unbounded values are forbidden.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/addyosmani-observability-and-instrumentation/) Install command in review MIT
 Compare Observability and instrumentation Add

Cloud operations · JetBrains

### [Observability Integrator](/skills/jetbrains-observability-integrator/)

Designs instrumentation that answers operational questions instead of filling dashboards: metrics tied to user journeys with a cardinality budget, structured logs with stable correlation identifiers and PII redaction by policy, trace propagation across async and coroutine boundaries, deliberate sampling, and liveness/readiness/startup health semantics.

 observability metrics structured-logging

**Why we selected it**Starts from the operational questions the instrumentation must answer — is the service healthy, which journey is slow, which dependency is failing, where is saturation growing — and explicitly rejects vanity dashboards.

**Weigh up**The worked context is Kotlin plus Spring (actuator exposure, coroutine propagation); the rules transfer, the framework specifics do not.

 Source reviewed

6 sources · 2026-10-13

[Read the full review ↗](/skills/jetbrains-observability-integrator/) Install command in review MIT (upstream Kotlin backend agent skills)
 Compare Observability Integrator Add

Release preparation · trailofbits

### [Open-source Release Preparation](/skills/trailofbits-open-sourcing/)

Prepare repository content, build instructions and packaging for a deliberate public release.

 release-preparation trailofbits

**Why we selected it**check_readiness.sh flags tracked filenames and presence indicators without scanning their contents; detect_org.sh checks remotes and recent author/committer email domains.

**Weigh up**The readiness script checks file/name presence rather than contents or security. Organization detection from remotes/commit emails is heuristic; licence selection and fresh-repository recommendations need the actual ownership and disclosure context.

 Source reviewed

6 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-open-sourcing/) Install command in review CC-BY-SA-4.0
 Compare Open-source Release Preparation Add

AI application development · OpenAI

### [OpenAI Agents SDK Workflow](/skills/openai-agents-sdk/)

Builds a small Agents SDK application around an explicit workflow contract, then checks the real agent path and optional local deployment.

 openai agents-sdk tools

**Why we selected it**Starts with a single agent and adds tools, delegation or sandboxing only when the application needs them.

**Weigh up**A companion credential gate can pause work before implementation even when a key already exists.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/openai-agents-sdk/) Upstream setup linked Proprietary (declared in plugin manifest)
 Compare OpenAI Agents SDK Workflow Add

AI application development · OpenAI

### [OpenAI API Troubleshooting](/skills/openai-openai-api-troubleshooting/)

Classifies a failed OpenAI request using its actual transport or API error and routes credentials, billing, throttling and access issues separately.

 openai api errors

**Why we selected it**Distinguishes exhausted quota from ordinary rate limiting even when the HTTP status is the same.

**Weigh up**It relies on companion documentation and credential skills; it does not provision or rotate keys itself.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/openai-openai-api-troubleshooting/) Upstream setup linked Proprietary (declared in plugin manifest)
 Compare OpenAI API Troubleshooting Add

Security · OpenAI

### [OpenAI Codex Security Threat Model](/skills/openai-threat-model/)

Creates or reuses a repository threat model bound to the actual target and revision, preserving supplied context and explicit review gaps.

 threat-modeling codex-security trust-boundaries

**Why we selected it**Binds reusable models to repository/version identity and avoids mixing scan-specific context into a shared cache.

**Weigh up**This is one phase in the Codex Security plugin, not a standalone full security scan.

 Source reviewed

8 sources · 2026-10-15

[Read the full review ↗](/skills/openai-threat-model/) Upstream setup linked Proprietary (declared in plugin manifest)
 Compare OpenAI Codex Security Threat Model Add

Data and research · OpenAI

### [OpenAI Data Analytics Notebooks](/skills/openai-jupyter-notebooks/)

Turns SQL or Python analysis into a traceable notebook whose conclusions are tied to executed outputs and stated assumptions.

 jupyter sql python

**Why we selected it**Records query links, input versions, filters and cohort definitions next to the analysis.

**Weigh up**Warehouse and operational-log placeholders depend on the host’s configured connectors; exports or supplied data are fallback paths.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/openai-jupyter-notebooks/) Upstream setup linked Proprietary (declared in plugin manifest)
 Compare OpenAI Data Analytics Notebooks Add

Agent development · OpenAI

### [OpenAI Evaluate Skill](/skills/openai-evaluate-skill/)

Connects a local skill review to structural checks, budget explanations and an explicitly separate live benchmark workflow.

 skills evaluation token-usage

**Why we selected it**Distinguishes static instruction-size estimates from observed usage collected by real agent runs.

**Weigh up**Static scores and budget bands are tool heuristics, not proof of task quality or safety.

 Source reviewed

8 sources · 2026-10-15

[Read the full review ↗](/skills/openai-evaluate-skill/) Upstream setup linked MIT (declared in plugin manifest)
 Compare OpenAI Evaluate Skill Add

Observability · grafana

### [OpenTelemetry with Grafana](/skills/grafana-opentelemetry/)

Connect application telemetry through direct OTLP export or an Alloy/Collector pipeline.

 observability grafana

**Why we selected it**It wires OpenTelemetry export to Grafana Cloud or a local Alloy collector and checks auth with an empty OTLP POST.

**Weigh up**The empty-body probe is not a valid trace; it only distinguishes auth from a bad path.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-opentelemetry/) Install command in review Apache-2.0
 Compare OpenTelemetry with Grafana Add

Testing · trailofbits

### [OSS-Fuzz Integration](/skills/trailofbits-ossfuzz/)

Prepare an open-source project for continuous fuzzing and reproduce its harnesses locally.

 testing trailofbits

**Why we selected it**The skill separates a local helper.py run from public enrollment, which it describes as selective.

**Weigh up**The documented local path clones OSS-Fuzz and runs Docker via helper.py. This file does not contain those images and does not submit the enrollment pull request.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-ossfuzz/) Install command in review CC-BY-SA-4.0
 Compare OSS-Fuzz Integration Add

Infrastructure · hashicorp

### [Packer Azure Image Builder](/skills/hashicorp-azure-image-builder/)

Prepare Azure managed or Compute Gallery images with Packer.

 infrastructure hashicorp

**Why we selected it**The source distinguishes managed images from gallery destinations and warns that gallery image versions cannot be overwritten.

**Weigh up**The Managed Identity example actually enables Azure CLI authentication; it is not evidence of managed-identity configuration. Example subscription-wide Contributor scope is broader than a dedicated build resource group.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/hashicorp-azure-image-builder/) Install command in review MPL-2.0
 Compare Packer Azure Image Builder Add

Image building · HashiCorp

### [Packer Windows builder](/skills/hashicorp-windows-builder/)

Pins HashiCorp's Packer Windows builder, which provisions over WinRM, deletes guest temp files during cleanup, and says a failed build may leave resources running.

 packer windows winrm

**Why we selected it**The file says a failed build may leave resources running and that cleanup has to be verified. Its cleanup provisioner deletes guest temp files and the Windows Update cache, and it stops and starts wuauserv.

**Weigh up**The in-guest cleanup provisioner does not remove cloud resources. The file's own note says a failed build may leave resources running and that this must be checked separately.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/hashicorp-windows-builder/) Install command in review MPL-2.0
 Compare Packer Windows builder Add

Web performance · Addy Osmani

### [Performance optimization](/skills/addyosmani-performance-optimization/)

Starts from a measurement workflow and names Core Web Vitals targets instead of guessing a speedup.

 performance web-vitals queries

**Why we selected it**Its five steps (measure, identify, fix, verify, guard) keep a change only when the re-measurement beats run-to-run variance with tests still green.

**Weigh up**Its See Also section points to ../../references/performance-checklist.md. The README says a per-skill npx install does not copy that repository-level directory.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/addyosmani-performance-optimization/) Install command in review MIT
 Compare Performance optimization Add

Databases · Pinecone

### [Pinecone quickstart](/skills/pinecone-quickstart/)

Pinecone's onboarding skill: either a semantic-search demo on a new integrated index through the Pinecone MCP and a bundled upsert script, or a Pinecone Assistant built from the user's own documents.

 vector-db embeddings reranking

**Why we selected it**Path A is a fixed, checkable loop: list-indexes to test the key, create-index-for-model for a serverless index quickstart-skills (aws, us-east-1, llama-text-embed-v2, text mapped to chunk_text), a bundled upsert of nine records with pinecone==9.1.0, search-records queries that share no keywords with the records, and optional bge-reranker-v2-m3 reranking.

**Weigh up**The skill directory skills/pinecone-quickstart last changed in a commit dated 2026-08-10 (git log at the pin); the pinned revision 885dc539 is dated 2026-09-18.

 Source reviewed

9 sources · 2026-10-21

[Read the full review ↗](/skills/pinecone-quickstart/) Upstream setup linked MIT
 Compare Pinecone quickstart Add

Framework development · JetBrains

### [Pinia](/skills/jetbrains-pinia/)

Reference-index over Pinia store design: defining stores, state, getters and actions, storeToRefs destructuring, plugins, composing stores without circular dependencies, SSR hydration, HMR and testing with @pinia/testing.

 pinia vue state-management

**Why we selected it**Splits the parts of Pinia that agents get wrong into nine reference files — storeToRefs reactivity, composing stores without circular dependencies, using stores outside components, SSR hydration — rather than compressing them into prose.

**Weigh up**The mirror carries the January 2026 generation, based on Pinia v3.0.4; the upstream antfu/skills generator has since produced a Pinia v4.0.3 revision (2026-09-25) that the pinned mirror does not include.

 Source reviewed

6 sources · 2026-10-07

[Read the full review ↗](/skills/jetbrains-pinia/) Install command in review MIT (upstream antfu/skills)
 Compare Pinia Add

Database review · PlanetScale

### [PlanetScale Postgres safety review](/skills/planetscale-planetscale-postgres-safety-review/)

Reviews a PlanetScale Postgres database and recommends roles, pg_strict, backups, and Traffic Control without applying them.

 postgres planetscale review

**Why we selected it**The skill reviews PlanetScale Postgres for roles, pg_strict, backups, traffic control, and network posture, and it says not to apply changes.

**Weigh up**The file does not apply schema, role, backup, or network changes.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/planetscale-planetscale-postgres-safety-review/) Install command in review MIT
 Compare PlanetScale Postgres safety review Add

Database review · PlanetScale

### [PlanetScale Vitess safety review](/skills/planetscale-vitess-safety-review/)

Review a PlanetScale Vitess database and recommend safety posture. The skill's own first instruction is not to apply changes.

 planetscale vitess schema

**Why we selected it**The file is a review that recommends posture and says not to apply changes.

**Weigh up**The purpose section says not to apply any changes.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/planetscale-vitess-safety-review/) Install command in review MIT
 Compare PlanetScale Vitess safety review Add

Agent development · Anthropic

### [Plugin Settings Pattern for Claude Code Plugins](/skills/anthropic-plugin-settings/)

Documents one pattern for per-project Claude Code plugin settings, a .claude/<plugin-name>.local.md file with YAML frontmatter and a Markdown body, and how hooks, commands and agents read it.

 claude-code plugin-dev configuration

**Why we selected it**It documents a single, concrete convention: settings and state in .claude/<plugin-name>.local.md in the project root, YAML frontmatter plus a Markdown body, kept out of git through a .claude/*.local.md line in .gitignore.

**Weigh up**Last commit touching plugins/plugin-dev/skills/plugin-settings at revision 41f32e40: 2026-02-05 (2438937b).

 Source reviewed

7 sources · 2026-10-21

[Read the full review ↗](/skills/anthropic-plugin-settings/) Upstream setup linked Apache-2.0
 Compare Plugin Settings Pattern for Claude Code Plugins Add

Agent development · Anthropic

### [Plugin Structure for Claude Code](/skills/anthropic-plugin-structure/)

Describes the Claude Code plugin layout: the .claude-plugin/plugin.json manifest, root-level commands, agents, skills and hooks directories, .mcp.json, auto-discovery and ${CLAUDE_PLUGIN_ROOT} paths.

 claude-code plugin-dev manifest

**Why we selected it**It states the layout rules a plugin loader relies on: the manifest lives at .claude-plugin/plugin.json, only its name field is required, and the commands, agents, skills and hooks directories sit at the plugin root, not inside .claude-plugin/.

**Weigh up**Last commit touching plugins/plugin-dev/skills/plugin-structure at revision 41f32e40: 2026-02-05 (2438937b).

 Source reviewed

7 sources · 2026-10-21

[Read the full review ↗](/skills/anthropic-plugin-structure/) Upstream setup linked Apache-2.0
 Compare Plugin Structure for Claude Code Add

Dependency reduction · Grafana

### [pnpm dependency reduction](/skills/grafana-audit-and-reduce-dependencies/)

Pins Grafana's pnpm reduction skill, which runs a read-only check first, stops off pnpm, and requires approval before adding a dependency.

 grafana pnpm dependencies

**Why we selected it**No selected skills record uses this source path.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-audit-and-reduce-dependencies/) Install command in review Apache-2.0
 Compare pnpm dependency reduction Add

Model development · Hugging Face

### [Portable Triton Kernels](/skills/huggingface-triton-kernels/)

Writes and benchmarks portable Triton kernels for NVIDIA and AMD GPUs: block-size discipline, autotune configuration, fp16/bf16/fp8 numerics, masked loads, reductions, correctness tests against a PyTorch reference and publishing to the Kernels Hub.

 triton gpu kernels

**Why we selected it**Its hard constraints encode the silent-failure traps: never autotune BLOCK_SIZE when it controls the reduction axis because partial rows give wrong results silently, and masked loads need a safe other value.

**Weigh up**Triton-specific: WebGPU/WGSL and raw CUDA C++ are out of scope, and the portability claim is NVIDIA plus AMD only.

 Source reviewed

5 sources · 2026-10-07

[Read the full review ↗](/skills/huggingface-triton-kernels/) Install command in review Apache-2.0
 Compare Portable Triton Kernels Add

Security review · Trail of Bits

### [Post-patch validation](/skills/trailofbits-post-patch-validation/)

Requires a baseline-versus-patched evidence contract before a security fix is called done.

 patches verification security

**Why we selected it**The description says to use it after a patch exists and before accepting it as fixed.

**Weigh up**CC-BY-SA-4.0 applies to adaptations you redistribute.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-post-patch-validation/) Install command in review CC-BY-SA-4.0
 Compare Post-patch validation Add

Databases · Timescale

### [Postgres](/skills/timescale-postgres/)

Timescale's postgres skill from pg-aiguide: a dispatcher that sends the agent to nine reference guides for schema exploration, table design, pgvector and hybrid search, TimescaleDB hypertables and schema migrations.

 postgresql sql schema

**Why we selected it**Timescale publishes it in timescale/pg-aiguide (frontmatter license Apache-2.0, author tigerdata; NOTICE reads "Copyright 2025 Timescale, Inc., d/b/a Tiger Data"), and the README prints a single-skill install line for it: `npx skills add timescale/pg-aiguide --skill postgres`.

**Weigh up**The skills/postgres directory last changed in a commit dated 2026-09-25; the pinned revision 187be00d is dated 2026-10-07.

 Source reviewed

13 sources · 2026-10-21

[Read the full review ↗](/skills/timescale-postgres/) Install command in review Apache-2.0
 Compare Postgres Add

Pull request repair · Trail of Bits

### [PR improver](/skills/trailofbits-pr-improver/)

Pins the branch loop that refuses the base branch, stops on an empty diff, will not replace a missing reviewer, and does not commit.

 pull-request review workflow

**Why we selected it**The skill refuses to run when the current branch is the base and stops when the diff is empty.

**Weigh up**The resource was not executed.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-pr-improver/) Install command in review CC-BY-SA-4.0
 Compare PR improver Add

Databases · Prisma

### [Prisma Client API](/skills/prisma-client-api/)

Covers Prisma Client model queries, relation filtering, interactive transactions, and batching semantics.

 prisma orm typescript

**Why we selected it**Details explicit relation filtering semantics (some, every, none) and type-safe pagination patterns (cursor-based vs offset-based) with TypeScript type examples.

**Weigh up**Assumes a generated Prisma Client in node_modules/@prisma/client or a custom output directory; does not execute code generation.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/prisma-client-api/) Install command in review MIT
 Compare Prisma Client API Add

Application deployment · Prisma

### [Prisma Compute](/skills/prisma-prisma-compute/)

Pins Prisma's Compute skill, which checks auth before app mutations and separates a non-promoting build from a production deploy.

 prisma compute deploy

**Why we selected it**A non-empty service token is the auth source, an empty token should fail closed, and a failed workspace must not fall through to another cached session.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/prisma-prisma-compute/) Install command in review MIT
 Compare Prisma Compute Add

Database adapters · Prisma

### [Prisma driver-adapter implementation](/skills/prisma-prisma-driver-adapter-implementation/)

A Prisma ORM 7 driver-adapter contract: one connection per transaction, cleanup hooks that do not issue a second commit, and original database errors kept intact.

 prisma sql transactions

**Why we selected it**It specifies the Prisma 7 SQL adapter contract, including one dedicated connection per transaction and commit hooks that must not send a second COMMIT.

**Weigh up**The skill is a protocol guide; it does not ship a working adapter or run Prisma.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/prisma-prisma-driver-adapter-implementation/) Install command in review MIT
 Compare Prisma driver-adapter implementation Add

Database migrations · Prisma

### [Prisma MongoDB upgrade](/skills/prisma-mongodb-upgrade/)

Pins Prisma's MongoDB upgrade skill, which refuses a Prisma 7 upgrade and refuses an implicit move from MongoDB to SQL.

 prisma mongodb upgrade

**Why we selected it**The catalogue has Prisma's v7 upgrade, client API, CLI, and driver-adapter skills and not this MongoDB decision file.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/prisma-mongodb-upgrade/) Install command in review MIT
 Compare Prisma MongoDB upgrade Add

Databases · Prisma

### [Prisma ORM 7 CLI](/skills/prisma-cli/)

Pins Prisma's ORM 7 CLI skill and its warning not to use these commands for Prisma 8 or for the public-beta Platform CLI.

 prisma database migrations

**Why we selected it**The catalogue has Prisma ORM setup and client-API skills and not this ORM 7 CLI reference.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/prisma-cli/) Install command in review MIT
 Compare Prisma ORM 7 CLI Add

Databases · Prisma

### [Prisma ORM Setup](/skills/prisma-orm-setup/)

Guides configuring Prisma ORM across PostgreSQL, MySQL, SQLite, SQL Server, CockroachDB, MongoDB, and Prisma Postgres.

 prisma orm database-setup

**Why we selected it**Configures provider-specific datasource blocks and connection string arguments across 7 distinct database engines without conflating parameters.

**Weigh up**Directs new projects towards Prisma ORM 8 forward-compatibility while maintaining v6/v7 fallbacks; does not execute database scaffolding.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/prisma-orm-setup/) Install command in review MIT
 Compare Prisma ORM Setup Add

Database migrations · Prisma

### [Prisma ORM v7 upgrade](/skills/prisma-prisma-upgrade-v7/)

Numbered Prisma ORM v6 to v7 migration that requires SQL driver adapters and stops the path for MongoDB.

 prisma orm typescript

**Why we selected it**The file is a numbered upgrade: prisma-client generator, prisma.config.ts, required SQL driver adapters, and a client import from the generated path.

**Weigh up**The file states Latest stable Prisma ORM version: 7.6.0 and requires Node.js 20.19.0+ and TypeScript 5.4.0+. This review did not query the npm registry.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/prisma-prisma-upgrade-v7/) Install command in review MIT
 Compare Prisma ORM v7 upgrade Add

Database setup · Prisma

### [Prisma Postgres setup](/skills/prisma-prisma-postgres-setup/)

Pins Prisma's Postgres setup skill, which will not delete another resource to get past a quota block and keeps the connection out of source and chat.

 prisma postgres provisioning

**Why we selected it**If provisioning is blocked by permissions or quota, the file says to report the blocker and not to delete another resource or switch workspaces.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/prisma-prisma-postgres-setup/) Install command in review MIT
 Compare Prisma Postgres setup Add

Cloud operations · JetBrains

### [Production Incident Responder](/skills/jetbrains-production-incident-responder/)

Runs production incident response as mitigate-first: state impact, pick the fastest reversible mitigation, preserve evidence while the symptom still exists, then diagnose — with heuristics for retry storms, cache stampedes and config-only regressions.

 incident-response hotfix rollback

**Why we selected it**Orders the response deliberately — reversible mitigation before root-cause work — and names the anti-patterns: reflexive restarts that destroy evidence and amplify connection storms, scaling the app tier when the database is the bottleneck.

**Weigh up**Framed for Kotlin plus Spring services; the response sequence is stack-generic but dashboard and tooling references assume JVM-ecosystem observability.

 Source reviewed

6 sources · 2026-10-13

[Read the full review ↗](/skills/jetbrains-production-incident-responder/) Install command in review MIT (upstream Kotlin backend agent skills)
 Compare Production Incident Responder Add

Observability · grafana

### [Profilecli Source Insights](/skills/grafana-profilecli-insights/)

Retrieve Pyroscope profiles and map hot functions to the corresponding source checkout.

 observability grafana

**Why we selected it**It queries an existing Pyroscope server with profilecli and maps hot functions back to this checkout only when the module path matches.

**Weigh up**The skill does not start profiling; it reads profiles that already exist.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-profilecli-insights/) Install command in review Apache-2.0
 Compare Profilecli Source Insights Add

Security review · Trail of Bits

### [Project Wycheproof](/skills/trailofbits-wycheproof/)

Loads Project Wycheproof vectors and maps valid, invalid, and acceptable results onto pass, fail, and warning, instead of treating a custom algorithm as in scope.

 cryptography test-vectors wycheproof

**Why we selected it**The result field has three values: valid should succeed, invalid should fail, and acceptable may succeed but is called non-ideal.

**Weigh up**The skill says to use other tools for timing measurement, fuzzing for new bugs, and not to expect vectors for experimental algorithms.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-wycheproof/) Install command in review CC-BY-SA-4.0
 Compare Project Wycheproof Add

Observability · Grafana Labs

### [Prometheus label strategy](/skills/grafana-prometheus-label-strategy/)

Designs labels before a cardinality incident, and forbids dropping a label that makes a series unique.

 prometheus labels cardinality

**Why we selected it**The first heading is the one rule: never drop a label that makes a series unique.

**Weigh up**A label audit is not a Grafana Cloud bill.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-prometheus-label-strategy/) Install command in review Apache-2.0
 Compare Prometheus label strategy Add

Model evaluation · Promptfoo

### [Promptfoo evals](/skills/promptfoo-promptfoo-evals/)

Official Promptfoo skill that writes, runs and refines declarative eval suites with deterministic assertions first and a CI gate.

 evaluations eval ci

**Why we selected it**Defines a non-redteam eval workflow with deterministic assertions before model-graded rubrics, inlined source evidence, calibrated known-good and known-bad controls, and an exit-code CI gate.

**Weigh up**Last commit 2026-10-15, the same day as the review; the bundle ships four skills and this candidate is the eval-authoring one only.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/promptfoo-promptfoo-evals/) Upstream setup linked MIT
 Compare Promptfoo evals Add

Metrics · Grafana Labs

### [PromQL query patterns](/skills/grafana-promql/)

PromQL skill that puts rate before aggregation, keeps the le label inside histogram_quantile, and guards a zero denominator.

 promql prometheus grafana

**Why we selected it**The primary file shows rate before sum, histogram_quantile with by (le, service), a comparison that drops zero denominators, and a recording-rule replacement checked against the Prometheus query API.

**Weigh up**The curl examples default to http://localhost:9090 and say to add basic auth for Grafana Cloud. No query was sent. The 0.999 figure is a placeholder in the file, not a measured SLO.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-promql/) Install command in review Apache-2.0
 Compare PromQL query patterns Add

API design · GitHub community

### [Protobuf gRPC API Review](/skills/github-protobuf-grpc-api-review/)

Reviews .proto and gRPC changes as long-lived contracts across binary wire, JSON and text formats, generated APIs and runtime behavior, with mixed-version rollout tracing and a four-rung verdict.

 protobuf grpc api-compatibility

**Why we selected it**Compatibility is evaluated on four independent dimensions (binary wire, named formats, generated source API, behavior and operations) instead of a single wire-compatibility verdict.

**Weigh up**Verdicts are only as good as the declared compatibility envelope; the skill itself requires lowering confidence when encodings, consumers or deployment order are unknown.

 Source reviewed

7 sources · 2026-10-15

[Read the full review ↗](/skills/github-protobuf-grpc-api-review/) Install command in review MIT
 Compare Protobuf gRPC API Review Add

Infrastructure development · HashiCorp

### [Provider actions](/skills/hashicorp-provider-actions/)

Guides Terraform Plugin Framework action registration, configuration and lifecycle-trigger integration.

 terraform actions provider

**Why we selected it**The first action in a provider requires ActionData to be set in Configure next to the existing resource data.

**Weigh up**Actions do not produce state that resource.TestCheckResourceAttr can read; the skill says to use a PostApplyFunc against the API.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/hashicorp-provider-actions/) Install command in review MPL-2.0
 Compare Provider actions Add

Infrastructure development · HashiCorp

### [Provider configuration](/skills/hashicorp-provider-configuration/)

Builds a provider Configure method as a credential chain and names every source a failed login tried.

 terraform authentication provider

**Why we selected it**The inspected headings include a credential provider chain and diagnostics that name every source tried.

**Weigh up**MPL-2.0 is file-level copyleft for a modified redistribution of this file.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/hashicorp-provider-configuration/) Install command in review MPL-2.0
 Compare Provider configuration Add

Infrastructure development · HashiCorp

### [Provider framework migration](/skills/hashicorp-provider-framework-migration/)

Starts by asking whether to migrate at all, then muxes the provider and verifies before claiming the port is done.

 terraform migration provider

**Why we selected it**The first heading is Decide Whether to Migrate at All.

**Weigh up**MPL-2.0 applies to modified redistributions of this file.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/hashicorp-provider-framework-migration/) Install command in review MPL-2.0
 Compare Provider framework migration Add

Testing · HashiCorp

### [Provider test patterns](/skills/hashicorp-provider-test-patterns/)

Writes Plugin Framework acceptance tests, including state checks and import verification.

 terraform acceptance-tests provider

**Why we selected it**The description names TestCase, TestStep, ConfigStateChecks and import testing.

**Weigh up**MPL-2.0 applies to a modified redistribution of this file.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/hashicorp-provider-test-patterns/) Install command in review MPL-2.0
 Compare Provider test patterns Add

Infrastructure development · HashiCorp

### [Push to HCP Packer registry](/skills/hashicorp-push-to-registry/)

Pins HashiCorp's Packer skill for pushing build metadata to an HCP Packer bucket, including the environment variables the build expects.

 packer hcp registry

**Why we selected it**The catalogue has HashiCorp's aws-ami-builder Packer skill and not this HCP Packer registry skill.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/hashicorp-push-to-registry/) Install command in review MPL-2.0
 Compare Push to HCP Packer registry Add

App Service deployment · Microsoft

### [Python App Service deploy](/skills/microsoft-python-appservice-deploy/)

Pins Microsoft's Python App Service deploy skill, which forbids health probes after deploy and forbids az webapp up.

 azure app-service python

**Why we selected it**After deploy returns, the skill forbids log tail, curl, Invoke-WebRequest, and any other health probe, then says to stop the turn.

**Weigh up**This review did not execute the resource.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-python-appservice-deploy/) Install command in review MIT
 Compare Python App Service deploy Add

Databases · Qdrant

### [Qdrant clients SDK](/skills/qdrant-clients-sdk/)

Qdrant skill that lists the official client SDKs with their repositories and installation lines, points to the REST and gRPC API references, and fetches code examples from a remote snippet search.

 qdrant vector-search grpc

**Why we selected it**SKILL.md names six officially supported client SDKs, links each to its qdrant GitHub repository, and prints an installation line for five of them: pip install qdrant-client[fastembed], npm install @qdrant/js-client-rest, cargo add qdrant-client, go get github.com/qdrant/go-client and dotnet add package Qdrant.Client.

**Weigh up**skills/qdrant-clients-sdk last changed in a commit dated 2026-06-05; the pinned revision is dated 2026-10-21. The README disclaimer says the skills are under active development and that content and structure may change between versions.

 Source reviewed

4 sources · 2026-10-21

[Read the full review ↗](/skills/qdrant-clients-sdk/) Upstream setup linked Apache-2.0
 Compare Qdrant clients SDK Add

Data and analytics · dbt Labs

### [Querying the dbt information schema](/skills/dbt-labs-querying-the-dbt-information-schema/)

Answers from the project metadata, with two routes, instead of guessing the DAG.

 dbt metadata lineage

**Why we selected it**The description limits the skill to a dbt v2 project's own metadata.

**Weigh up**A metadata query is not a production build.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/dbt-labs-querying-the-dbt-information-schema/) Install command in review Apache-2.0
 Compare Querying the dbt information schema Add

Documents · Trail of Bits

### [React-PDF](/skills/trailofbits-react-pdf/)

Generates PDF documents with @react-pdf/renderer in TypeScript and JSX — flexbox layout, inline SVG, registered local fonts, Knuth-Plass typesetting — with a when-not-to-use map and crash-avoidance rules for fonts and async rendering.

 pdf pdf-generation react

**Why we selected it**States when NOT to use it — reading PDFs, filling forms, HTML conversion — routing each to pdfplumber, pypdf/pdftk or WeasyPrint instead of stretching one tool across every PDF task.

**Weigh up**Node-only: @react-pdf/renderer renders server-side or in scripts; this is not a browser-PDF skill.

 Source reviewed

6 sources · 2026-10-07

[Read the full review ↗](/skills/trailofbits-react-pdf/) Install command in review MIT
 Compare React-PDF Add

Observability · Anthropic

### [Receipts](/skills/anthropic-receipts/)

Builds a personal Claude Code impact report from this machine's session transcripts and local git history: what shipped, in which projects, and each project's share of usage, as a Markdown report and an HTML receipt in the home directory.

 claude-code receipts git-history

**Why we selected it**Mining is a local Node script, scripts/mine-transcripts.mjs, that reads ~/.claude/projects/**/*.jsonl and runs read-only git commands; the README says the only data that reaches the model is the git user name, aggregate counts and project names.

**Weigh up**Last commit touching plugins/receipts/skills/receipts at revision 41f32e40: 2026-10-08 (0baf7d19).

 Source reviewed

4 sources · 2026-10-21

[Read the full review ↗](/skills/anthropic-receipts/) Install command in review Apache-2.0
 Compare Receipts Add

Database engineering · redis

### [Redis Cluster Key and Read Design](/skills/redis-redis-clustering/)

Plan hash-tag placement and replica reads for sharded Redis workloads.

 database-engineering redis

**Why we selected it**Hash-tag and replica references make key co-location and eventual consistency explicit; entity-level tags prevent unrelated tenant identifiers from sharing a slot.

**Weigh up**The blanket statement that all pipelines require one slot is overbroad: behavior depends on cluster-aware client routing and transaction mode. Shared tags can create hot slots; replica reads can be stale.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/redis-redis-clustering/) Install command in review MIT
 Compare Redis Cluster Key and Read Design Add

Database engineering · redis

### [Redis Connection Engineering](/skills/redis-redis-connections/)

Review Redis pooling, batching, incremental scans and client timeout choices.

 database-engineering redis

**Why we selected it**The definition separates intentional blocking queue operations from server-blocking full scans and distinguishes nontransactional batching from atomic transactions.

**Weigh up**Retry-on-timeout can repeat non-idempotent writes after an ambiguous response. Pool exhaustion, multiplexing and caching support are client-specific; the numeric timeout examples are starting points.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/redis-redis-connections/) Install command in review MIT
 Compare Redis Connection Engineering Add

Database engineering · redis

### [Redis Data Modeling](/skills/redis-redis-core/)

Choose Redis structures and key namespaces from access patterns.

 database-engineering redis

**Why we selected it**The data-type table maps operations to structures and contrasts per-field Hash updates with whole-object string rewrites; key hierarchy is a separate design step.

**Weigh up**Namespace prefixes aid organization but do not enforce tenant isolation. JSON, vector and search capabilities require compatible server editions and versions.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/redis-redis-core/) Install command in review MIT
 Compare Redis Data Modeling Add

Agent memory · redis

### [Redis Iris Agent Memory](/skills/redis-iris-development/)

Integrate session events and searchable long-term memory with Redis Cloud Agent Memory.

 agent-memory redis

**Why we selected it**The definition distinguishes session and long-term tiers; the bulk reference uses caller IDs and partial-success results, while promotion explicitly permits delayed or missing extraction.

**Weigh up**Promotion is asynchronous and a successful event write does not establish a searchable fact. The bulk example slices the first batch only; iterate remaining batches and validate ID characters before use.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/redis-iris-development/) Install command in review MIT
 Compare Redis Iris Agent Memory Add

Observability · redis

### [Redis Observability Review](/skills/redis-redis-observability/)

Select Redis metrics and diagnostic commands for latency, memory and connection incidents.

 observability redis

**Why we selected it**The definition groups memory, connection, throughput and persistence metrics and offers command-level investigation; the separate metrics example lacks the zero-denominator guard used in the main definition.

**Weigh up**Fixed hit-ratio and memory thresholds are examples, not universal alerts; sustained blocked clients may be expected for queues. The metrics reference divides by zero when there are no hits or misses.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/redis-redis-observability/) Install command in review MIT
 Compare Redis Observability Review Add

Search and retrieval · redis

### [Redis Search and Retrieval](/skills/redis-redis-search/)

Design lexical, filtered and vector retrieval with Redis Search indexes.

 search-and-retrieval redis

**Why we selected it**The definition distinguishes filter-then-vector retrieval from lexical/vector score fusion and separates retrieval from aggregation and index-management commands.

**Weigh up**The quoted exact-match speedup and HNSW recall figures are not guarantees. New commands require version checks; index creation does not mean backfill is ready for an alias switch.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/redis-redis-search/) Install command in review MIT
 Compare Redis Search and Retrieval Add

Security · Redis, Inc.

### [Redis security](/skills/redis-security/)

Pins Redis's production-hardening skill for authentication, ACLs, and network binding, and records that any one of those layers is not enough on its own.

 redis acl tls

**Why we selected it**The catalogue has the Redis semantic-cache skill and not this security skill from the same repository.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/redis-security/) Install command in review MIT
 Compare Redis security Add

Caching · Redis, Inc.

### [Redis semantic cache](/skills/redis-semantic-cache/)

Redis skill for LangCache cache-aside search and set on Redis Cloud, with separate caches per task and stated similarity thresholds.

 redis langcache semantic-cache

**Why we selected it**The catalogue has a Redis MCP server and no LangCache skill.

**Weigh up**This review did not execute the skill or call LangCache.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/redis-semantic-cache/) Install command in review MIT
 Compare Redis semantic cache Add

Data pipelines · Redpanda

### [Redpanda streaming](/skills/redpanda-streaming/)

Redpanda reference skill for using the broker through its Kafka-compatible API: rpk topic and record commands, producer and consumer settings, transactions, client compatibility, tiered storage and licensed enterprise topic features.

 redpanda streaming transactions

**Why we selected it**SKILL.md works through the Kafka API with rpk commands (topic list, create, produce, consume, alter-config, delete) and a franz-go Go snippet, plus producer and consumer property tables, the transaction call sequence with isolation.level=read_committed, and tiered storage settings.

**Weigh up**skills/streaming last changed in a commit dated 2026-10-20 (an update to references/SOURCES.md); the pinned revision is dated 2026-10-20.

 Source reviewed

5 sources · 2026-10-21

[Read the full review ↗](/skills/redpanda-streaming/) Upstream setup linked Apache-2.0
 Compare Redpanda streaming Add

Creative production · Remotion

### [Remotion Captions](/skills/remotion-remotion-captions/)

Routes Remotion caption work through one typed Caption contract: transcribing audio with whisper.cpp, displaying TikTok-style paged captions with word highlighting, and importing existing .srt subtitle files.

 captions subtitles srt

**Why we selected it**Defines one typed Caption contract (text, startMs, endMs, timestampMs, confidence, pageBreakAfter) and routes transcription, display and SRT import through it, so caption data cannot drift between pipeline stages.

**Weigh up**Remotion-only: the Caption type and packages are Remotion’s, so this is not a general subtitle toolkit.

 Source reviewed

7 sources · 2026-10-15

[Read the full review ↗](/skills/remotion-remotion-captions/) Install command in review Remotion License (custom, source-available; free for individuals and small companies)
 Compare Remotion Captions Add

Creative production · Remotion

### [Remotion Video Workflows](/skills/remotion-remotion-best-practices/)

Routes video work to focused Remotion guides for creation, preview, rendering, media and reusable video applications.

 video remotion react

**Why we selected it**Keeps new-project scaffolding separate from adding a composition to an existing project.

**Weigh up**This is a router into a larger reference package, so copying the definition alone loses the working guidance.

 Source reviewed

8 sources · 2026-10-15

[Read the full review ↗](/skills/remotion-remotion-best-practices/) Install command in review No redistribution license found
 Compare Remotion Video Workflows Add

Development workflow · Superpowers

### [Requesting Code Review](/skills/obra-requesting-code-review/)

Prepares a requirements-aware review brief around an explicit base and head revision.

 code-review requirements subagents

**Why we selected it**Gives the reviewer concrete requirements, implementation context and a bounded Git comparison.

**Weigh up**A base-to-head comparison excludes uncommitted changes; include those separately when they are in scope.

 Source reviewed

5 sources · 2026-10-14

[Read the full review ↗](/skills/obra-requesting-code-review/) Install command in review MIT
 Compare Requesting Code Review Add

Code review · Trail of Bits

### [Review Walkthrough](/skills/trailofbits-review-walkthrough/)

Turns the committed diff of the current branch into a standalone HTML page of ordered review steps, each with an explanation and severity-tagged findings anchored to diff lines.

 code-review diff-review git-diff

**Why we selected it**Its bundled renderer compares every step with the complete captured patch, so a step whose per-file diff was split, rewritten, omitted or invented is refused rather than shown.

**Weigh up**Runs only on explicit invocation (disable-model-invocation: true): /review-walkthrough:review-walkthrough in Claude Code, $review-walkthrough in Codex.

 Source reviewed

9 sources · 2026-10-22

[Read the full review ↗](/skills/trailofbits-review-walkthrough/) Upstream setup linked CC-BY-SA-4.0
 Compare Review Walkthrough Add

Development workflow · getsentry

### [Reviewer-Facing PR Writing](/skills/getsentry-pr-writer/)

Write or refresh PR titles and bodies from the full branch change and its reviewer impact.

 development-workflow getsentry

**Why we selected it**New pull requests are created as drafts after the whole branch diff is read, not from the latest commit alone.

**Weigh up**Create and update both use authenticated gh, so they publish the title and body. The skill does not merge or request reviewers.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-pr-writer/) Install command in review Apache-2.0
 Compare Reviewer-Facing PR Writing Add

Languages and tooling · GitHub community

### [Ruff Recursive Fix](/skills/github-ruff-recursive-fix/)

Enforces Python code quality with scoped Ruff runs: safe fixes first, unsafe fixes second with diff review each pass, then targeted manual remediation under explicit stop criteria.

 python ruff linting

**Why we selected it**Fix passes are ordered by blast radius: safe autofixes with diff review and formatting first, unsafe fixes only if findings remain, then minimal manual edits.

**Weigh up**Unsafe autofixes can change behavior; the workflow's value depends on actually performing its mandated diff reviews rather than waving them through.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/github-ruff-recursive-fix/) Install command in review MIT
 Compare Ruff Recursive Fix Add

Security review · Trail of Bits

### [Rust review](/skills/trailofbits-rust-review/)

Reviews Rust unsafe, FFI and concurrency, and lists rationalisations the reviewer must reject.

 rust unsafe security

**Why we selected it**The definition has both When to Use and When NOT to Use headings.

**Weigh up**CC-BY-SA-4.0 requires share-alike and attribution for an adaptation you redistribute.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-rust-review/) Install command in review CC-BY-SA-4.0
 Compare Rust review Add

Testing · trailofbits

### [Ruzzy Ruby Fuzzing](/skills/trailofbits-ruzzy/)

Create Ruby and native-extension fuzz harnesses with coverage tracing and sanitizer-aware execution.

 testing trailofbits

**Why we selected it**The handbook is specifically for Ruzzy, and it says pure Ruby needs a second tracer script that C-extension fuzzing does not.

**Weigh up**LD_PRELOAD is required for the sanitizer and must not be exported, because the file says that interferes with other programs.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-ruzzy/) Install command in review CC-BY-SA-4.0
 Compare Ruzzy Ruby Fuzzing Add

Machine learning · huggingface

### [SageMaker Serving Image Selection](/skills/huggingface-sagemaker-serving-image-selection/)

Choose a region-compatible serving container from the AWS catalogue and inspect architecture, runtime and mirroring requirements.

 machine-learning huggingface

**Why we selected it**It picks a SageMaker serving image and prefers a compatible Hugging Face curated family over a newer generic engine tag.

**Weigh up**The skill does not create the SageMaker endpoint.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/huggingface-sagemaker-serving-image-selection/) Install command in review Apache-2.0
 Compare SageMaker Serving Image Selection Add

Testing and reliability · Trail of Bits

### [SARIF Parsing](/skills/trailofbits-sarif-parsing/)

Extracts and summarizes SARIF findings with reusable jq examples and a Python helper.

 sarif static-analysis ci

**Why we selected it**Explains run structure and severity inheritance instead of treating every absent result.level as the same severity.

**Weigh up**The helper is not a complete SARIF validator: invocation-level ruleConfigurationOverrides and extension rule components are not resolved.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-sarif-parsing/) Install command in review CC-BY-SA-4.0
 Compare SARIF Parsing Add

Databases · JetBrains

### [Schema Migration Planner](/skills/jetbrains-schema-migration-planner/)

Plans database schema changes as phased expand, dual-write, backfill, switch-read, contract sequences with explicit lock, replication and rollback-safety analysis, instead of a single DDL statement.

 sql schema-migration expand-contract

**Why we selected it**Encodes expand/contract migration as a planning contract: classify the change as additive, destructive, semantic or data-moving, decide whether old and new application versions must coexist, then phase the rollout and treat cleanup as a separate step behind an explicit proof threshold.

**Weigh up**Framed for Kotlin plus Spring services; the workflow is dialect-generic but the tooling notes lean on Flyway and Liquibase in that ecosystem.

 Source reviewed

6 sources · 2026-10-13

[Read the full review ↗](/skills/jetbrains-schema-migration-planner/) Install command in review MIT (upstream Kotlin backend agent skills)
 Compare Schema Migration Planner Add

Code review · Trail of Bits

### [Second Opinion](/skills/trailofbits-second-opinion/)

Captures one patch (uncommitted work, a branch against a base, or a single commit) and has the Codex, Antigravity or Gemini CLI review it, then reports each reviewer's findings and where two reviews agree or differ.

 code-review diff-review openai

**Why we selected it**When two providers are chosen, both receive the same captured patch, and the skill summarises their agreements and disagreements "without turning agreement into proof".

**Weigh up**Sends the captured diff, the user's focus and applicable project instructions to OpenAI (codex exec) or Google (agy, gemini) through CLIs the user installs and signs in to.

 Source reviewed

8 sources · 2026-10-22

[Read the full review ↗](/skills/trailofbits-second-opinion/) Install command in review CC-BY-SA-4.0
 Compare Second Opinion Add

Security · Sentry

### [Secret Serialization Review](/skills/getsentry-secret-serialization/)

Finds a credential field that survives generated serialization, and the sink that stringifies the whole object.

 secrets serialization dataclasses

**Why we selected it**The exclusion table says dataclasses.field(repr=False) does not block asdict, Pydantic Field(exclude=True) does not block repr, and neither flag blocks vars, __dict__ or pickle.

**Weigh up**The repository README describes the pack as skills for Sentry employees. The documented whole-pack install includes skills this catalogue has withheld.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-secret-serialization/) Install command in review Apache-2.0
 Compare Secret Serialization Review Add

Security review · Addy Osmani

### [Security and hardening](/skills/addyosmani-security-and-hardening/)

Starts with a threat model and a three-tier boundary, not with a generic vulnerability list.

 security owasp hardening

**Why we selected it**It starts with a threat model: trust boundaries, named assets and a STRIDE pass over each boundary, with abuse cases written next to use cases.

**Weigh up**Each control links to references/hardening-patterns.md inside the skill, and the review checklist to ../../references/security-checklist.md, which the README says a per-skill npx install does not copy.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/addyosmani-security-and-hardening/) Install command in review MIT
 Compare Security and hardening Add

Security review · Cloudflare

### [Security Audit](/skills/cloudflare-security-audit/)

Source-first security audit with independent verification, a coverage ledger and a sandbox requirement before any target code runs.

 security-audit vulnerability-research sandboxing

**Why we selected it**Target-controlled builds, tests and processes run only inside an OS-enforced sandbox with no external network, an allowlisted environment and resource limits; without every control the lead stays needs_validation.

**Weigh up**Full audit mode needs a host with parallel sub-agents and Node.js for the bundled validators. The companion Markdown files and both validators were not opened for this review.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/cloudflare-security-audit/) Install command in review MIT
 Compare Security Audit Add

Security · trailofbits

### [Security Audit Preparation](/skills/trailofbits-audit-prep-assistant/)

Prepare a frozen, buildable codebase and evidence package for an external security review.

 security trailofbits

**Why we selected it**The checklist identifies copied code and modifications, documents actors/privileges and on-chain/off-chain assumptions, and treats a reproducible frozen source as an assessment input.

**Weigh up**Coverage targets and preparation timelines are planning suggestions; a clean scanner report or high coverage does not establish audit readiness by itself.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-audit-prep-assistant/) Install command in review CC-BY-SA-4.0
 Compare Security Audit Preparation Add

Security · trailofbits

### [Semgrep Repository Scan](/skills/trailofbits-semgrep/)

Plan and execute language-scoped Semgrep scans with explicit partial, failed and uncovered scan states.

 security trailofbits

**Why we selected it**The scan skill treats the user's request to scan as not enough approval, and run-scans.sh is what puts --metrics=off on every generated command.

**Weigh up**OSS Semgrep, as this file describes it, cannot track data flow across files. Third-party rules are cloned into the output directory and then deleted.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-semgrep/) Upstream setup linked CC-BY-SA-4.0
 Compare Semgrep Repository Scan Add

Security and privacy · Trail of Bits

### [Semgrep Rule Creator](/skills/trailofbits-semgrep-rule-creator/)

Turns a concrete bug pattern into a Semgrep rule with positive and negative test cases.

 semgrep static-analysis regression-tests

**Why we selected it**Requires vulnerable and safe examples before rule implementation, then runs Semgrep validation and rule tests.

**Weigh up**A passing fixture suite establishes behavior on those examples; it does not prove complete detection or an acceptable false-positive rate on other repositories.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-semgrep-rule-creator/) Install command in review CC-BY-SA-4.0
 Compare Semgrep Rule Creator Add

Security · trailofbits

### [Semgrep Rule Variants](/skills/trailofbits-semgrep-rule-variant-creator/)

Port one verified rule to target languages with applicability review and language-specific positive and negative fixtures.

 security trailofbits

**Why we selected it**This skill ports one finished Semgrep rule to named languages. A new rule from a bug description is sent to semgrep-rule-creator instead.

**Weigh up**allowed-tools includes WebFetch and Write. Resume does not survive a new session, because runs live under that session's directory.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-semgrep-rule-variant-creator/) Upstream setup linked CC-BY-SA-4.0
 Compare Semgrep Rule Variants Add

Research and documentation · Sentry

### [Sentry API Endpoint Documentation](/skills/getsentry-document-api-endpoint/)

Aligns a Sentry API endpoint’s runtime response, TypedDict definitions and drf-spectacular OpenAPI schema.

 openapi django-rest-framework sentry

**Why we selected it**Checks runtime serialization against types and schema, including the difference between an absent field and a nullable one.

**Weigh up**The file paths, ownership checks and validation commands are specific to Sentry; this is not a drop-in guide for every Django API.

 Source reviewed

8 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-document-api-endpoint/) Install command in review Apache-2.0
 Compare Sentry API Endpoint Documentation Add

Documentation editing · Functional Software, Inc. dba Sentry

### [Sentry brand guidelines](/skills/getsentry-brand-guidelines/)

Writes Sentry UI copy and defaults to Plain Speech unless the context calls for Sentry Voice.

 copy tone sentry

**Why we selected it**Plain Speech is the default, and Sentry Voice is limited to surfaces such as 404s, empty states, and onboarding.

**Weigh up**The handbook links are references. The skill does not fetch them and does not check a rendered page.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-brand-guidelines/) Install command in review Apache-2.0
 Compare Sentry brand guidelines Add

Developer Tools · Sentry

### [Sentry Claude Settings Audit](/skills/getsentry-claude-settings-audit/)

Audits repository tooling to generate least-privilege Claude Code settings.json read-only allowlists.

 sentry claude-code permissions

**Why we selected it**Inspects package manifests and monorepo configurations to discover project-specific read-only test, lint, and type-check commands.

**Weigh up**Generated settings recommendations require human confirmation before copying into .claude/settings.json.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-claude-settings-audit/) Install command in review Apache-2.0
 Compare Sentry Claude Settings Audit Add

Code review · Functional Software, Inc. dba Sentry

### [Sentry code review](/skills/getsentry-code-review/)

Reviews a change for runtime, query, security, design, and test gaps, and does not block on style.

 review security sentry

**Why we selected it**The checklist separates defects that should block a change from style comments that should not.

**Weigh up**The file is a checklist. It has no gh command, so it does not submit a GitHub review or change the code.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-code-review/) Install command in review Apache-2.0
 Compare Sentry code review Add

Code editing · Functional Software, Inc. dba Sentry

### [Sentry code simplifier](/skills/getsentry-code-simplifier/)

Refines recently modified code for clarity and says to leave its behaviour unchanged.

 refactor clarity sentry

**Why we selected it**The skill's first rule is that behaviour, outputs, and features stay the same while the shape of the code changes.

**Weigh up**The definition assumes CLAUDE.md standards but specifies no fallback when that file is absent.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-code-simplifier/) Install command in review Apache-2.0
 Compare Sentry code simplifier Add

Git commits · Functional Software, Inc. dba Sentry

### [Sentry commit message](/skills/getsentry-commit/)

Drafts one conventional commit on a feature branch, and stops if the branch is still main or master.

 git commit sentry

**Why we selected it**The skill stops a commit that is still on main or master unless the user explicitly asked for that, and it asks for one reviewable change per commit.

**Weigh up**It tells the agent to pass paragraphs as separate git commit -m arguments and not to open an editor. It does not push the commit or open a pull request.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-commit/) Install command in review Apache-2.0
 Compare Sentry commit message Add

Git branches · Functional Software, Inc. dba Sentry

### [Sentry create branch](/skills/getsentry-create-branch/)

Creates one local branch with git checkout -b and does not say to push or to commit.

 git branch sentry

**Why we selected it**The workflow creates the branch without asking for a name confirmation, and it only checks out the default branch when the user says so.

**Weigh up**With no local diff it invents a generic description such as repo-maintenance. It does not commit, push, or open a pull request.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-create-branch/) Install command in review Apache-2.0
 Compare Sentry create branch Add

Testing and reliability · Sentry

### [Sentry Find Bugs](/skills/getsentry-find-bugs/)

Reviews a branch diff against surrounding code and existing tests, reporting only substantiated issues and explicit coverage limits.

 code-review git-diff security-review

**Why we selected it**Requires the complete diff to be read before findings and follows changed behavior into surrounding implementations and tests.

**Weigh up**The initial command compares committed branch history and omits uncommitted edits; inspect those separately if they are in scope.

 Source reviewed

7 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-find-bugs/) Install command in review Apache-2.0
 Compare Sentry Find Bugs Add

Development workflow · getsentry

### [Sentry Frontend Queue Triage](/skills/getsentry-triage-frontend-issues/)

Prepare a bounded archive plan for the Sentry internal javascript issue queue and apply only the approved rows.

 development-workflow getsentry

**Why we selected it**The skill only archives issues in the sentry/javascript project, and only with untilEscalating, after the user approves the displayed plan.

**Weigh up**It needs the Sentry MCP at mcp.sentry.dev and the update_issue tool. If that tool is missing it stops.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-triage-frontend-issues/) Install command in review Apache-2.0
 Compare Sentry Frontend Queue Triage Add

Review queue · Functional Software, Inc. dba Sentry

### [Sentry GitHub review requests](/skills/getsentry-gh-review-requests/)

Lists unread review-requested notifications for open pull requests tied to named teams.

 github reviews sentry

**Why we selected it**The skill's only declared tool is Bash, and both the skill and the script require an authenticated gh CLI.

**Weigh up**The default organisation is getsentry. Another org has to be passed explicitly.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-gh-review-requests/) Install command in review Apache-2.0
 Compare Sentry GitHub review requests Add

Development workflow · getsentry

### [Sentry Presentation Builder](/skills/getsentry-presentation-creator/)

Create a branded React slide deck with charts only where supplied measurements support them.

 development-workflow getsentry

**Why we selected it**Charts are allowed only for numbers that are already in the source. The skill forbids estimated or invented series.

**Weigh up**SKILL.md forbids category pills above headings, while references/design-system.md says tags are used on every slide. Those two files disagree.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-presentation-creator/) Install command in review Apache-2.0
 Compare Sentry Presentation Builder Add

AI application development · Sentry

### [Sentry Prompt Optimizer](/skills/getsentry-prompt-optimizer/)

Starts from a written contract before rewriting a prompt, and names the model family as a choice rather than a default.

 prompts prompt-evals token-cost

**Why we selected it**Optimization starts from a written contract and an eval slice, not from a rewrite.

**Weigh up**The failure-mode list includes editing before the eval target is defined.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-prompt-optimizer/) Install command in review Apache-2.0
 Compare Sentry Prompt Optimizer Add

Pull requests · Functional Software, Inc. dba Sentry

### [Sentry pull request issue link](/skills/getsentry-pr-link-issue/)

Appends an Issues block to the current pull request after reading its body.

 github pull-request sentry

**Why we selected it**The skill edits an existing pull request body and stops when the branch has no pull request.

**Weigh up**It uses authenticated gh, so it can change the pull request body on GitHub. It does not open the pull request, create the GitHub issue, or create the Linear ticket.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-pr-link-issue/) Install command in review Apache-2.0
 Compare Sentry pull request issue link Add

Documentation editing · Functional Software, Inc. dba Sentry

### [Sentry SRED work summary](/skills/getsentry-sred-work-summary/)

Collects one person's GitHub, Notion and Linear links for a year and groups them in a private Notion document.

 notion github linear

**Why we selected it**The workflow collects a person's GitHub, Notion, and Linear links for a fixed February-to-January window and writes them to a private Notion page.

**Weigh up**Notion and Linear access are MCP connections, and GitHub may be gh. The skill does not file a tax claim or compute an amount.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-sred-work-summary/) Install command in review Apache-2.0
 Compare Sentry SRED work summary Add

Code editing · Functional Software, Inc. dba Sentry

### [Sentry typing exclusion worker](/skills/getsentry-typing-exclusion-worker/)

Removes an assigned batch of modules from a mypy exclusion list, then fixes and checks only that batch.

 mypy python typing

**Why we selected it**The worker is limited to one assigned mypy batch and a fixed summary for a manager.

**Weigh up**Only assigned exclusion entries may be removed, and cross-team modules need explicit approval.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-typing-exclusion-worker/) Install command in review Apache-2.0
 Compare Sentry typing exclusion worker Add

Observability · Anthropic

### [Session Report](/skills/anthropic-session-report/)

Runs a bundled Node analyzer over local Claude Code transcripts and fills an HTML template with token use by project, subagent type and skill, cache breaks and the most expensive prompts, plus a few findings and suggestions.

 claude-code token-usage prompt-caching

**Why we selected it**Its numbers come from a bundled script, analyze-sessions.mjs, which breaks token use down by project, subagent type and skill and lists cache breaks and the top prompts; the model pastes that JSON into the template and adds 3-5 findings, expressed as shares of total tokens, and 1-4 suggestions.

**Weigh up**Last commit touching plugins/session-report/skills/session-report at revision 41f32e40: 2026-04-09 (9dc3809e).

 Source reviewed

6 sources · 2026-10-21

[Read the full review ↗](/skills/anthropic-session-report/) Upstream setup linked Apache-2.0
 Compare Session Report Add

Model evaluation · Braintrust

### [Size an Eval Dataset](/skills/braintrustdata-braintrust-size-eval-dataset/)

Computes or audits eval sample sizes, detectable effects and clean-trial counts, with clustering and pairing assumptions stated.

 evaluation sample-size statistics

**Why we selected it**It forbids returning a sample size without stating effect size, baseline rate, risk tolerance, clustering, pairing, confidence and power, and requires a sensitivity range rather than one number.

**Weigh up**The body cites anchors in reference.md, which is not in the skill directory at this revision. The header points to references/power-analysis.md, which was not opened.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/skills/braintrustdata-braintrust-size-eval-dataset/) Install command in review Apache-2.0
 Compare Size an Eval Dataset Add

Agent development · Anthropic

### [Skill Development for Claude Code Plugins](/skills/anthropic-skill-development/)

Guides writing a skill that ships inside a Claude Code plugin: directory layout, a third-person trigger description, an imperative SKILL.md body and progressive disclosure into references/, examples/ and scripts/.

 claude-code plugin-dev skills

**Why we selected it**It adapts the skill-creator method to plugin skills, which is what separates it from the general skill-creator: plugin skills are created by hand under plugin-name/skills/<skill-name>/ instead of with init_skill.py, ship with the plugin rather than as separate ZIP files, and are reviewed with plugin-dev's skill-reviewer agent.

**Weigh up**Last commit touching plugins/plugin-dev/skills/skill-development at revision 41f32e40: 2026-02-05 (2438937b).

 Source reviewed

5 sources · 2026-10-21

[Read the full review ↗](/skills/anthropic-skill-development/) Upstream setup linked Apache-2.0
 Compare Skill Development for Claude Code Plugins Add

Skill review loop · Trail of Bits

### [Skill improver](/skills/trailofbits-skill-improver/)

Pins the skill loop that stops when plugin-dev is missing, refuses an inline rewrite, and does not commit.

 skill review workflow

**Why we selected it**Several matching skills are a question to the user, and a missing plugin-dev reviewer stops the run instead of a self-review.

**Weigh up**The resource was not executed.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-skill-improver/) Install command in review CC-BY-SA-4.0
 Compare Skill improver Add

Security review · Sentry

### [Skill scanner](/skills/getsentry-skill-scanner/)

Audits a skill before install, with a bundled script and explicit confidence levels.

 skills supply-chain review

**Why we selected it**A Bundled Script heading means the check is not only prose.

**Weigh up**The bundled script was not executed in this review.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/getsentry-skill-scanner/) Install command in review Apache-2.0
 Compare Skill scanner Add

Security review · Trail of Bits

### [Slicing Code Context](/skills/trailofbits-trailmark-slicing-code-context/)

Uses Trailmark to cut a bounded, graph-informed slice of source around a function, class, caller, callee, call path, entry point or line range and hands it to a smaller worker model that may only propose edits.

 code-understanding call-paths subagents

**Why we selected it**Builds a deterministic Trailmark slice packet and gives a worker only the task and that packet; the worker may propose changes but not apply them.

**Weigh up**Workers may only propose changes; the skill is not for tasks that need direct worker edits.

 Source reviewed

6 sources · 2026-10-22

[Read the full review ↗](/skills/trailofbits-trailmark-slicing-code-context/) Upstream setup linked CC-BY-SA-4.0
 Compare Slicing Code Context Add

Security · trailofbits

### [Smart Contract Development Guidelines](/skills/trailofbits-guidelines-advisor/)

Review smart-contract architecture, implementation and verification against a structured guideline set.

 security trailofbits

**Why we selected it**The detailed assessment distinguishes storage layout, inheritance order, initializer front-running, function shadowing and direct implementation use.

**Weigh up**This is an advisory checklist, not a security certificate. Compiler behavior and proxy semantics require version-specific inspection; not every project should adopt the same migration pattern.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-guidelines-advisor/) Install command in review CC-BY-SA-4.0
 Compare Smart Contract Development Guidelines Add

Security · trailofbits

### [Smart Contract Maturity Assessment](/skills/trailofbits-code-maturity-assessor/)

Assess a blockchain codebase against an explicit nine-category maturity rubric.

 security trailofbits

**Why we selected it**The criteria require more than event declarations for auditing maturity and compare arithmetic precision and low-level code against explicit reference behavior.

**Weigh up**Rubric scores are reviewer judgments, not measured probabilities of safety. Unobserved off-chain processes must remain unknown until corroborated; an average can hide a critical weakness.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-code-maturity-assessor/) Install command in review CC-BY-SA-4.0
 Compare Smart Contract Maturity Assessment Add

Security · trailofbits

### [Smart Contract Security Workflow](/skills/trailofbits-secure-workflow-guide/)

Combine static analysis, feature checks, invariants and manual review in a smart-contract workflow.

 security trailofbits

**Why we selected it**The workflow separates known-pattern scans from state/authorization diagrams, property design and manual review of privacy, transaction ordering and external assumptions.

**Weigh up**Detector/spec counts in the definition are version-dependent. A completed symbolic or fuzzing run only supports the properties and explored paths actually checked.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-secure-workflow-guide/) Install command in review CC-BY-SA-4.0
 Compare Smart Contract Security Workflow Add

Security review · Trail of Bits

### [Solana vulnerability scanner](/skills/trailofbits-solana-vulnerability-scanner/)

Pins Trail of Bits' Solana scanner, which refuses a short coverage table, keeps the version-scoped row, and does not treat passing lints or an Anchor attribute as a full check.

 solana anchor security

**Why we selected it**A short or empty coverage table is an incomplete scan, and the version-scoped pattern stays in the table with the targeted solana-program version instead of being dropped.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-solana-vulnerability-scanner/) Install command in review CC-BY-SA-4.0
 Compare Solana vulnerability scanner Add

Development workflow · addyosmani

### [Source-Driven Implementation](/skills/addyosmani-source-driven-development/)

Ground version-sensitive code changes in official documentation and explicit source citations.

 development-workflow addyosmani

**Why we selected it**The workflow orders sources by authority and expressly excludes model-targeted directives and unrelated outbound endpoints from copied documentation examples.

**Weigh up**Official documentation can be incomplete or refer to another version; a citation is not runtime proof. Retrieved instructions must not expand the authorized task.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/addyosmani-source-driven-development/) Install command in review MIT
 Compare Source-Driven Implementation Add

Security · trailofbits

### [Specification to Code Compliance](/skills/trailofbits-spec-to-code-compliance/)

Compare authoritative requirements with implementation evidence and retain undecidable or unchecked requirements.

 security trailofbits

**Why we selected it**The skill compares code with a document that says what the code is supposed to do. It is not a general bug hunt, and it is not a documentation rewrite.

**Weigh up**Declared tools are Workflow, Task, Read, Grep, and Glob. There is no WebFetch in the frontmatter. The check writes local report files and is not meant to be done inline for a long requirement list.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-spec-to-code-compliance/) Upstream setup linked CC-BY-SA-4.0
 Compare Specification to Code Compliance Add

Planning and delivery · Matt Pocock

### [Specification to Dependency-Aware Tickets](/skills/mattpocock-to-tickets/)

Splits an agreed plan into small vertical slices, with explicit blocking relationships and a review before publication.

 tickets dependencies planning

**Why we selected it**Asks for user agreement on the proposed breakdown before creating the tickets.

**Weigh up**Ticket publication is not transactional: partial failures or repeated runs can leave duplicates and incomplete dependency links.

 Source reviewed

16 sources · 2026-10-15

[Read the full review ↗](/skills/mattpocock-to-tickets/) Install command in review MIT
 Compare Specification to Dependency-Aware Tickets Add

Observability · Axiom, Inc.

### [SPL to APL](/skills/axiomhq-spl-to-apl/)

Translate a Splunk SPL fragment into Axiom APL, including the argument reversal and the time filter the SPL picker does not carry over.

 splunk apl queries

**Why we selected it**The translation rules include argument order and time filters that a mechanical rename would miss.

**Weigh up**APL join is described as preview, limited to 50k rows, and only inner, innerunique, and leftouter.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/axiomhq-spl-to-apl/) Install command in review MIT
 Compare SPL to APL Add

Security · JetBrains

### [Spring Security Configurator Auditor](/skills/jetbrains-spring-security-configurator-auditor/)

Designs and audits Spring Security configurations: explicit public-endpoint allowlists, JWT and OAuth2 resource-server trust boundaries with issuer, audience and clock-skew validation, ordered filter chains, method security aligned with request security, and CSRF treated as a trust-model decision.

 spring-security authentication authorization

**Why we selected it**Audits before it configures: enumerate public endpoints explicitly, model who can do what to which resource under which tenant before writing matcher code, and prefer deny-by-default so new endpoints start closed.

**Weigh up**Spring Security plus Kotlin specifics; servlet versus reactive stack differences are flagged but only the Spring ecosystem is covered.

 Source reviewed

6 sources · 2026-10-13

[Read the full review ↗](/skills/jetbrains-spring-security-configurator-auditor/) Install command in review MIT (upstream Kotlin backend agent skills)
 Compare Spring Security Configurator Auditor Add

Databases · GitHub community

### [SQL Object Impact Analysis](/skills/github-sql-object-impact-analysis/)

Before a schema change, traces every reference to a table, column, stored procedure, view or trigger across both SQL objects and application code, and produces a structured blast-radius report with confidence-classified findings.

 sql schema-changes impact-analysis

**Why we selected it**Classifies every finding as Direct, Indirect or Uncertain and forbids presenting an Uncertain finding as Direct — the report must state the search method used and its limits instead of implying completeness.

**Weigh up**Static text search cannot resolve every dynamic-SQL construction or reflection-based ORM mapping; the skill says so itself and requires the report to say so.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/github-sql-object-impact-analysis/) Install command in review MIT
 Compare SQL Object Impact Analysis Add

Documentation · Stripe

### [Stripe docs CLI](/skills/stripe-docs/)

Pins Stripe's skill for reading docs through the Stripe CLI, including the login step it requires for gated pages.

 stripe docs cli

**Why we selected it**The catalogue has Stripe billing and payments skills and not this documentation-lookup skill.

**Weigh up**This review did not execute the resource.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/stripe-docs/) Install command in review MIT
 Compare Stripe docs CLI Add

Payments · Stripe

### [Stripe Pay](/skills/stripe-stripe-pay/)

Stops a business-to-business Stripe transfer until the user has seen the exact command and confirmed the handle, amount and currency.

 stripe transfers cli

**Why we selected it**A transfer is not run until the user has seen the exact command and confirmed it.

**Weigh up**The skill forbids sending money unless the user explicitly asks, and it forbids -y before confirmation.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/stripe-stripe-pay/) Install command in review MIT
 Compare Stripe Pay Add

Substrate pallet audit · Trail of Bits

### [Substrate vulnerability scanner](/skills/trailofbits-substrate-vulnerability-scanner/)

Pins the Substrate scanner's rule that a short or empty coverage table is an unfinished scan, and that ensure_signed is not a privileged origin.

 substrate frame pallet

**Why we selected it**A coverage table with fewer than every pattern row, or an empty verdict, must be reported as incomplete, and not having looked is not an n/a.

**Weigh up**The resource was not executed.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-substrate-vulnerability-scanner/) Install command in review CC-BY-SA-4.0
 Compare Substrate vulnerability scanner Add

Databases · Supabase

### [Supabase Development](/skills/supabase-supabase/)

Covers the full Supabase surface beyond Postgres tuning: Auth flows, client and SSR integration, CLI and MCP use, declarative or imperative schema changes, and structured debugging.

 supabase auth migrations

**Why we selected it**Separates declarative schemas from imperative migrations and pairs each path with committing guidance instead of treating all schema edits alike.

**Weigh up**Triggers on any Supabase task, so it can load for work the narrower Postgres skill would handle better; pick the skill per task.

 Source reviewed

6 sources · 2026-10-13

[Read the full review ↗](/skills/supabase-supabase/) Install command in review MIT
 Compare Supabase Development Add

Databases · Supabase

### [Supabase Postgres Best Practices](/skills/supabase-supabase-postgres-best-practices/)

Connects Postgres schema and query decisions to worked SQL examples, connection guidance and row-level security checks.

 postgresql sql indexes

**Why we selected it**Pairs incorrect and corrected SQL with query-plan examples instead of offering only generic database advice.

**Weigh up**Illustrative speedups and blanket indexing rules are not measurements of your workload; inspect actual plans and write costs.

 Source reviewed

7 sources · 2026-10-13

[Read the full review ↗](/skills/supabase-supabase-postgres-best-practices/) Install command in review MIT
 Compare Supabase Postgres Best Practices Add

Testing and reliability · Jesse Vincent / Superpowers

### [Superpowers Receiving Code Review](/skills/obra-receiving-code-review/)

Checks review feedback against the code and project constraints before making and testing each requested change.

 review-feedback regressions verification

**Why we selected it**Treats reviewer suggestions as hypotheses to verify, with explicit checks for existing behavior, platform constraints and unused functionality.

**Weigh up**Its conversational tone rules are a style preference, and its pause-on-ambiguity rule may be too restrictive for independent review items.

 Source reviewed

7 sources · 2026-10-14

[Read the full review ↗](/skills/obra-receiving-code-review/) Install command in review MIT
 Compare Superpowers Receiving Code Review Add

Testing and reliability · Jesse Vincent / Superpowers

### [Superpowers Systematic Debugging](/skills/obra-systematic-debugging/)

Moves debugging from reproducible evidence through a single hypothesis to a verified fix, with a stop point for repeated failed attempts.

 debugging root-cause reproduction

**Why we selected it**Asks for evidence at component boundaries and backward tracing of bad values before proposing a patch.

**Weigh up**The bundled polluter helper assumes npm tests, hides their output and swallows their failing exit statuses.

 Source reviewed

8 sources · 2026-10-14

[Read the full review ↗](/skills/obra-systematic-debugging/) Install command in review MIT
 Compare Superpowers Systematic Debugging Add

Testing and reliability · Jesse Vincent / Superpowers

### [Superpowers Test-Driven Development](/skills/obra-test-driven-development/)

Makes an observed failing behavior test the entry point for implementation and checks that assertions can detect real production mistakes.

 tdd regression-tests test-design

**Why we selected it**Requires verifying why a test fails before changing implementation, then running the project suite after the fix.

**Weigh up**The workflow is deliberately prescriptive: it tells an agent to discard implementation written before tests and seek permission for exceptions.

 Source reviewed

7 sources · 2026-10-14

[Read the full review ↗](/skills/obra-test-driven-development/) Install command in review MIT
 Compare Superpowers Test-Driven Development Add

Testing and reliability · Jesse Vincent / Superpowers

### [Superpowers Verification Before Completion](/skills/obra-verification-before-completion/)

Requires a fresh command result or direct check for each completion claim and distinguishes passing tests from fulfilling requirements.

 verification evidence builds

**Why we selected it**Maps common claims to appropriate evidence, including compiler/build status, original bug reproduction and requirements checks.

**Weigh up**This is a behavioral checklist, not an automatic enforcement mechanism or runtime test harness.

 Source reviewed

6 sources · 2026-10-14

[Read the full review ↗](/skills/obra-verification-before-completion/) Install command in review MIT
 Compare Superpowers Verification Before Completion Add

Research and documentation · Jesse Vincent / Superpowers

### [Superpowers Writing Plans](/skills/obra-writing-plans/)

Turns an agreed specification into file-specific implementation tasks with verification steps and a structured plan review.

 implementation-planning specifications tests

**Why we selected it**Makes each task name concrete files, expected behavior and meaningful failing/passing checks rather than leaving implementation placeholders.

**Weigh up**Detailed code in a plan can become stale as the repository changes; planned checks are not evidence that tests have run.

 Source reviewed

8 sources · 2026-10-14

[Read the full review ↗](/skills/obra-writing-plans/) Install command in review MIT
 Compare Superpowers Writing Plans Add

Security and privacy · Trail of Bits

### [Supply Chain Risk Auditor](/skills/trailofbits-supply-chain-risk-auditor/)

Collects dependency identity, advisory and repository-maintenance evidence while retaining unassessable cases.

 dependencies supply-chain provenance

**Why we selected it**Keeps ecosystem and resolved package versions attached to evidence and distinguishes unknown results from clean checks.

**Weigh up**Documented project inputs include npm package-lock/shrinkwrap, Python uv.lock and supported Go module files; other lock formats need a separate extraction step.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-supply-chain-risk-auditor/) Install command in review CC-BY-SA-4.0
 Compare Supply Chain Risk Auditor Add

Databases · SurrealDB

### [SurrealQL](/skills/surrealdb-surrealql/)

SurrealDB skill for writing, adapting and troubleshooting SurrealQL statements, with statement tables linked to the docs and instructions to validate and format queries with the SurrealDB CLI and surql-fmt.

 graph schema queries

**Why we selected it**Tables map SurrealQL query, schema and control-flow statements, from SELECT and LIVE SELECT to DEFINE TABLE, DEFINE INDEX and BEGIN / COMMIT, to their surrealdb.com docs pages, with references for querying, schema and values.

**Weigh up**The skill directory skills/surrealql last changed in a commit dated 2026-06-16; the pinned revision is dated 2026-09-29. SKILL.md metadata says version 0.2.0.

 Source reviewed

3 sources · 2026-10-21

[Read the full review ↗](/skills/surrealdb-surrealql/) Install command in review MIT
 Compare SurrealQL Add

Framework development · Svelte

### [Svelte Core Best Practices](/skills/svelte-svelte-core-bestpractices/)

Svelte-maintained guidance for reactivity, component composition and integration with browser APIs.

 svelte reactivity components

**Why we selected it**Explains when to derive state instead of synchronizing it with effects, and when reactive wrappers or subscriptions are needed.

**Weigh up**The references span several Svelte releases and include experimental async behavior. Check the installed compiler version and required flags before applying an example.

 Source reviewed

17 sources · 2026-10-13

[Read the full review ↗](/skills/svelte-svelte-core-bestpractices/) Install command in review MIT
 Compare Svelte Core Best Practices Add

Observability · Grafana Labs

### [Synthetic monitoring checks](/skills/grafana-synthetic-monitoring-checks/)

Separates a reliability probe from a load test, and names the assertion mistake that leaves probe_success green.

 synthetic-monitoring k6 probes

**Why we selected it**The first heading says reliability monitoring, not load testing.

**Weigh up**No probe was deployed in this review.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/grafana-synthetic-monitoring-checks/) Install command in review Apache-2.0
 Compare Synthetic monitoring checks Add

Development workflow · GitHub community (awesome-copilot)

### [Task Context Map](/skills/github-context-map/)

Map implementation files, dependencies, tests and reference patterns before changing code.

 development-workflow github

**Why we selected it**The template keeps files to modify, direct dependencies, tests and reference patterns separate and includes explicit API/schema/configuration risk checks.

**Weigh up**A search-based map can miss runtime, generated and external dependencies; the map is a starting hypothesis rather than exhaustive coverage.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/github-context-map/) Install command in review MIT
 Compare Task Context Map Add

Telegram access control · Anthropic

### [Telegram access](/skills/anthropic-telegram-access/)

Pins the Telegram access skill, which resolves a state directory, refuses channel-originated edits, and will not approve a pairing without its code.

 telegram access-control pairing

**Why we selected it**The skill refuses access changes that arrive as a Telegram or Discord message and says those mutations must not be downstream of untrusted input.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/anthropic-telegram-access/) Install command in review Apache-2.0
 Compare Telegram access Add

Telegram channel setup · Anthropic

### [Telegram configure](/skills/anthropic-telegram-configure/)

Pins the Telegram setup skill, which stores a bot token with mode 600 and says pairing should end once the allowlist is known.

 telegram bot-token allowlist

**Why we selected it**The skill resolves the state directory, writes the bot token there, and says to chmod 600 the env file because the token is a credential. The tool list includes that chmod.

**Weigh up**This review did not execute the resource.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/anthropic-telegram-configure/) Install command in review Apache-2.0
 Compare Telegram configure Add

Framework development · Temporal Technologies

### [Temporal Developer](/skills/temporalio-temporal-developer/)

Temporal SDK guidance across seven languages, centred on replay determinism, versioning and wrapping LLM calls in activities.

 temporal durable-execution workflows

**Why we selected it**It explains history replay and why a non-determinism error blocks a workflow, then routes to core and language-specific determinism, versioning and pitfalls references.

**Weigh up**Most guidance sits in the references directory; only SKILL.md and references/core/ai-patterns.md were read. The README lists Rust as Public Preview and PHP as not yet supported.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/skills/temporalio-temporal-developer/) Install command in review MIT
 Compare Temporal Developer Add

Cloud operations · GitHub community

### [Terraform AzureRM Set Diff Analyzer](/skills/github-terraform-azurerm-set-diff-analyzer/)

Separates false-positive Terraform plan diffs — order-only changes in Set-type attributes — from real resource changes, using a stdlib-only Python analyzer over terraform show -json output with CI-ready exit codes.

 terraform azure plan-review

**Why we selected it**Ships a runnable analyzer rather than prose: scripts/analyze_plan.py is standard-library-only Python 3.8+ that classifies order-only versus real changes and exposes --exit-code semantics for CI gating.

**Weigh up**AzureRM-focused: the position-comparison mechanism is general Terraform, but the attribute reference and examples cover Azure resources only.

 Source reviewed

9 sources · 2026-10-15

[Read the full review ↗](/skills/github-terraform-azurerm-set-diff-analyzer/) Install command in review MIT
 Compare Terraform AzureRM Set Diff Analyzer Add

Infrastructure development · HashiCorp

### [Terraform ephemeral resources](/skills/hashicorp-provider-ephemeral-resources/)

Implement short-lived values with Open, optional Renew/Close, private lease handles and explicit non-persistence boundaries.

 terraform provider secrets

**Why we selected it**It implements Terraform 1.10 ephemeral resources whose values are never written to state or plan.

**Weigh up**Ephemeral values cannot be stored in regular resource attributes.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/hashicorp-provider-ephemeral-resources/) Install command in review MPL-2.0
 Compare Terraform ephemeral resources Add

Infrastructure development · HashiCorp

### [Terraform module refactor](/skills/hashicorp-refactor-module/)

Extract Terraform modules while explicitly migrating existing state addresses.

 terraform modules state

**Why we selected it**The definition prefers state list/show-json over treating raw state format as a stable interface and distinguishes moved blocks from manual state migration.

**Weigh up**State contains plaintext sensitive values even in JSON output. Terraform tests defaulting to apply can create real infrastructure; address migration requires a reviewed plan and recoverable state.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/hashicorp-refactor-module/) Install command in review MPL-2.0
 Compare Terraform module refactor Add

Infrastructure · hashicorp

### [Terraform Policy Authoring and Tests](/skills/hashicorp-terraform-policy/)

Author or migrate policy HCL with version-specific mock schemas and targeted pass/fail policy tests.

 infrastructure hashicorp

**Why we selected it**It routes Terraform Policy authoring and tests by the installed tfpolicy minor line, 0.2.x or 0.3.x.

**Weigh up**The skill does not write .tftest.hcl or general Terraform configuration.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/hashicorp-terraform-policy/) Install command in review MPL-2.0
 Compare Terraform Policy Authoring and Tests Add

Testing · HashiCorp

### [Terraform Provider Acceptance Tests](/skills/hashicorp-run-acceptance-tests/)

Runs one Terraform provider TestAcc against a test account, with an explicit timeout and a flip check for a false pass.

 terraform acceptance-tests go

**Why we selected it**The procedure is bounded: confirm the credentials point at a test account, run one TestAcc with TF_ACC=1 and a timeout above Go’s 10-minute default, and discover extra variables from PreCheck and os.Getenv rather than guessing.

**Weigh up**Acceptance tests create real infrastructure and can cost money. The skill says so, and sweepers are left to a separate provider-test-patterns skill if that skill is installed.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/hashicorp-run-acceptance-tests/) Install command in review MPL-2.0
 Compare Terraform Provider Acceptance Tests Add

Infrastructure · hashicorp

### [Terraform Provider Documentation](/skills/hashicorp-provider-docs/)

Generate Registry documentation from implemented schema descriptions, focused templates and reusable HCL examples.

 infrastructure hashicorp

**Why we selected it**It generates Terraform Registry docs from schema descriptions and tfplugindocs templates, and it forbids pages for objects the provider does not implement.

**Weigh up**The skill does not publish the provider; it only prepares docs and names the tag and manifest checks.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/hashicorp-provider-docs/) Install command in review MPL-2.0
 Compare Terraform Provider Documentation Add

Infrastructure development · HashiCorp

### [Terraform Provider Resources](/skills/hashicorp-provider-resources/)

Implements Plugin Framework resources and data sources, including drift, import and the acceptance tests a submission needs.

 terraform provider go

**Why we selected it**The scope names CRUD, plan modifiers, validators, waiters, import and acceptance-test coverage as one workflow.

**Weigh up**MPL-2.0 is file-level copyleft for modified redistributions of this file.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/hashicorp-provider-resources/) Install command in review MPL-2.0
 Compare Terraform Provider Resources Add

Infrastructure · hashicorp

### [Terraform Provider Scaffold](/skills/hashicorp-new-terraform-provider/)

Scaffold a Plugin Framework provider with configuration schema, unknown-value guards and environment credential fallback.

 infrastructure hashicorp

**Why we selected it**It scaffolds a Plugin Framework provider only after confirming a new terraform-provider-* workspace.

**Weigh up**The skill stops if the user does not want a new workspace.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/hashicorp-new-terraform-provider/) Install command in review MPL-2.0
 Compare Terraform Provider Scaffold Add

Infrastructure development · HashiCorp

### [Terraform search and import](/skills/hashicorp-terraform-search-import/)

Runs Terraform Search only after the provider is shown to support that resource type, and switches to a manual import when it does not.

 terraform import discovery

**Why we selected it**The skill says to verify list-resource support before writing a query, and to stop the search path when the type is unsupported.

**Weigh up**Search needs an initialized working directory and a provider that implements list for that type.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/hashicorp-terraform-search-import/) Install command in review MPL-2.0
 Compare Terraform search and import Add

Infrastructure development · HashiCorp

### [Terraform Stacks](/skills/hashicorp-terraform-stacks/)

Covers Terraform Stacks component and deployment files, including the required Terraform version file.

 terraform stacks hcl

**Why we selected it**The definition names .tfcomponent.hcl and .tfdeploy.hcl as distinct files.

**Weigh up**MPL-2.0 applies to modified redistributions of this file.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/hashicorp-terraform-stacks/) Install command in review MPL-2.0
 Compare Terraform Stacks Add

Development workflow · HashiCorp

### [Terraform style guide](/skills/hashicorp-terraform-style-guide/)

Applies HashiCorp's own HCL conventions for file order, naming, variables and outputs.

 terraform style hcl

**Why we selected it**The headings cover file organisation, formatting, naming, variables and outputs as separate rules.

**Weigh up**Style agreement is not a plan or an apply.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/hashicorp-terraform-style-guide/) Install command in review MPL-2.0
 Compare Terraform style guide Add

Development workflow · GitHub community (awesome-copilot)

### [Test Gap Audit](/skills/github-test-gap-audit/)

Map risky behavior to existing tests and report confirmed gaps separately from heuristic leads.

 development-workflow github

**Why we selected it**It audits missing or weak tests and stays read-only unless the user asks for new tests.

**Weigh up**The skill does not install dependencies or start services unless the user asks.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/github-test-gap-audit/) Install command in review MIT
 Compare Test Gap Audit Add

Agent development · Trail of Bits

### [Testing Handbook Skill Generator](/skills/trailofbits-testing-handbook-generator/)

Maintainer workflow that reads sections of the Trail of Bits Testing Handbook (appsec.guide) and writes or refreshes the matching Claude Code skills inside the trailofbits/skills testing-handbook-skills plugin.

 skills agent-development fuzzing

**Why we selected it**It maps handbook sections to four skill types (tool, fuzzer, technique and domain), each with its own template under templates/.

**Weigh up**It maintains the trailofbits/skills repository itself: it writes under plugins/testing-handbook-skills/skills/ and edits the repository root README.md, so it needs a checkout of that repository.

 Source reviewed

8 sources · 2026-10-22

[Read the full review ↗](/skills/trailofbits-testing-handbook-generator/) Upstream setup linked CC-BY-SA-4.0
 Compare Testing Handbook Skill Generator Add

AI application development · Together AI

### [Together AI](/skills/togethercomputer-together-ai/)

Routes Together AI work to domain guides, with rules against retrying unrecoverable errors and leaving billable resources running.

 together-ai inference fine-tuning

**Why we selected it**Dedicated endpoints, containers and clusters bill while they run; the file says to create them only when asked, delete what was created and confirm it is gone.

**Weigh up**Model IDs in the guides are examples checked 2026-10-07, per the file. The frontmatter still lists embeddings and reranking, while domains/embeddings.md says Together does not currently offer them.

 Source reviewed

4 sources · 2026-10-13

[Read the full review ↗](/skills/togethercomputer-together-ai/) Install command in review MIT
 Compare Together AI Add

Security · trailofbits

### [Token Integration Review](/skills/trailofbits-token-integration-analyzer/)

Review token implementations and protocol integrations for non-standard transfer and approval behavior.

 security trailofbits

**Why we selected it**The checklist separates missing return values, transfer fees, rebasing, hooks and owner-controlled changes, and asks whether the protocol handles those behaviors rather than relying on token reputation.

**Weigh up**Named-token examples and sample reports are illustrative and may be stale or internally inconsistent. Safe wrappers do not resolve rebasing, upgradeability or accounting assumptions automatically.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-token-integration-analyzer/) Install command in review CC-BY-SA-4.0
 Compare Token Integration Review Add

TON contract audit · Trail of Bits

### [TON vulnerability scanner](/skills/trailofbits-ton-vulnerability-scanner/)

Pins the TON scanner's refusal to omit a coverage row, and its requirement to cite the stored address a Jetton sender is compared against.

 ton func jetton

**Why we selected it**An empty verdict or a missing pattern row is an incomplete scan, and not having looked is not an n/a.

**Weigh up**The resource was not executed.

 Source reviewed

4 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-ton-vulnerability-scanner/) Install command in review CC-BY-SA-4.0
 Compare TON vulnerability scanner Add

Security · Trail of Bits

### [Trail of Bits Agentic Actions Auditor](/skills/trailofbits-agentic-actions-auditor/)

Traces external issue or pull-request input into AI-enabled GitHub Actions and reports the permissions that could amplify an injection path.

 github-actions prompt-injection ci-security

**Why we selected it**Checks environment intermediaries and reusable-workflow inputs as well as prompt text.

**Weigh up**Static guidance only: it does not execute an attack, fix workflows or certify that CI is secure.

 Source reviewed

5 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-agentic-actions-auditor/) Upstream setup linked CC-BY-SA-4.0
 Compare Trail of Bits Agentic Actions Auditor Add

Security · Trail of Bits

### [Trail of Bits Audit Context Building](/skills/trailofbits-audit-context-building/)

Builds a cited dossier of function invariants, assumptions and dependencies before a separate vulnerability-hunting pass.

 audit code-understanding invariants

**Why we selected it**Follows callees and unsuccessful paths instead of trusting names such as validate or authorize.

**Weigh up**The skill is a router into a plugin workflow and named function analyzer; a copied standalone SKILL.md is insufficient. No download is offered for that reason: workflows/audit-context.js and agents/function-analyzer.md sit outside the skill directory.

 Source reviewed

7 sources · 2026-10-13

[Read the full review ↗](/skills/trailofbits-audit-context-building/) Upstream setup linked CC-BY-SA-4.0
 Compare Trail of Bits Audit Context Building Add

Security · Trail of Bits

### [Trail of Bits Differential Security Review](/skills/trailofbits-differential-review/)

Reviews security-relevant changes against their baseline, removed protections, callers and concrete attacker scenarios.

 diff-review git-history security

**Why we selected it**Uses git history to ask why a removed check existed and whether a previous fix is being undone.

**Weigh up**The methodology includes checking out the baseline and head; use a suitable worktree so the review does not disrupt uncommitted work.

 Source reviewed

6 sources · 2026-10-13

[Read the full review ↗](/skills/trailofbits-differential-review/) Attributed definition available CC-BY-SA-4.0
 Compare Trail of Bits Differential Security Review Add

Code correctness · Trail of Bits

### [Trail of Bits Dimensional Analysis](/skills/trailofbits-dimensional-analysis/)

Coordinates unit discovery, source annotations and arithmetic review, with a manifest recording which files were validated or blocked.

 units fixed-point arithmetic

**Why we selected it**Tracks semantic units separately from decimal scaling across arithmetic and function boundaries.

**Weigh up**The workflow edits source comments and writes root-level manifests; it is not a read-only spot check.

 Source reviewed

7 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-dimensional-analysis/) Upstream setup linked CC-BY-SA-4.0
 Compare Trail of Bits Dimensional Analysis Add

Languages and tooling · Trail of Bits

### [Trail of Bits Modern C++](/skills/trailofbits-modern-cpp/)

Pushes new C++ toward C++20, 23, and 26 idioms and a hardened libc++, and stops when the user requires an older standard or the file is C.

 cpp modern-cpp memory-safety

**Why we selected it**When NOT to Use respects an explicit older-standard constraint and excludes pure C, build-system questions, and projects that are not primarily C++.

**Weigh up**An embedded or legacy ABI that must stay on an older standard is a stated reason not to apply the skill.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-modern-cpp/) Install command in review CC-BY-SA-4.0
 Compare Trail of Bits Modern C++ Add

Testing and reliability · Trail of Bits

### [Trail of Bits Mutation Analysis](/skills/trailofbits-mutation-testing/)

Interprets mutation campaign results and turns survivors into qualified test-gap reports or separately reproduced bug findings.

 mutation-testing test-gaps mewt

**Why we selected it**Separates test-gap analysis from bug hunting, so an uncaught mutation is not automatically presented as a vulnerability.

**Weigh up**This selection focuses on existing-report analysis. Setup and optimization need separate review: examples hardcode src/, retain a pre-optimization acceptance check and mix counting formats. Do not copy their campaign estimates or purge steps unchanged.

 Source reviewed

15 sources · 2026-10-13

[Read the full review ↗](/skills/trailofbits-mutation-testing/) Install command in review CC-BY-SA-4.0
 Compare Trail of Bits Mutation Analysis Add

Testing and reliability · Trail of Bits

### [Trail of Bits Property-Based Testing](/skills/trailofbits-property-based-testing/)

Chooses meaningful invariants and generators for tests that explore an input domain, while rejecting tautological or vacuous assertions.

 property-testing hypothesis invariants

**Why we selected it**Explains how tests can pass while restating implementation or filtering away nearly every input.

**Weigh up**Property selection still needs a valid specification; an incorrect invariant can generate misleading failures.

 Source reviewed

6 sources · 2026-10-13

[Read the full review ↗](/skills/trailofbits-property-based-testing/) Attributed definition available CC-BY-SA-4.0
 Compare Trail of Bits Property-Based Testing Add

Security · Trail of Bits

### [Trail of Bits Sharp Edges](/skills/trailofbits-sharp-edges/)

Examines APIs and configuration for cases where ordinary developer mistakes can disable a security boundary.

 api-design secure-defaults configuration

**Why we selected it**Looks at zero, empty, negative and mixed-up values rather than only intended happy-path usage.

**Weigh up**This is a design-review method, not a general implementation bug scanner.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/skills/trailofbits-sharp-edges/) Attributed definition available CC-BY-SA-4.0
 Compare Trail of Bits Sharp Edges Add

Security review · Trail of Bits

### [Trailmark](/skills/trailofbits-trailmark/)

Parses a codebase into a queryable graph of functions, classes and calls and runs pre-analysis passes for blast radius, taint, privilege boundaries and entry points, so later trailmark skills can ask structural questions instead of reading files.

 code-understanding call-paths blast-radius

**Why we selected it**Builds one queryable source/binary graph and runs preanalysis() for blast radius, entry points, privilege boundaries and taint, storing the results as annotations and named subgraphs.

**Weigh up**It is static analysis; the skill lists runtime behaviour analysis under When NOT to Use.

 Source reviewed

5 sources · 2026-10-22

[Read the full review ↗](/skills/trailofbits-trailmark/) Upstream setup linked CC-BY-SA-4.0
 Compare Trailmark Add

Security review · Trail of Bits

### [Trailmark Finding Triage](/skills/trailofbits-trailmark-finding-triage/)

Triages a single finding, SARIF result, weAudit annotation, suspicious function or report excerpt with Trailmark reachability, entrypoint-path, taint, privilege-boundary, blast-radius and caller/callee evidence, returning one of four verdicts: Promote, Needs manual review, Deprioritize or Blocked.

 triage sarif blast-radius

**Why we selected it**Triages one finding with reachability, entrypoint paths, taint, privilege-boundary, blast-radius and caller/callee evidence from the graph.

**Weigh up**Trailmark Finding Triage's SKILL.md declares allowed-tools that include Write; it writes an evidence packet, and evidence_packet.py can write JSON with --out.

 Source reviewed

6 sources · 2026-10-22

[Read the full review ↗](/skills/trailofbits-trailmark-finding-triage/) Upstream setup linked CC-BY-SA-4.0
 Compare Trailmark Finding Triage Add

Security review · Trail of Bits

### [Trailmark Review Gate](/skills/trailofbits-trailmark-review-gate/)

Runs a Trailmark structural gate over a branch, pull request, fix commit, release diff or ref range and returns PASS, WARN, FAIL or UNKNOWN for new entrypoints, lost validation, privilege-boundary drift, blast-radius growth and newly reachable sinks.

 diff-review pull-request blast-radius

**Why we selected it**Applies PASS/WARN/FAIL/UNKNOWN gate rules over a branch, PR, fix commit, release diff or ref range, running engine.preanalysis() on both snapshots.

**Weigh up**Trailmark Review Gate's SKILL.md declares allowed-tools that include Write; it writes a gate packet (references/output-format.md) for the branch reviewer.

 Source reviewed

5 sources · 2026-10-22

[Read the full review ↗](/skills/trailofbits-trailmark-review-gate/) Upstream setup linked CC-BY-SA-4.0
 Compare Trailmark Review Gate Add

Security review · Trail of Bits

### [Trailmark Structural Analysis](/skills/trailofbits-trailmark-structural/)

Builds a Trailmark graph and runs engine.preanalysis() to report complexity hotspots, taint, blast radius, privilege boundaries and attack surface, with extra 0.4+/0.5+ fields when that Trailmark is installed.

 blast-radius graph security-audit

**Why we selected it**Builds a graph and runs engine.preanalysis() for hotspots, taint, blast radius, privilege boundaries and attack surface, enriched by 0.4+/0.5+ data when present.

**Weigh up**Trailmark Structural Analysis's SKILL.md declares allowed-tools Bash, Read, Grep and Glob, with no Write.

 Source reviewed

5 sources · 2026-10-22

[Read the full review ↗](/skills/trailofbits-trailmark-structural/) Upstream setup linked CC-BY-SA-4.0
 Compare Trailmark Structural Analysis Add

Security review · Trail of Bits

### [Trailmark Summary](/skills/trailofbits-trailmark-summary/)

Runs a Trailmark summary over a codebase and returns the auto-detected languages, an entry-point count and a dependency list as a quick structural overview.

 code-understanding graph security-audit

**Why we selected it**Returns auto-detected languages, an entry-point count and a dependency list, and reports a gap rather than fabricate any of the three.

**Weigh up**Trailmark Summary's SKILL.md declares allowed-tools Bash, Read, Grep and Glob, with no Write.

 Source reviewed

5 sources · 2026-10-22

[Read the full review ↗](/skills/trailofbits-trailmark-summary/) Upstream setup linked CC-BY-SA-4.0
 Compare Trailmark Summary Add

Security review · Trail of Bits

### [Trailmark Variant Neighborhood](/skills/trailofbits-trailmark-variant-neighborhood/)

Expands one confirmed or suspected vulnerability into a Trailmark graph neighborhood of variant candidates — siblings, shared callers and callees, common sinks, common entrypoint paths, interface implementations and overrides — then ranks them for follow-up.

 variant-analysis triage graph

**Why we selected it**Expands one confirmed issue into a graph neighborhood of variants: shared callers and callees, sinks, entrypoint-path neighbours, interface and override siblings, and taint or boundary peers.

**Weigh up**Trailmark Variant Neighborhood's SKILL.md declares allowed-tools that include Write; it writes a handoff packet (references/output-format.md).

 Source reviewed

5 sources · 2026-10-22

[Read the full review ↗](/skills/trailofbits-trailmark-variant-neighborhood/) Upstream setup linked CC-BY-SA-4.0
 Compare Trailmark Variant Neighborhood Add

Machine learning · huggingface

### [TRL Training API](/skills/huggingface-trl-training/)

Select TRL trainers and dataset shapes, then configure SFT or online preference/reward training in Python or the CLI.

 machine-learning huggingface

**Why we selected it**It maps each stable TRL trainer to a dataset shape and says the chat template is applied by the library.

**Weigh up**The skill does not launch a training job.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/huggingface-trl-training/) Install command in review Apache-2.0
 Compare TRL Training API Add

Data engineering · dbt-labs

### [Troubleshoot dbt Platform Jobs](/skills/dbt-labs-troubleshooting-dbt-job-errors/)

Diagnose failed platform runs from scoped run logs, node artifacts and source history.

 data-engineering dbt-labs

**Why we selected it**It diagnoses dbt platform job failures from run logs and the Admin API, and it forbids changing a test just to make it pass.

**Weigh up**The skill is not for local dbt development errors.

 Source reviewed

4 sources · 2026-10-15

[Read the full review ↗](/skills/dbt-labs-troubleshooting-dbt-job-errors/) Install command in review Apache-2.0
 Compare Troubleshoot dbt Platform Jobs Add

Languages and tooling · JetBrains

### [Turborepo](/skills/jetbrains-turborepo/)

Monorepo build-system discipline for Turborepo: package tasks instead of root tasks, turbo.json task registration, cache outputs and hashing inputs, environment variables as cache keys, --affected runs, CI setup, and tag-based package boundaries.

 turborepo monorepo turbo-json

**Why we selected it**Leads with the mistake every Turborepo setup makes — task logic in the root package.json — and shows the correct package-scripts plus turbo.json registration as wrong/right code pairs, including why root tasks defeat parallelization.

**Weigh up**Pinned to the vendored snapshot of Turborepo 2.8.18-canary.7 (synced 2026-03-16); Turborepo releases quickly and flag or boundaries behaviour may drift from newer versions.

 Source reviewed

10 sources · 2026-10-13

[Read the full review ↗](/skills/jetbrains-turborepo/) Install command in review MIT (skill-local, Vercel copyright)
 Compare Turborepo Add

Databases · Turso

### [Turso Database](/skills/tursodatabase-turso-db/)

Turso's skill for its in-process SQLite-compatible engine: hard constraints first, then decision trees to feature and SDK reference files, plus CLI, SQL and MCP quick references.

 sqlite sql vector-search

**Why we selected it**States ten constraints before any code is written: BETA status, single-process file access, no WITHOUT ROWID tables, no VACUUM, UTF-8 only, WAL as the default journal mode with the legacy delete, truncate and persist modes unsupported, full-text search behind a compile-time feature, encryption behind a flag, experimental MVCC, and lower-is-closer vector distance.

**Weigh up**The skill directory skills/turso-db last changed in a commit dated 2026-03-25 (git log at the pin); the pinned revision 34ced52f is dated 2026-07-22.

 Source reviewed

4 sources · 2026-10-21

[Read the full review ↗](/skills/tursodatabase-turso-db/) Upstream setup linked MIT
 Compare Turso Database Add

Evidence and evaluation · Undominated.ai

### [Undominated · 2-bit activation outlier audit](/skills/undominated-2bit-activation-outlier-audit/)

Audits 2-bit weight quantization (QuIP#, AQLM) activation outlier preservation and SQNR thresholds.

 serving 2-bit quantization

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates measured SQNR against acceptable signal limits; does not compute matrix inversions.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-2bit-activation-outlier-audit/) Attributed definition available MIT
 Compare Undominated · 2-bit activation outlier audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · A dev POST keeps its slash](/skills/undominated-slash-not-post/)

Refuse a dev POST path with no trailing slash. trailingSlash always 404s that path in dev. Production is a different path shape.

 trailing-slash dev post

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**A production path without a slash can pass. This checker sends no request.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-slash-not-post/) Attributed definition available MIT
 Compare Undominated · A dev POST keeps its slash Add

Evidence and evaluation · Undominated.ai

### [Undominated · A load return is not the catalogue](/skills/undominated-load-not-catalogue/)

Refuse a load() return labelled catalogue. The catalogue is imported by the page. Putting it in the load return inlines it into every prerendered page.

 pages catalogue prerender

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**The label is caller-supplied. A pass does not read a page.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-load-not-catalogue/) Attributed definition available MIT
 Compare Undominated · A load return is not the catalogue Add

Evidence and evaluation · Undominated.ai

### [Undominated · A marginal block is not priced](/skills/undominated-marginal-not-whole/)

Refuse a marginal-block bill. A whole request uses the rate of the rung that contains its input length. This checker does not price either mode.

 pricing context billing

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**No amount is read. A whole-request label can pass, and the checker still does not price it.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-marginal-not-whole/) Attributed definition available MIT
 Compare Undominated · A marginal block is not priced Add

Evidence and evaluation · Undominated.ai

### [Undominated · A missing announcement is not safe](/skills/undominated-announced-not-safe/)

Refuse a safety claim built from none-announced, unknown, or unrated. Those labels do not establish that a subject is safe.

 safety labels claims

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**The result never sets established to true. A false or null claim stays unestablished. No source is fetched.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-announced-not-safe/) Attributed definition available MIT
 Compare Undominated · A missing announcement is not safe Add

Evidence and evaluation · Undominated.ai

### [Undominated · A models list is not a chat call](/skills/undominated-models-list-not-chat/)

Refuse a claim that chat works because /v1/models returned the id. A list is not a completion. This checker sends no request.

 models chat nim

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**The result never says chat was established. Another evidence label can pass and does not prove a completion.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-models-list-not-chat/) Attributed definition available MIT
 Compare Undominated · A models list is not a chat call Add

Evidence and evaluation · Undominated.ai

### [Undominated · A prompt is not the catalogue](/skills/undominated-topk-not-dump/)

Refuse a prompt whose scope is the whole catalogue. Retrieval stays top-k. No catalogue is copied.

 prompt catalogue retrieval

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**A top-k scope can pass. This checker does not count rows or read the catalogue.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-topk-not-dump/) Attributed definition available MIT
 Compare Undominated · A prompt is not the catalogue Add

Evidence and evaluation · Undominated.ai

### [Undominated · A query is not a passage](/skills/undominated-query-not-passage/)

Refuse an embedding call whose input_type does not match the role. A query and a passage are different requests. No vector is computed.

 embeddings query passage

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Matching query or matching passage can pass. No text is embedded.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-query-not-passage/) Attributed definition available MIT
 Compare Undominated · A query is not a passage Add

Evidence and evaluation · Undominated.ai

### [Undominated · A rollback is not the baseline](/skills/undominated-rollback-not-baseline/)

Refuse to record a rolled-back or unproven deploy as the accepted baseline. The baseline advances only after a deploy has proven good.

 deploy baseline rollback

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**This checker does not contact a host. A pass on a supplied proven outcome does not prove the deploy.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-rollback-not-baseline/) Attributed definition available MIT
 Compare Undominated · A rollback is not the baseline Add

Evidence and evaluation · Undominated.ai

### [Undominated · A token is not PUBLIC_](/skills/undominated-public-not-secret/)

Refuse a provider token in a PUBLIC_ variable or in browser code. A server environment is outside this refusal and is not approved by a pass.

 secrets browser public-prefix

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**A server environment can pass. A pass does not approve the file the token lives in.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-public-not-secret/) Attributed definition available MIT
 Compare Undominated · A token is not PUBLIC_ Add

Evidence and evaluation · Undominated.ai

### [Undominated · A zero base is not defined](/skills/undominated-zero-base-undefined/)

Refuse a multiple whose base is zero. The multiple is not defined. This checker does not emit a quotient.

 pricing multiple base

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**A positive base can pass, and the result still does not define the multiple. Amounts are not a field.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-zero-base-undefined/) Attributed definition available MIT
 Compare Undominated · A zero base is not defined Add

Evidence and evaluation · Undominated.ai

### [Undominated · Activation Recomputation Tax Audit](/skills/undominated-activation-recomputation-tax-audit/)

Audits selective vs full gradient checkpointing memory savings vs compute FLOP taxes for long-context prefill.

 checkpointing recomputation vram

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Calculates theoretical FLOP addition based on attention and MLP re-forwarding.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-activation-recomputation-tax-audit/) Attributed definition available MIT
 Compare Undominated · Activation Recomputation Tax Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Adversarial suffix detection audit](/skills/undominated-adversarial-suffix-detection-audit/)

Checks a supplied perplexity-ratio assertion and anomaly threshold over local numeric input; a flag is a heuristic signal for review, not proof of an attack.

 evaluation security jailbreak

**Why we selected it**Pairs a bounded numeric audit with an offline Python checker and an explicitly synthetic threshold-breach example.

**Weigh up**Does not measure perplexity, inspect prompts, execute a target model or establish detector accuracy. Input provenance and threshold suitability remain unverified; attack_detected means only that the unrounded ratio exceeded the supplied threshold.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-adversarial-suffix-detection-audit/) Attributed definition available MIT
 Compare Undominated · Adversarial suffix detection audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Advertised-route audit](/skills/undominated-advertised-route/)

Refuse a crawl-list URL whose English-only path gained a locale prefix, or whose ?format=md sibling was never written.

 seo crawl locale

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Checks a supplied URL list against a supplied relative file list. It does not read a build directory, fetch URLs, or treat a present file as correct content. Locale codes are two letters and English-only paths must be listed exactly.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-advertised-route/) Attributed definition available MIT
 Compare Undominated · Advertised-route audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Agent consensus cost audit](/skills/undominated-agent-consensus-cost-audit/)

Audits token costs and accuracy ROI of multi-agent consensus, majority voting, and debate protocols.

 pricing consensus majority-voting

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates accuracy deltas against cost multipliers; does not conduct voting rounds.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-agent-consensus-cost-audit/) Attributed definition available MIT
 Compare Undominated · Agent consensus cost audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Agent trajectory cost audit](/skills/undominated-agent-trajectory-cost-audit/)

Audit multi-turn agent execution loops for quadratic token accumulation, retry loops, tool call overhead, and cumulative trajectory dollar costs.

 agents trajectory cost

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Calculates costs from supplied turn token counts; does not execute multi-step agent actions.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-agent-trajectory-cost-audit/) Attributed definition available MIT
 Compare Undominated · Agent trajectory cost audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · AI resource intake audit](/skills/undominated-resource-audit/)

Review a skill, agent or MCP server for pinned source identity, licensing, requested permissions and observable verification before adding it to a trusted collection.

 skills agents mcp

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic local checks over supplied evidence; not a guarantee of source truth or production suitability.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-resource-audit/) Install command in review MIT
 Compare Undominated · AI resource intake audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Air-Gapped Inference Economics Audit](/skills/undominated-airgapped-inference-audit/)

Calculates on-premise hardware CapEx amortization, rack power, and hosting TCO per 1M tokens to verify self-hosting economic viability.

 air-gapped sovereign tco

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic financial amortization model. Requires explicit electricity and CapEx inputs.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-airgapped-inference-audit/) Attributed definition available MIT
 Compare Undominated · Air-Gapped Inference Economics Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Alias resolution](/skills/undominated-alias-resolution/)

Resolve an explicitly supplied alias to one distinct concrete target, refusing unresolved or conflicting candidate evidence. Use before treating a latest-style pointer as a concrete model ID.

 identity alias catalogue

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Checks one caller-supplied candidate set, refusing unresolved, conflicting and self-targets. It does not verify target existence, candidate completeness, recency or recursively resolve aliases.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/skills/undominated-alias-resolution/) Install command in review MIT
 Compare Undominated · Alias resolution Add

Evidence and evaluation · Undominated.ai

### [Undominated · An add_header keeps the snippet](/skills/undominated-snippet-not-inherited/)

Refuse an nginx location that sets add_header without the shared header snippet. add_header in a location discards inherited headers.

 nginx headers snippet

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**A location that sets no header can pass. This checker does not read an nginx file.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-snippet-not-inherited/) Attributed definition available MIT
 Compare Undominated · An add_header keeps the snippet Add

Evidence and evaluation · Undominated.ai

### [Undominated · Apple unified memory bandwidth audit](/skills/undominated-apple-unified-memory-bandwidth-audit/)

Audits Apple Silicon unified memory bandwidth utilization and token generation throughput efficiency.

 serving apple-silicon metal

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Calculates theoretical memory bandwidth utilization; does not profile Metal shaders directly.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-apple-unified-memory-bandwidth-audit/) Attributed definition available MIT
 Compare Undominated · Apple unified memory bandwidth audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · arena.ai is not scraped](/skills/undominated-arena-not-scrape/)

Refuse an arena.ai scrape. The Hugging Face dataset pin can pass. Any other origin can pass and is not approved.

 arena licence huggingface

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**A Hugging Face dataset label can pass. This checker does not fetch either origin.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-arena-not-scrape/) Attributed definition available MIT
 Compare Undominated · arena.ai is not scraped Add

Evidence and evaluation · Undominated.ai

### [Undominated · Artificial Analysis is not republished](/skills/undominated-aa-not-public/)

Refuse redistribution of Artificial Analysis. A pass for any other source does not approve that source. No series is copied.

 licensing redistribution artificial-analysis

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Leaving it unreprinted can pass. Another source can pass and is not approved.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-aa-not-public/) Attributed definition available MIT
 Compare Undominated · Artificial Analysis is not republished Add

Evidence and evaluation · Undominated.ai

### [Undominated · ASCII art jailbreak evasion audit](/skills/undominated-ascii-art-jailbreak-evasion-audit/)

Audits ASCII art spatial obfuscation and safety alignment bypass resistance in prompt inputs.

 evaluation security ascii-art

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates observed character dispersion and safety classifier scores; does not modify prompt tokens.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-ascii-art-jailbreak-evasion-audit/) Attributed definition available MIT
 Compare Undominated · ASCII art jailbreak evasion audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Audio streaming chunk latency audit](/skills/undominated-audio-streaming-chunk-latency-audit/)

Audits continuous audio streaming inference chunk sizes and Real-Time Factor (RTF) latency bounds.

 serving audio streaming

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Calculates RTF ratios based on chunk durations; does not process PCM audio streams.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-audio-streaming-chunk-latency-audit/) Attributed definition available MIT
 Compare Undominated · Audio streaming chunk latency audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Auto Prompt Distillation Audit](/skills/undominated-auto-prompt-distillation-audit/)

Calculates prompt instruction compression efficiency and downstream task execution fidelity.

 distillation prompt-compaction efficiency

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates token ratio and automated verification test pass rate.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-auto-prompt-distillation-audit/) Attributed definition available MIT
 Compare Undominated · Auto Prompt Distillation Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Batch discount audit](/skills/undominated-batch-discount-audit/)

Audit batch API SLA windows, advertised vs realized discounts, queue starvation risk, and cancellation policies.

 batch pricing discounts

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Checks pricing rate cards and declared turnaround windows; does not submit live asynchronous batch jobs.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-batch-discount-audit/) Attributed definition available MIT
 Compare Undominated · Batch discount audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Batch Queue Starvation Risk Audit](/skills/undominated-batch-queue-starvation-risk-audit/)

Calculates batch queue processing delays and verifies turnaround compliance against provider SLA deadlines.

 batch-api queue-starvation sla

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates queue entry to completion timestamps.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-batch-queue-starvation-risk-audit/) Attributed definition available MIT
 Compare Undominated · Batch Queue Starvation Risk Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Benchmark cohort audit](/skills/undominated-benchmark-audit/)

Audit a benchmark comparison for matched model identity, missing coverage, restricted populations and misleading confidence-interval interpretations.

 benchmarks statistics coverage

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic local checks over supplied evidence; not a guarantee of source truth or production suitability.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-benchmark-audit/) Install command in review MIT
 Compare Undominated · Benchmark cohort audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Bidirectional speculative audit](/skills/undominated-bidirectional-speculative-audit/)

Audits bidirectional speculative drafting hit rates during structured JSON and schema generation.

 serving structured-outputs speculative

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Calculates grammar hit ratios; does not compile context-free grammars directly.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-bidirectional-speculative-audit/) Attributed definition available MIT
 Compare Undominated · Bidirectional speculative audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · BitNet ternary weight audit](/skills/undominated-bitnet-ternary-weight-audit/)

Audits BitNet b1.58 ternary weight representation and addition-only kernel energy reduction factors.

 serving bitnet ternary

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates observed energy reduction factors; does not synthesize CUDA assembly directly.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-bitnet-ternary-weight-audit/) Attributed definition available MIT
 Compare Undominated · BitNet ternary weight audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Browser code does not name loopback](/skills/undominated-loopback-not-browser/)

Refuse a browser script that names 127.0.0.1. That address is the visitor's machine. A server-side sidecar may name it.

 browser loopback sidecar

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Server-side code may name loopback. This checker does not fetch the page.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-loopback-not-browser/) Attributed definition available MIT
 Compare Undominated · Browser code does not name loopback Add

Evidence and evaluation · Undominated.ai

### [Undominated · Burst Concurrency & Queue Degradation Audit](/skills/undominated-burst-concurrency-audit/)

Evaluates queue buffering latency and HTTP 429/503 drop rates under sudden burst step-load profiles.

 concurrency load-testing sla

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Load profiles must simulate realistic client traffic patterns with appropriate timeout limits.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-burst-concurrency-audit/) Attributed definition available MIT
 Compare Undominated · Burst Concurrency & Queue Degradation Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Cache multiplier](/skills/undominated-cache-multiplier/)

Keep a cache figure that is a multiplier distinct from an absolute rate.

 pricing cache units

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Does not convert a multiplier into a vendor rate.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-cache-multiplier/) Attributed definition available MIT
 Compare Undominated · Cache multiplier Add

Evidence and evaluation · Undominated.ai

### [Undominated · Cache-tier billing audit](/skills/undominated-cache-tier-billing/)

Bill a request against the cache tier that applies to it, so a cached prefix is not charged at the base input rate.

 pricing caching billing

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic local arithmetic for one request against one supplied rate set; it does not walk a context-tier ladder or apply batch, off-peak or subscription billing rules.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-cache-tier-billing/) Attributed definition available MIT
 Compare Undominated · Cache-tier billing audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Canary Deployment Drift Audit](/skills/undominated-canary-deployment-drift-audit/)

Calculates statistical output distribution divergence (PSI/KS-test) between stable baseline and canary model deployments.

 canary distribution-shift psi

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates Population Stability Index (PSI) metrics across token length and embedding features.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-canary-deployment-drift-audit/) Attributed definition available MIT
 Compare Undominated · Canary Deployment Drift Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Carbon intensity scheduling audit](/skills/undominated-carbon-intensity-scheduling-audit/)

Audits grid carbon intensity temporal variations to schedule batch inference during green energy peaks.

 pricing carbon green-energy

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Calculates carbon savings from historical grid carbon intensity metrics; does not control job schedulers.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-carbon-intensity-scheduling-audit/) Attributed definition available MIT
 Compare Undominated · Carbon intensity scheduling audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Chunked Prefill Scheduler Audit](/skills/undominated-chunked-prefill-scheduler-audit/)

Calibrates chunked prefill chunk sizes to eliminate inter-token latency (ITL) spikes while preserving prefill throughput.

 chunked-prefill itl-jitter vllm

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates observed ITL jitter and prefill chunk size constraints.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-chunked-prefill-scheduler-audit/) Attributed definition available MIT
 Compare Undominated · Chunked Prefill Scheduler Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · CI/CD Regression Gate Audit](/skills/undominated-ci-cd-regression-gate-audit/)

Automated deployment gate: enforces strict latency, output schema validity, and accuracy thresholds in CI/CD pipelines.

 ci-cd regression-gate automated-deploy

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic pass/fail gate over test evaluation suite outputs.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-ci-cd-regression-gate-audit/) Attributed definition available MIT
 Compare Undominated · CI/CD Regression Gate Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Concurrency cliff audit](/skills/undominated-concurrency-cliff-audit/)

Audit inference throughput degradation, queue build-up, and throughput cliff saturation as concurrency scales.

 concurrency throughput saturation

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Analyzes benchmarked throughput matrix; does not launch concurrent load testing clusters.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-concurrency-cliff-audit/) Attributed definition available MIT
 Compare Undominated · Concurrency cliff audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Context compaction audit](/skills/undominated-context-compaction-audit/)

Audit conversational context compaction, summarization, and message pruning for named entity retention, critical fact loss, and semantic distortion.

 context compaction summarization

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Performs exact string and entity verification; does not generate text summaries.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-context-compaction-audit/) Attributed definition available MIT
 Compare Undominated · Context compaction audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Context-rung selection](/skills/undominated-rung-select/)

Select the context-tier rung that contains a request's input length, so the dearest later rung is not applied to a shorter prompt.

 pricing context tiers

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Selects one whole-request rung from a supplied ladder. It does not model marginal block pricing or fetch vendor rates.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-rung-select/) Attributed definition available MIT
 Compare Undominated · Context-rung selection Add

Evidence and evaluation · Undominated.ai

### [Undominated · Context-tier ladder audit](/skills/undominated-context-tier/)

Check a past-this-length price multiple against every rung, so the dearest rung is not applied at the first boundary.

 pricing context tiers

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic local check of a supplied ladder; it does not fetch vendor prices or model marginal block billing.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/skills/undominated-context-tier/) Install command in review MIT
 Compare Undominated · Context-tier ladder audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Continuous Batching Scheduler Audit](/skills/undominated-continuous-batching-scheduler-audit/)

Audits iteration-level scheduling vs static request batching to verify throughput gains and elimination of tail-latency bubble waste.

 continuous-batching scheduler orca

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Empirical model based on measured throughput and sequence length variance.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-continuous-batching-scheduler-audit/) Attributed definition available MIT
 Compare Undominated · Continuous Batching Scheduler Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Cross modal KV allocation audit](/skills/undominated-cross-modal-kv-allocation-audit/)

Audits visual token versus text token KV cache allocation ratios in long multimodal conversations.

 serving multimodal kv-cache

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Verifies total VRAM footprint across modality caches; does not compute attention weights.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-cross-modal-kv-allocation-audit/) Attributed definition available MIT
 Compare Undominated · Cross modal KV allocation audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Currency isolation audit](/skills/undominated-currency-isolate/)

Refuse to add, average or rank amounts whose currencies differ, so a missing code is not treated as USD and no exchange rate is invented.

 pricing currency totals

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic isolation of supplied amounts. It does not convert currencies or fetch an exchange rate.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-currency-isolate/) Attributed definition available MIT
 Compare Undominated · Currency isolation audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · DARE random drop rescale audit](/skills/undominated-dare-random-drop-rescale-audit/)

Audits DARE (Drop And REscale) random drop rate and benchmark capability retention across merged models.

 evaluation dare model-merging

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates reported benchmark retention rates under selected drop probabilities; does not perform weight arithmetic.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-dare-random-drop-rescale-audit/) Attributed definition available MIT
 Compare Undominated · DARE random drop rescale audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Datacenter power envelope audit](/skills/undominated-datacenter-power-envelope-audit/)

Audits datacenter rack power density, cooling overhead, and PUE compliance under 100% GPU duty cycles.

 pricing datacenter power

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Calculates total power draw from IT load and PUE coefficients; does not measure physical current.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-datacenter-power-envelope-audit/) Attributed definition available MIT
 Compare Undominated · Datacenter power envelope audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Decimal determinism audit](/skills/undominated-decimal-determinism/)

Prove a published rate, a computed bill and a displayed figure agree to the last digit, so no displayed decimal comes from IEEE-754.

 decimal precision pricing

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic decimal recomputation over supplied rates, quantity and billed values; it does not fetch vendor prices or judge display formatting.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-decimal-determinism/) Attributed definition available MIT
 Compare Undominated · Decimal determinism audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Delivery class](/skills/undominated-delivery-class/)

Refuse a dominance claim that treats batch delivery, or a model's own other delivery, as a like-for-like beater of synchronous delivery.

 delivery batch dominance

**Why we selected it**It refuses a dominance claim that treats batch delivery, or the same weights on another delivery, as a like-for-like beater of synchronous delivery.

**Weigh up**The checker does not read prices, scores, or context.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-delivery-class/) Attributed definition available MIT
 Compare Undominated · Delivery class Add

Evidence and evaluation · Undominated.ai

### [Undominated · DGX SuperPOD TCO Audit](/skills/undominated-dgx-superpod-tco-audit/)

Calculates enterprise GPU cluster Total Cost of Ownership including InfiniBand fabrics, power usage effectiveness (PUE), and rack hosting.

 superpod tco dgx

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic financial amortization and utility model.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-dgx-superpod-tco-audit/) Attributed definition available MIT
 Compare Undominated · DGX SuperPOD TCO Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Do not scale the invoice unit](/skills/undominated-unit-not-scaled/)

Refuse a scale factor or a restated invoice unit. A per-thousand row is not turned into a per-million row by multiplying. Amounts are not read.

 pricing units invoice

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**A factor is not applied and is not copied out. Amounts are not a field of this checker.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-unit-not-scaled/) Attributed definition available MIT
 Compare Undominated · Do not scale the invoice unit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Dominance wording audit](/skills/undominated-dominance-wording/)

Classify a two-model comparison before publishing it, so a tie or a dropped requirement is not called both better and cheaper.

 dominance wording capabilities

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic local checks over one supplied pair and the listed requirements; not a guarantee of source truth.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/skills/undominated-dominance-wording/) Install command in review MIT
 Compare Undominated · Dominance wording audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Dynamic Spot Rate Arbitrage Audit](/skills/undominated-dynamic-spot-rate-arbitrage-audit/)

Calculates real-time price arbitrage across multi-provider spot inference endpoints under strict latency SLOs.

 spot-arbitrage routing pricing

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates observed rate cards and achieved dollar savings.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-dynamic-spot-rate-arbitrage-audit/) Attributed definition available MIT
 Compare Undominated · Dynamic Spot Rate Arbitrage Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Dynamic Tool Filtering Tax Audit](/skills/undominated-dynamic-tool-filtering-tax-audit/)

Calculates token savings achieved by dynamically retrieving relevant tools into context vs sending static tool catalogs.

 tool-filter prompt-tokens dynamic-tools

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates observed token reduction ratios.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-dynamic-tool-filtering-tax-audit/) Attributed definition available MIT
 Compare Undominated · Dynamic Tool Filtering Tax Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Eagle-2 dynamic draft tree audit](/skills/undominated-eagle2-dynamic-draft-tree-audit/)

Audits Eagle-2 dynamic draft tree pruning and net token throughput multipliers.

 serving eagle-2 speculative-tree

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates observed tree acceptance statistics; does not execute tree verification kernels.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-eagle2-dynamic-draft-tree-audit/) Attributed definition available MIT
 Compare Undominated · Eagle-2 dynamic draft tree audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Elo drift audit](/skills/undominated-elo-drift-audit/)

Audit Bradley-Terry win-rate confidence interval bounds, active pair sampling bias, and Elo deflation/inflation drift across benchmark dataset versions.

 elo benchmarks statistics

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Computes statistical significance over supplied benchmark rating snapshots; does not compute Elo from raw battle votes.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-elo-drift-audit/) Attributed definition available MIT
 Compare Undominated · Elo drift audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Embodied silicon carbon TCO audit](/skills/undominated-embodied-silicon-carbon-tco-audit/)

Audits embodied carbon in GPU manufacturing (Scope 3) amortized per 1 billion inference tokens.

 pricing embodied-carbon scope3

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Calculates amortized Scope 3 grams per 1M tokens based on device lifetime and volume; does not audit fabs.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-embodied-silicon-carbon-tco-audit/) Attributed definition available MIT
 Compare Undominated · Embodied silicon carbon TCO audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Equal is not better](/skills/undominated-equal-not-better/)

Refuse to call an equal score or an equal price an improvement.

 comparisons ties wording

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Does not rank a catalogue.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-equal-not-better/) Attributed definition available MIT
 Compare Undominated · Equal is not better Add

Evidence and evaluation · Undominated.ai

### [Undominated · EU AI Act Transparency Audit](/skills/undominated-eu-ai-act-transparency-audit/)

Checks four supplier declarations in a local JSON file: training compute, copyright summary, energy log, and model card. A true declaration is not an EU AI Act determination.

 eu-ai-act transparency compliance

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**A pass means each supplied declaration is true. It is not a legal determination and it does not inspect a model card, a paper, or a regulator's file.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-eu-ai-act-transparency-audit/) Attributed definition available MIT
 Compare Undominated · EU AI Act Transparency Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Eval contamination and judge audit](/skills/undominated-eval-contamination-audit/)

Audit benchmark evaluation sets and prompts for training set contamination, n-gram overlap, verbatim memorization, and judge prompt skew.

 contamination benchmarks ngrams

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic text overlap and statistical correlation over supplied samples; does not crawl external web corpora.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-eval-contamination-audit/) Attributed definition available MIT
 Compare Undominated · Eval contamination and judge audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Evidence audit](/skills/undominated-evidence-audit/)

Audit a numeric claim against locally saved source evidence, including denominator and reproducible calculations, before citing or publishing it.

 evidence provenance claims

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic local checks over supplied evidence; not a guarantee of source truth or production suitability.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-evidence-audit/) Install command in review MIT
 Compare Undominated · Evidence audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · False-Positive Refusal Rate Audit](/skills/undominated-false-refusal-rate-audit/)

Quantifies false-positive refusal rates on benign software engineering, cybersecurity, and clinical research queries.

 safety refusals over-refusal

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Test datasets must exclude genuinely dangerous dual-use materials to measure true false positives.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-false-refusal-rate-audit/) Attributed definition available MIT
 Compare Undominated · False-Positive Refusal Rate Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Family snapshot](/skills/undominated-family-snapshot/)

Require family membership to be a subset of the catalogue snapshot.

 families snapshots identity

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Does not infer family membership from names.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-family-snapshot/) Attributed definition available MIT
 Compare Undominated · Family snapshot Add

Evidence and evaluation · Undominated.ai

### [Undominated · Few-Shot Example Pruning Audit](/skills/undominated-few-shot-example-pruning-audit/)

Calculates the marginal accuracy contribution per few-shot exemplar to eliminate low-ROI prompt tokens.

 few-shot exemplars pruning

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates observed benchmark accuracy across example subset ablations.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-few-shot-example-pruning-audit/) Attributed definition available MIT
 Compare Undominated · Few-Shot Example Pruning Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Filter invariance](/skills/undominated-filter-invariance/)

Check that filtering preserves the relative order of retained IDs. Use for search or facet behavior that is intended to hide rows without re-sorting them.

 ranking filters population

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Checks one supplied ordered population and subsequence, including empty arrays. It does not check scores, numeric ranks, frontier membership or dominance labels.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/skills/undominated-filter-invariance/) Install command in review MIT
 Compare Undominated · Filter invariance Add

Evidence and evaluation · Undominated.ai

### [Undominated · Final-host audit](/skills/undominated-final-host/)

Refuse a vendor quote when the final host you recorded is not the host you requested. A redirect is not that vendor. www is not stripped, and this checker sends no request.

 provenance pricing audit

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Compares the two host strings you supply. It does not send a request, read a body, or strip www. A pass is not a rate card.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/skills/undominated-final-host/) Install command in review MIT
 Compare Undominated · Final-host audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Final-path audit](/skills/undominated-final-path/)

Refuse a page claim when the final path you recorded is not the path you requested. A redirect to the homepage is not that page. The host is a different checker, and this one sends no request.

 provenance pricing audit

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Checks recorded path strings in a narrow ASCII subset. It rejects whitespace, doubled leading slashes, URLs, queries, fragments and dot segments; it does not fetch, compare hosts, decode percent escapes, or verify page content.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/skills/undominated-final-path/) Install command in review MIT
 Compare Undominated · Final-path audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · FP4 E2M1 microscaling audit](/skills/undominated-fp4-e2m1-microscaling-audit/)

Audits OCP Microscaling Formats (MXFP4 / E2M1) block scaling factors and perplexity degradation delta.

 serving fp4 e2m1

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Verifies reported perplexity differentials on standard evaluation benchmarks; does not perform forward passes.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-fp4-e2m1-microscaling-audit/) Attributed definition available MIT
 Compare Undominated · FP4 E2M1 microscaling audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · FP4 Quantization Noise Audit](/skills/undominated-fp4-quantization-noise-audit/)

Calculates Signal-to-Quantization-Noise Ratio (SQNR) and verifies perplexity degradation across FP4 / NVFP4 tensor formats.

 fp4 nvfp4 sqnr

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates observed SQNR and benchmark scores. Does not calibrate activation clipping.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-fp4-quantization-noise-audit/) Attributed definition available MIT
 Compare Undominated · FP4 Quantization Noise Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Generated artefacts stay uncommitted](/skills/undominated-generated-not-commit/)

Refuse a commit path the caller has classified as generated. Source can pass. A pass does not prove the path is source.

 git generated artefacts

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**A source label can pass and does not prove the path. This checker does not list the tree.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-generated-not-commit/) Attributed definition available MIT
 Compare Undominated · Generated artefacts stay uncommitted Add

Evidence and evaluation · Undominated.ai

### [Undominated · GPU Underutilization Cost Audit](/skills/undominated-gpu-underutilization-cost-audit/)

Calculates financial penalties of reserved GPU instances operating under low continuous utilization factors.

 underutilization idle-power reserved-instances

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates utilization duty cycles and contractual hourly rates.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-gpu-underutilization-cost-audit/) Attributed definition available MIT
 Compare Undominated · GPU Underutilization Cost Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Graph RAG Extraction Tax Audit](/skills/undominated-graph-rag-extraction-tax-audit/)

Calculates entity-relationship extraction token overhead and graph construction costs compared to vector retrieval.

 graph-rag knowledge-graph extraction-tax

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates prompt token inflation for entity and relationship triples extraction.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-graph-rag-extraction-tax-audit/) Attributed definition available MIT
 Compare Undominated · Graph RAG Extraction Tax Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Guardrail Latency Overhead Audit](/skills/undominated-guardrail-latency-tax-audit/)

Measures the TTFT penalty and token inflation imposed by input and output safety moderation guardrail layers.

 guardrails safety ttft

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Measures synchronous guardrail configurations; asynchronous streaming guardrails require separate event analysis.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-guardrail-latency-tax-audit/) Attributed definition available MIT
 Compare Undominated · Guardrail Latency Overhead Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · H2O heavy hitter eviction audit](/skills/undominated-h2o-heavy-hitter-eviction-audit/)

Audits Heavy Hitter Oracle (H2O) KV cache eviction and critical prompt token retention under memory limits.

 serving h2o kv-cache

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates observed accuracy retention under selected token budgets; does not generate prompt responses.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-h2o-heavy-hitter-eviction-audit/) Attributed definition available MIT
 Compare Undominated · H2O heavy hitter eviction audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Header-not-row audit](/skills/undominated-header-not-row/)

Refuse a unit claim that borrows the table's display header when that row does not state its own unit. A per-million header is not every row's invoice unit. Amounts are not read.

 pricing meter audit

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**The header is ignored. rowUnit has to come from that row's own sentence, or be null. It does not read amounts or convert units. A pass is not a vendor quote.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-header-not-row/) Install command in review MIT
 Compare Undominated · Header-not-row audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Hierarchical Memory Consolidation Audit](/skills/undominated-hierarchical-memory-consolidation-audit/)

Audits episodic-to-semantic memory compaction token costs in long-horizon autonomous agents.

 agent-memory consolidation episodic-memory

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates compression ratio and preservation flags.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-hierarchical-memory-consolidation-audit/) Attributed definition available MIT
 Compare Undominated · Hierarchical Memory Consolidation Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Hint versus handler](/skills/undominated-hint-vs-handler/)

Refuse a read-only hint when the handler notes you supply include a write, or when those notes are empty. A hint is not a review of the handler.

 mcp permissions read-only

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Checks supplied operation names against a true read-only hint. It does not read tool names, open a handler, or start a server. A pass is not proof the server is read-only.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-hint-vs-handler/) Attributed definition available MIT
 Compare Undominated · Hint versus handler Add

Evidence and evaluation · Undominated.ai

### [Undominated · HTTP/2 Multiplexing & Head-of-Line Audit](/skills/undominated-http2-multiplexing-audit/)

Measures TTFT variance and head-of-line blocking under HTTP/2 multiplexing vs HTTP/1.1 connection pools under high stream concurrency.

 http2 multiplexing ttft

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**HTTP/2 stream prioritization may vary depending on intermediary reverse proxy configurations.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-http2-multiplexing-audit/) Attributed definition available MIT
 Compare Undominated · HTTP/2 Multiplexing & Head-of-Line Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Hybrid transformer SSM memory audit](/skills/undominated-hybrid-transformer-ssm-memory-audit/)

Audits memory footprint and KV cache allocation in hybrid models combining attention and Mamba layers.

 serving hybrid jamba

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Calculates layer-wise memory allocations; assumes linear recurrent state sizes.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-hybrid-transformer-ssm-memory-audit/) Attributed definition available MIT
 Compare Undominated · Hybrid transformer SSM memory audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Identity dedup audit](/skills/undominated-identity-dedup/)

Collapse duplicate identities inside one population before ranking, so one model or one seller cannot be counted twice.

 deduplication identity denominators

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic local check over supplied rows and caller-normalised identities; it does not resolve upstream aliases or verify provenance.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-identity-dedup/) Attributed definition available MIT
 Compare Undominated · Identity dedup audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Indicative-rate audit](/skills/undominated-indicative-rate/)

Refuse a global-rate claim when the excerpt says the figure is indicative, varies by country, starts at a floor, or is a list price beside a credit. One sentence is not every region's rate.

 pricing region audit

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Looks for qualifying wording in the excerpt you supply. Negation is not parsed. It does not read amounts or pick a country. A pass is not a vendor quote.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-indicative-rate/) Install command in review MIT
 Compare Undominated · Indicative-rate audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Indirect Prompt Injection Detector](/skills/undominated-indirect-prompt-injection-detector/)

Audits model vulnerability to untrusted prompt injections embedded in retrieved RAG contexts and web documents.

 indirect-injection rag-security data-poisoning

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates detection and mitigation rates across indirect injection test corpora.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-indirect-prompt-injection-detector/) Attributed definition available MIT
 Compare Undominated · Indirect Prompt Injection Detector Add

Evidence and evaluation · Undominated.ai

### [Undominated · Install receipt](/skills/undominated-install-receipt/)

Compare an expected file manifest with a sha256sum receipt and, when asked, the bytes in a directory next to the input.

 install integrity sha256

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Hashes only the files named inside the input directory. A pass is not evidence that npm or the Skills CLI performed the install.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-install-receipt/) Attributed definition available MIT
 Compare Undominated · Install receipt Add

Evidence and evaluation · Undominated.ai

### [Undominated · IP Infringement Verbatim Memorization Audit](/skills/undominated-ip-infringement-verbatim-audit/)

Measures verbatim memorization rates of copyrighted code and text corpora in model completion outputs.

 copyright memorization ip-risk

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates 50-token exact match n-gram overlap against protected corpora.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-ip-infringement-verbatim-audit/) Attributed definition available MIT
 Compare Undominated · IP Infringement Verbatim Memorization Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · JSON Schema Constrained Decoding Tax Audit](/skills/undominated-json-schema-constrained-decoding-tax-audit/)

Measures token generation throughput penalty and grammar compilation overhead incurred by FSM-constrained decoding engines.

 structured-output json-schema constrained-decoding

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates measured TPS and initial compilation time. Schema-dependent regex parsing overhead.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-json-schema-constrained-decoding-tax-audit/) Attributed definition available MIT
 Compare Undominated · JSON Schema Constrained Decoding Tax Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Judge Prompt Variance Audit](/skills/undominated-judge-prompt-variance-audit/)

Measures LLM-as-a-judge score variance, position bias, and length preference bias across automated evaluation runs.

 llm-judge position-bias eval-variance

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates observed pairwise swaps and position agreement scores.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-judge-prompt-variance-audit/) Attributed definition available MIT
 Compare Undominated · Judge Prompt Variance Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Keep every ladder rung](/skills/undominated-ladder-not-flattened/)

Refuse a published context-tier ladder whose rung count differs from the source. Dropping a rung flattens the ladder. Adding a rung invents one. Prices and boundaries are not read.

 pricing context ladder

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Prices and boundaries are not read. A matching count does not say the boundaries are right.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-ladder-not-flattened/) Attributed definition available MIT
 Compare Undominated · Keep every ladder rung Add

Evidence and evaluation · Undominated.ai

### [Undominated · KV Cache INT4 Outlier Drift Audit](/skills/undominated-kv-cache-int4-outlier-drift-audit/)

Audits key/value cache INT4 quantization channel scaling to prevent catastrophic attention drift on long sequences.

 int4 kv-cache outliers

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Audits maximum absolute error across attention logit distributions.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-kv-cache-int4-outlier-drift-audit/) Attributed definition available MIT
 Compare Undominated · KV Cache INT4 Outlier Drift Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · KV Cache Memory Sizing Audit](/skills/undominated-kv-cache-sizing-audit/)

Audits KV cache memory footprint per token and max concurrent sequence limits under FP16, FP8, and INT4 KV caches to prevent serving OOMs.

 kv-cache vram hardware

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Hardware memory models assume standard Multi-Head Attention (MHA) or Grouped-Query Attention (GQA). Verify key-value head counts explicitly.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-kv-cache-sizing-audit/) Attributed definition available MIT
 Compare Undominated · KV Cache Memory Sizing Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · KV Transfer RDMA Bandwidth Audit](/skills/undominated-kv-transfer-rdma-bandwidth-audit/)

Calculates RDMA network saturation and link concurrency during high-throughput KV cache migration.

 rdma kv-cache network

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates theoretical link saturation based on concurrent migration sessions.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-kv-transfer-rdma-bandwidth-audit/) Attributed definition available MIT
 Compare Undominated · KV Transfer RDMA Bandwidth Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Length bias audit](/skills/undominated-length-bias-audit/)

Audit length bias (verbosity bias) in LLM-as-a-judge evaluations and preference datasets, detecting artificial win-rate inflation.

 evaluations bias llm-judge

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic analysis of battle length deltas and outcomes; does not re-score answers independently.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-length-bias-audit/) Attributed definition available MIT
 Compare Undominated · Length bias audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Length bias removal audit](/skills/undominated-length-bias-removal-audit/)

Audits reward model length bias and synthetic response verbosity inflation in preference datasets.

 evaluation dpo rlhf

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Calculates Pearson/Spearman correlation between length and reward; does not train reward models.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-length-bias-removal-audit/) Attributed definition available MIT
 Compare Undominated · Length bias removal audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Licence-boundary audit](/skills/undominated-licence-boundary/)

Check a redistribution claim against the licence evidence you recorded. A public page is not a licence.

 licensing redistribution attribution

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic consistency check of a filled licence note; it does not interpret licence text or fetch the licence.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/skills/undominated-licence-boundary/) Install command in review MIT
 Compare Undominated · Licence-boundary audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Linear Attention Recurrent State Audit](/skills/undominated-linear-attention-recurrent-state-audit/)

Verifies $O(1)$ constant memory scaling of recurrent and state-space architectures during generation versus Transformer attention.

 mamba rwkv linear-attention

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Pure mathematical verification of recurrent hidden state tensor volume.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-linear-attention-recurrent-state-audit/) Attributed definition available MIT
 Compare Undominated · Linear Attention Recurrent State Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Live Benchmark Drift Detector](/skills/undominated-live-benchmark-drift-detector/)

Detects silent provider model weight updates, quant modifications, and temperature drift across production endpoints.

 drift-detector model-drift regression

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates statistical score deltas against historical baseline confidence intervals.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-live-benchmark-drift-detector/) Attributed definition available MIT
 Compare Undominated · Live Benchmark Drift Detector Add

Evidence and evaluation · Undominated.ai

### [Undominated · Locale is not content](/skills/undominated-locale-not-content/)

Refuse a translated label as proof that the page body is translated.

 i18n claims locale

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Does not translate anything.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-locale-not-content/) Attributed definition available MIT
 Compare Undominated · Locale is not content Add

Evidence and evaluation · Undominated.ai

### [Undominated · Long-Context Distraction Audit](/skills/undominated-context-distraction-audit/)

Audits retrieval accuracy degradation as irrelevant distractor documents are added to prompts (evaluating signal-to-noise ratio in long contexts).

 long-context distraction retrieval

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Distractor documents must share lexical domain similarity with target needles to detect realistic confusion.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-context-distraction-audit/) Attributed definition available MIT
 Compare Undominated · Long-Context Distraction Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Lookahead decoding n-gram audit](/skills/undominated-lookahead-decoding-n-gram-audit/)

Audits Lookahead Decoding parallel Jacobi n-gram candidate generation and net wall-clock speedup.

 serving lookahead-decoding speculative

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Profiles acceptance rates and wall-clock multipliers; does not generate token trajectories.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-lookahead-decoding-n-gram-audit/) Attributed definition available MIT
 Compare Undominated · Lookahead decoding n-gram audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Loopback needs curl --resolve](/skills/undominated-resolve-not-host-header/)

Refuse a Host header pointed at loopback. That request sends no SNI and hits the default server. curl --resolve can pass.

 nginx sni loopback

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**curl --resolve can pass. A pass for a named host does not send the request.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-resolve-not-host-header/) Attributed definition available MIT
 Compare Undominated · Loopback needs curl --resolve Add

Evidence and evaluation · Undominated.ai

### [Undominated · LoRA Cache Swapping Latency Audit](/skills/undominated-lora-cache-swapping-latency-audit/)

Audits dynamic LoRA adapter loading latency from host system memory to GPU VRAM.

 lora swapping pcie

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates measured adapter transfer latency across PCIe.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-lora-cache-swapping-latency-audit/) Attributed definition available MIT
 Compare Undominated · LoRA Cache Swapping Latency Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Mamba-2 SSD chunk audit](/skills/undominated-mamba2-ssd-chunk-audit/)

Audits Mamba-2 Structured State Space Duality (SSD) matrix chunk sizes and continuous decoding throughput.

 serving mamba-2 ssm

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Profiles token throughput at given SSD chunk configurations; does not retrain state matrices.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-mamba2-ssd-chunk-audit/) Attributed definition available MIT
 Compare Undominated · Mamba-2 SSD chunk audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Many-Shot Jailbreak Resilience Audit](/skills/undominated-many-shot-jailbreak-resilience-audit/)

Evaluates model safety adherence under long-context many-shot in-prompt jailbreak demonstrations.

 many-shot jailbreak adversarial

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates refusal accuracy on adversarial benchmark suites.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-many-shot-jailbreak-resilience-audit/) Attributed definition available MIT
 Compare Undominated · Many-Shot Jailbreak Resilience Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · master is not force-pushed](/skills/undominated-force-not-master/)

Refuse a force push whose branch is master. Another branch is outside this refusal, and a pass does not approve the force push.

 git force-push master

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**A non-force push can pass. A pass for another branch does not approve a force push.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-force-not-master/) Attributed definition available MIT
 Compare Undominated · master is not force-pushed Add

Evidence and evaluation · Undominated.ai

### [Undominated · MCP permission map](/skills/undominated-mcp-permission-map/)

Bind a saved MCP tools/list capture to explicit permission labels and reject a read-only claim that a label contradicts.

 mcp permissions tools

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Compares human labels with the capture. It does not start the server or infer permissions from descriptions.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-mcp-permission-map/) Attributed definition available MIT
 Compare Undominated · MCP permission map Add

Evidence and evaluation · Undominated.ai

### [Undominated · Meter-scope audit](/skills/undominated-meter-scope/)

Refuse a unit claim that borrows an invoice unit from a note that does not name that meter, so a knowledge-base billing sentence cannot reprice an inference row.

 pricing units meters

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Checks supplied meter names and allowlisted unit strings. It does not fetch a page, convert units, or read amounts. A pass is not a vendor quote.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-meter-scope/) Attributed definition available MIT
 Compare Undominated · Meter-scope audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Mixed Precision Layer Allocation Audit](/skills/undominated-mixed-precision-layer-allocation-audit/)

Audits selective high-precision preservation on sensitive initial and final layers versus bulk quantized middle layers.

 mixed-precision layer-allocation fp16

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic parameter weighted average bit calculation.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-mixed-precision-layer-allocation-audit/) Attributed definition available MIT
 Compare Undominated · Mixed Precision Layer Allocation Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Model card transparency audit](/skills/undominated-model-card-transparency-audit/)

Audit model card releases against the Foundation Model Transparency Index, checking documentation completeness across pre-training data, compute hours, and limitations.

 transparency model-cards governance

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Checks presence of documented transparency indicators; does not verify independent accuracy of training data logs.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-model-card-transparency-audit/) Attributed definition available MIT
 Compare Undominated · Model card transparency audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Model Cascade Routing Audit](/skills/undominated-cascade-routing-audit/)

Audits 2-tier cascading routing policies (small draft model with confidence gate to frontier verifier), calculating net cost savings and escalation ratios.

 cascade routing arbitrage

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Resolution rates must be calibrated on representative domain evaluation splits.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-cascade-routing-audit/) Attributed definition available MIT
 Compare Undominated · Model Cascade Routing Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Model Distillation Fidelity Audit](/skills/undominated-distillation-fidelity-audit/)

Measures task accuracy retention and output distribution alignment of distilled student models relative to teacher models.

 distillation fidelity teacher-student

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluation benchmarks must be out-of-distribution relative to student fine-tuning training datasets.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-distillation-fidelity-audit/) Attributed definition available MIT
 Compare Undominated · Model Distillation Fidelity Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Model Merge Interference Audit](/skills/undominated-model-merge-interference-audit/)

Measures weight interference and cosine similarity degradation in spherical linear interpolation (SLERP) model merges.

 model-merge slerp interference

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates layer cosine similarity bounds.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-model-merge-interference-audit/) Attributed definition available MIT
 Compare Undominated · Model Merge Interference Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Model migration preflight](/skills/undominated-migration-preflight/)

Check a proposed model replacement for required modalities, context, tool use, structured output and evaluation coverage before calling it a safe saving.

 models migration compatibility

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic local checks over supplied evidence; not a guarantee of source truth or production suitability.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-migration-preflight/) Install command in review MIT
 Compare Undominated · Model migration preflight Add

Evidence and evaluation · Undominated.ai

### [Undominated · MoE Activation Memory Footprint Audit](/skills/undominated-moe-activation-memory-footprint-audit/)

Calculates active versus total parameter memory footprint and expert weight swapping overhead on constrained GPU nodes.

 moe memory vram

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic memory sizing. Assumes steady-state layer distribution.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-moe-activation-memory-footprint-audit/) Attributed definition available MIT
 Compare Undominated · MoE Activation Memory Footprint Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · MoE Expert Parallelism All-to-All Audit](/skills/undominated-moe-ep-all-to-all-comm-audit/)

Calculates All-to-All collective dispatch and combine communication overhead across nodes in Expert Parallel (EP) clusters.

 moe expert-parallelism all-to-all

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates ring/pairwise All-to-All collective equations.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-moe-ep-all-to-all-comm-audit/) Attributed definition available MIT
 Compare Undominated · MoE Expert Parallelism All-to-All Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · MoE Expert Routing Tax Audit](/skills/undominated-moe-expert-routing-tax-audit/)

Audits top-k gating entropy, expert load distribution, and token drop rates under finite expert capacity factors.

 moe mixture-of-experts gating

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates observed routing frequencies and capacity factors. Does not modify router logits.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-moe-expert-routing-tax-audit/) Attributed definition available MIT
 Compare Undominated · MoE Expert Routing Tax Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Multi-agent error cascade audit](/skills/undominated-multi-agent-error-cascade-audit/)

Audits error compounding probability across sequential multi-agent tool execution pipelines.

 evaluation multi-agent error-cascade

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Computes joint failure probability based on observed step error rates; does not execute agent tool steps.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-multi-agent-error-cascade-audit/) Attributed definition available MIT
 Compare Undominated · Multi-agent error cascade audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Multi-Head Latent Attention Audit](/skills/undominated-mla-latent-dimension-audit/)

Calculates DeepSeek Multi-Head Latent Attention (MLA) low-rank compression factors and verifies KV cache reduction relative to MHA and GQA.

 mla deepseek attention

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Pure mathematical verification of KV projection tensor sizes and per-token memory footprint.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-mla-latent-dimension-audit/) Attributed definition available MIT
 Compare Undominated · Multi-Head Latent Attention Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Multi-LoRA Kernel Overhead Audit](/skills/undominated-multi-lora-kernel-overhead-audit/)

Measures batched multi-adapter GPU kernel overhead (S-LoRA) versus single-model inference throughput.

 lora s-lora multi-tenant

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates measured throughput compared to pure base model baseline.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-multi-lora-kernel-overhead-audit/) Attributed definition available MIT
 Compare Undominated · Multi-LoRA Kernel Overhead Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Multi-Token Prediction Speedup Audit](/skills/undominated-multi-token-prediction-speedup-audit/)

Calculates acceptance rate thresholds and net speedup of Multi-Token Prediction (MTP) heads vs standard autoregression.

 mtp multi-token-prediction speculative

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates observed acceptance rate and head compute cost.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-multi-token-prediction-speedup-audit/) Attributed definition available MIT
 Compare Undominated · Multi-Token Prediction Speedup Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Multi-Turn State Drift Audit](/skills/undominated-multi-turn-state-drift-audit/)

Calculates cumulative token inflation and prefill cost scaling across multi-turn agent conversations to verify context compaction policies.

 multi-turn context-compaction state-drift

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates cumulative turn sums and compacted history savings.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-multi-turn-state-drift-audit/) Attributed definition available MIT
 Compare Undominated · Multi-Turn State Drift Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Multilingual Retrieval Parity Audit](/skills/undominated-multilingual-retrieval-audit/)

Audits cross-lingual embedding alignment and retrieval recall parity across high- and low-resource languages.

 multilingual embeddings retrieval

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Benchmark queries must be human-curated and idiomatic in the target locale.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-multilingual-retrieval-audit/) Attributed definition available MIT
 Compare Undominated · Multilingual Retrieval Parity Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Multiplier-aside audit](/skills/undominated-multiplier-aside/)

Refuse a base-rate claim when the excerpt names a multiplier. Priority, fast, and scale factors are not the on-demand rate. The number in 2x is not read as a price.

 pricing multiplier audit

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Looks for multiplier wording in the excerpt you supply. Negation is not parsed. It does not read amounts or apply a factor. A pass is not a vendor quote.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/skills/undominated-multiplier-aside/) Install command in review MIT
 Compare Undominated · Multiplier-aside audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Native Sparse Attention Audit](/skills/undominated-native-sparse-attention-audit/)

Audits Native Sparse Attention (NSA) compression ratios, block-sparse top-k selection, and memory bandwidth reduction.

 nsa sparse-attention native-sparse

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates block-sparse index selection math. Does not train sparse kernels.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-native-sparse-attention-audit/) Attributed definition available MIT
 Compare Undominated · Native Sparse Attention Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Needle-in-a-haystack density audit](/skills/undominated-needle-in-haystack-density-audit/)

Audit long-context retrieval recall across varying context lengths, needle depth placements, and distractor similarity levels.

 retrieval long-context needle-in-haystack

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Analyzes supplied retrieval test results; does not execute long-context inference runs.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-needle-in-haystack-density-audit/) Attributed definition available MIT
 Compare Undominated · Needle-in-a-haystack density audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · nginx is reloaded, not restarted](/skills/undominated-reload-not-restart/)

Refuse an nginx restart. A reload is review until nginx -t has succeeded. This checker does not run nginx.

 nginx reload restart

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**A tested reload can pass. This checker does not run nginx or reload a host.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-reload-not-restart/) Attributed definition available MIT
 Compare Undominated · nginx is reloaded, not restarted Add

Evidence and evaluation · Undominated.ai

### [Undominated · NPU INT8 TPU offload audit](/skills/undominated-npu-int8-tpu-offload-audit/)

Audits mobile NPU and edge accelerator power efficiency measured in Tokens per Joule.

 serving npu edge

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Calculates Tokens per Joule metrics; does not interface with hardware power meters.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-npu-int8-tpu-offload-audit/) Attributed definition available MIT
 Compare Undominated · NPU INT8 TPU offload audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Offer join](/skills/undominated-offer-join/)

Refuse a price that does not name both the model and the seller.

 pricing identity offers

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Does not fetch a price.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-offer-join/) Attributed definition available MIT
 Compare Undominated · Offer join Add

Evidence and evaluation · Undominated.ai

### [Undominated · Open-weights licence audit](/skills/undominated-open-weights-licence-audit/)

Audit open-weights model licenses against commercial deployment restrictions, Monthly Active User thresholds, synthetic data output constraints, and attribution requirements.

 licensing open-weights compliance

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Technical license boundary check; does not constitute formal legal counsel.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-open-weights-licence-audit/) Attributed definition available MIT
 Compare Undominated · Open-weights licence audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · P99.9 tail latency budget audit](/skills/undominated-p999-tail-latency-budget-audit/)

Audits tail latency distribution ratios (p99.9 / p50) to detect micro-stalls and jitter in production serving.

 serving tail-latency p999

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Calculates percentile ratio bounds from reported latency summaries; does not record live request times.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-p999-tail-latency-budget-audit/) Attributed definition available MIT
 Compare Undominated · P99.9 tail latency budget audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Page is not a quote](/skills/undominated-page-not-quote/)

Keep a pricing-page research note from becoming a joined rate. A spelled currency and unit are not a price.

 pricing provenance word-bar

**Why we selected it**It keeps a fetched pricing page from becoming a joined rate: a spelled currency and unit are not a price.

**Weigh up**This check does not decide whether a provider publishes prices. A failed fetch is not that finding either.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-page-not-quote/) Attributed definition available MIT
 Compare Undominated · Page is not a quote Add

Evidence and evaluation · Undominated.ai

### [Undominated · Parallel Tool Call Fan-Out Audit](/skills/undominated-parallel-tool-call-fanout-audit/)

Calculates concurrency speedup and total payload token loads for simultaneous multi-tool execution in agent loops.

 tool-call parallelism fan-out

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates observed tool execution latencies and serial sum comparisons.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-parallel-tool-call-fanout-audit/) Attributed definition available MIT
 Compare Undominated · Parallel Tool Call Fan-Out Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Payback basis](/skills/undominated-payback-basis/)

Check switching-cost payback against savings per period using exact arithmetic. Use when a migration claims to pay back in a stated number of periods.

 cost migration arithmetic

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Exact savings-based arithmetic only; repeating results remain rational pairs. Currency and period alignment, taxes, timing, discounting and source truth are not verified.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/skills/undominated-payback-basis/) Install command in review MIT
 Compare Undominated · Payback basis Add

Evidence and evaluation · Undominated.ai

### [Undominated · PII Scrubbing Latency Tax Audit](/skills/undominated-pii-scrubbing-latency-tax-audit/)

Measures token count shifts and millisecond pre-inference latency added by NER-based redaction and token replacement pipelines.

 pii privacy redaction

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates deterministic byte and token drift metrics. Does not judge NER classification precision.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-pii-scrubbing-latency-tax-audit/) Attributed definition available MIT
 Compare Undominated · PII Scrubbing Latency Tax Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Pipeline parallelism bubble audit](/skills/undominated-pipeline-parallelism-bubble-audit/)

Audits pipeline schedule bubble fraction and microbatch allocation in 1F1B schedules.

 serving parallelism pipeline-parallel

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Calculates 1F1B bubble fraction based on microbatch counts; assumes uniform stage execution latency.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-pipeline-parallelism-bubble-audit/) Attributed definition available MIT
 Compare Undominated · Pipeline parallelism bubble audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Plan-quote hygiene](/skills/undominated-plan-quote/)

Keep unverified subscription quotes out of a USD monthly ceiling. A source sentence is not a price.

 plans quotes currency

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic local checks over a supplied plan table; not a guarantee that a vendor page still matches.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/skills/undominated-plan-quote/) Install command in review MIT
 Compare Undominated · Plan-quote hygiene Add

Evidence and evaluation · Undominated.ai

### [Undominated · Population denominator](/skills/undominated-population-denominator/)

Require a stated population, a computed population and a claimed count to be the same set, so a statistic on a subset is not published as the whole set.

 denominators population claims

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Set equality over supplied membership flags. It does not compute a correlation, a price or a rank.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-population-denominator/) Attributed definition available MIT
 Compare Undominated · Population denominator Add

Evidence and evaluation · Undominated.ai

### [Undominated · Population scope](/skills/undominated-population-scope/)

Check that a claimed count uses the population the sentence names.

 population claims denominators

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Does not recompute a market statistic.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-population-scope/) Attributed definition available MIT
 Compare Undominated · Population scope Add

Evidence and evaluation · Undominated.ai

### [Undominated · Precision prompt cost estimator](/skills/undominated-prompt-cost-estimator/)

Calculate inference costs across prompt tokens, completion tokens, cached prompt tokens (read/write), reasoning tokens, and multi-turn trajectories using explicit provider pricing ladders.

 pricing tokens prompt-caching

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic decimal calculations over supplied token counts and pricing ladders; does not model network egress or batch discounts.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-prompt-cost-estimator/) Attributed definition available MIT
 Compare Undominated · Precision prompt cost estimator Add

Evidence and evaluation · Undominated.ai

### [Undominated · Prefill-Decode Disaggregation Audit](/skills/undominated-prefill-decode-disaggregation-audit/)

Audits separate prefill and decode worker node topologies and calculates RDMA KV transfer latency vs GPU compute overlap.

 disaggregation prefill-decode rdma

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates RDMA network transfer bandwidth vs compute overlap bounds.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-prefill-decode-disaggregation-audit/) Attributed definition available MIT
 Compare Undominated · Prefill-Decode Disaggregation Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Prefix Caching Radix Tree Audit](/skills/undominated-prefix-caching-radix-audit/)

Audits Radix tree prefix caching efficiency, memory allocation, cache hit rate, and effective TTFT reduction to prevent latency degradation under memory pressure.

 prefix-caching radix-tree vllm

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Assumes deterministic prompt prefix sharing. Does not simulate dynamic sequence eviction under memory fragmentation.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-prefix-caching-radix-audit/) Attributed definition available MIT
 Compare Undominated · Prefix Caching Radix Tree Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Process reward model tax audit](/skills/undominated-process-reward-model-tax-audit/)

Audits Process Reward Model (PRM) step-level verification token overhead versus outcome accuracy gains.

 evaluation prm reward-model

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates observed benchmark differentials and token counts; does not execute reward models.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-process-reward-model-tax-audit/) Attributed definition available MIT
 Compare Undominated · Process reward model tax audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Prompt Extraction & Leakage Resilience Audit](/skills/undominated-prompt-leakage-resilience-audit/)

Evaluates system prompt confidentiality retention under adversarial prompt extraction and reconstruction attacks.

 prompt-leakage jailbreak security

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**System prompts containing sensitive credentials violate security policies; never store secrets in prompts.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-prompt-leakage-resilience-audit/) Attributed definition available MIT
 Compare Undominated · Prompt Extraction & Leakage Resilience Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Prompt Injection Classifier Tax Audit](/skills/undominated-prompt-injection-classifier-tax-audit/)

Quantifies TTFT latency inflation and false-positive rejection rates of pre-flight security moderation guardrails.

 prompt-injection jailbreak security-classifier

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates observed classifier latency and measured false positive rates across benchmark datasets.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-prompt-injection-classifier-tax-audit/) Attributed definition available MIT
 Compare Undominated · Prompt Injection Classifier Tax Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Provider Failover Latency Tax Audit](/skills/undominated-provider-failover-latency-tax-audit/)

Measures circuit breaker timeouts, retry amplification, and failover latency tax during upstream provider outages.

 failover circuit-breaker resilience

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates measured timeout windows and retry latency.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-provider-failover-latency-tax-audit/) Attributed definition available MIT
 Compare Undominated · Provider Failover Latency Tax Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Provider quote comparison](/skills/undominated-provider-quote-compare/)

Compare like-for-like provider quotes with complete context tiers and distinct sellers; recompute workload cost without inventing cache or reasoning discounts.

 pricing providers tier-ladders

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic local checks over supplied evidence; not a guarantee of source truth or production suitability.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-provider-quote-compare/) Install command in review MIT
 Compare Undominated · Provider quote comparison Add

Evidence and evaluation · Undominated.ai

### [Undominated · PyramidKV layer budget audit](/skills/undominated-pyramidkv-layer-budget-audit/)

Audits PyramidKV non-uniform layer cache allocations to verify total VRAM budget compliance.

 serving pyramidkv layer-allocation

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Verifies layer budget sums against hardware capacity limits; does not compute per-layer attention.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-pyramidkv-layer-budget-audit/) Attributed definition available MIT
 Compare Undominated · PyramidKV layer budget audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Quantisation label](/skills/undominated-quantisation-label/)

Keep an unknown quantisation labelled unknown, so a missing weight format is not published as full precision or fp16.

 quantisation models labels

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Label equality only. It does not inspect weights or translate aliases such as float16 and fp16.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-quantisation-label/) Attributed definition available MIT
 Compare Undominated · Quantisation label Add

Evidence and evaluation · Undominated.ai

### [Undominated · Quantization Degradation Audit](/skills/undominated-quant-degradation-audit/)

Audits perplexity and benchmark score degradation across quantization levels (BF16, FP8, INT4 AWQ, Q4_K_M) to prevent claiming unquantized performance for quantized serving.

 quantization benchmarks fp8

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Scores must derive from identical evaluation harness configurations and matching temperature.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-quant-degradation-audit/) Attributed definition available MIT
 Compare Undominated · Quantization Degradation Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Queue queuing theory audit](/skills/undominated-queue-queuing-theory-audit/)

Audits M/M/c queuing models under variable arrival rates to predict queue buildup before cluster saturation.

 serving queuing-theory mmc

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Calculates predicted queue wait times from arrival and service rates; does not execute HTTP traffic.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-queue-queuing-theory-audit/) Attributed definition available MIT
 Compare Undominated · Queue queuing theory audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Quote-join audit](/skills/undominated-quote-join/)

Join a vendor quote to a catalogue model only when the provider and the model id match exactly, so a case fold is not an identity.

 identity pricing join

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Exact string equality only. A join is not a quality, context, modality or price claim, and the checker does not apply an alias table.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-quote-join/) Attributed definition available MIT
 Compare Undominated · Quote-join audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · RAG Chunk Overlap Tax Audit](/skills/undominated-chunk-overlap-tax-audit/)

Calculates redundant token costs incurred by sliding-window chunk overlap in RAG ingestion and vector indexing pipelines.

 rag chunking vector-db

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Overlap reductions must be validated against retrieval boundary preservation.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-chunk-overlap-tax-audit/) Attributed definition available MIT
 Compare Undominated · RAG Chunk Overlap Tax Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Rate-unit audit](/skills/undominated-rate-unit/)

Refuse a token-price conversion until the currency and the unit are both explicit, so per M or a bare cent figure cannot become a per-million USD rate.

 pricing units currency

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic local conversion of supplied decimal strings; a scaled figure is not a new vendor quote and the checker does not guess that M means million.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-rate-unit/) Attributed definition available MIT
 Compare Undominated · Rate-unit audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Read-only claim audit](/skills/undominated-readonly-claim/)

Reject a read-only label when a listed tool name contains a mutation token, without treating a passing name list as proof the server is read-only.

 mcp permissions read-only

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Checks name tokens only. A pass is not proof the handlers are read-only, and a name outside the token list still needs the handler opened.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-readonly-claim/) Attributed definition available MIT
 Compare Undominated · Read-only claim audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · README is not a licence](/skills/undominated-readme-not-licence/)

Refuse a README sentence as a software licence.

 licensing redistribution readme

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Does not identify an SPDX licence from prose.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-readme-not-licence/) Attributed definition available MIT
 Compare Undominated · README is not a licence Add

Evidence and evaluation · Undominated.ai

### [Undominated · Reasoning Budget Allocator Audit](/skills/undominated-reasoning-budget-allocator/)

Audits dynamic reasoning token ceilings to prevent cyclical reasoning explosions while guaranteeing sufficient tokens for complex proofs.

 reasoning budget cot

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Verifies token envelope compliance and sentinel termination. Does not grade mathematical correctness of reasoning.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-reasoning-budget-allocator/) Attributed definition available MIT
 Compare Undominated · Reasoning Budget Allocator Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Reasoning token audit](/skills/undominated-reasoning-token-audit/)

Audit reasoning token expansion ratios, budget caps, separate billing vs output billing, and hidden multiplier surcharges across reasoning models.

 reasoning tokens pricing

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic local checks over supplied token counts; does not evaluate model reasoning depth or solution correctness.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-reasoning-token-audit/) Attributed definition available MIT
 Compare Undominated · Reasoning token audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Reasoning trace redundancy audit](/skills/undominated-reasoning-trace-redundancy-audit/)

Audits reasoning trace self-correction loops and verbosity redundancy to prune repetitive reflection tokens.

 evaluation reasoning verbosity

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates trace redundancy percentages and fidelity preservation; does not generate answers.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-reasoning-trace-redundancy-audit/) Attributed definition available MIT
 Compare Undominated · Reasoning trace redundancy audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Receipt drift](/skills/undominated-receipt-drift/)

Fail a verification receipt whose hashes no longer match the supplied bytes.

 receipts hashes verification

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Hashes only the bytes it is given.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-receipt-drift/) Attributed definition available MIT
 Compare Undominated · Receipt drift Add

Evidence and evaluation · Undominated.ai

### [Undominated · Rendered-surface and payload agreement](/skills/undominated-surface-agreement/)

Prove a rendered surface and the JSON it serves state the same value for every supplied field.

 agreement provenance payload

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Compares two supplied snapshots field by field; it does not fetch either surface, prove a release shipped both halves, or establish which side is correct.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-surface-agreement/) Attributed definition available MIT
 Compare Undominated · Rendered-surface and payload agreement Add

Evidence and evaluation · Undominated.ai

### [Undominated · Resource release proof](/skills/undominated-release-proof/)

Verify local release artifacts and meaningful public-response receipts without confusing a build, HTTP 200 or registry metadata with a working installation.

 releases verification distribution

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic local checks over supplied evidence; not a guarantee of source truth or production suitability.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-release-proof/) Install command in review MIT
 Compare Undominated · Resource release proof Add

Evidence and evaluation · Undominated.ai

### [Undominated · Restriction of range](/skills/undominated-restriction-of-range/)

Refuse a correlation or agreement claim whose evidence population is narrower than the population the sentence names.

 correlation population benchmarks

**Why we selected it**It refuses a correlation or agreement sentence whose evidence identifiers are a narrower population than the sentence names.

**Weigh up**Identity match is not evidence that two benchmarks agree.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-restriction-of-range/) Attributed definition available MIT
 Compare Undominated · Restriction of range Add

Evidence and evaluation · Undominated.ai

### [Undominated · Review-gate ratchet](/skills/undominated-ratchet-gate/)

Check that a review gate moved in one direction only, stricter and never looser, so an automated reviewer cannot weaken a check to pass a change.

 ratchet review gates

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic local check of one rule set against another; it does not edit a gate, judge whether the resulting severities are correct, or run the gate itself.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-ratchet-gate/) Attributed definition available MIT
 Compare Undominated · Review-gate ratchet Add

Evidence and evaluation · Undominated.ai

### [Undominated · Ring Attention Interconnect Audit](/skills/undominated-ring-attention-interconnect-audit/)

Verifies communication-to-computation overlap in block-wise Ring Attention across distributed sequence-parallel nodes.

 ring-attention sequence-parallel long-context

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates steady-state block pipelining. Does not model warmup or cooldown steps.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-ring-attention-interconnect-audit/) Attributed definition available MIT
 Compare Undominated · Ring Attention Interconnect Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Ring attention latency audit](/skills/undominated-ring-attention-latency-audit/)

Audits Ring Attention circular KV cache passing latency against block compute time in 1M+ context inference.

 serving ring-attention context-parallelism

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Profiles communication-to-compute ratio; does not modify CUDA streams.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-ring-attention-latency-audit/) Attributed definition available MIT
 Compare Undominated · Ring attention latency audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Ring MLA hybrid audit](/skills/undominated-ring-mla-hybrid-audit/)

Audits Ring Attention combined with Multi-Head Latent Attention (MLA) compressed latent states.

 serving mla ring-attention

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Calculates compression ratios of MLA latent projections; does not verify latent reconstruction loss.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-ring-mla-hybrid-audit/) Attributed definition available MIT
 Compare Undominated · Ring MLA hybrid audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · RWKV-6 linear state audit](/skills/undominated-rwkv6-linear-state-audit/)

Audits RWKV-6 linear recurrent state decay parameters and numerical stability across long token horizons.

 serving rwkv linear-attention

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates accumulated drift epsilon against tolerance limits; does not compute forward passes.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-rwkv6-linear-state-audit/) Attributed definition available MIT
 Compare Undominated · RWKV-6 linear state audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Schema Validation Retry Cost Audit](/skills/undominated-schema-validation-retry-cost-audit/)

Quantifies wasted token expenditures incurred by recursive error correction loops when models emit invalid tool parameters.

 validation-retry error-recovery token-waste

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates retry counts and token billing sums.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-schema-validation-retry-cost-audit/) Attributed definition available MIT
 Compare Undominated · Schema Validation Retry Cost Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Schema-not-quote audit](/skills/undominated-schema-not-quote/)

Refuse a model-rate claim when the excerpt describes a pricing field or a schema. A sentence that says values are in a unit is a field description, not a model's rate. Amounts are not read.

 pricing provenance audit

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Looks for schema phrases in the excerpt you supply. Negation is not parsed. It does not read amounts. A plain pass is not a vendor quote.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-schema-not-quote/) Install command in review MIT
 Compare Undominated · Schema-not-quote audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Self-Healing Prompt Optimizer Audit](/skills/undominated-self-healing-prompt-optimizer/)

Audits automated prompt refinement iterations to resolve edge-case test failures without human intervention.

 self-healing prompt-optimization automated-repair

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates iteration convergence count and test pass rates.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-self-healing-prompt-optimizer/) Attributed definition available MIT
 Compare Undominated · Self-Healing Prompt Optimizer Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Self-play distillation tax audit](/skills/undominated-self-play-distillation-tax-audit/)

Audits teacher-student self-play distillation token expenditure against student benchmark accuracy gains.

 pricing distillation self-play

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Calculates financial cost per benchmark point; does not execute training runs.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-self-play-distillation-tax-audit/) Attributed definition available MIT
 Compare Undominated · Self-play distillation tax audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Self-Speculative Early Exit Audit](/skills/undominated-self-speculative-early-exit-audit/)

Audits layer skipping and early exit draft verification within a single model architecture.

 early-exit self-speculative layer-skip

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates exit layer depth and accuracy retention.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-self-speculative-early-exit-audit/) Attributed definition available MIT
 Compare Undominated · Self-Speculative Early Exit Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Seller-spread audit](/skills/undominated-seller-spread/)

Check a price-spread multiple against distinct seller owners, so one vendor's own service tiers are not counted as competition.

 pricing sellers spread

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic local checks over supplied rows and caller-assigned seller owners; not a guarantee of source truth or market coverage.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/skills/undominated-seller-spread/) Install command in review MIT
 Compare Undominated · Seller-spread audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Semantic Prompt Pruning Audit](/skills/undominated-semantic-prompt-pruning-audit/)

Measures token reduction percentages and verifies mutual information retention in token pruning pipelines.

 prompt-pruning compression token-cost

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates observed token counts and task verification flags.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-semantic-prompt-pruning-audit/) Attributed definition available MIT
 Compare Undominated · Semantic Prompt Pruning Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Semantic Router Latency & Token Tax Audit](/skills/undominated-semantic-router-tax-audit/)

Quantifies embedding model latency and static classifier token taxes in semantic routing topologies prior to upstream generation.

 semantic-routing embedding latency

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Classifier embedding cache hit rates should be considered under repetitive query distributions.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-semantic-router-tax-audit/) Attributed definition available MIT
 Compare Undominated · Semantic Router Latency & Token Tax Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Sequence parallelism ring audit](/skills/undominated-sequence-parallelism-ring-audit/)

Audits sequence parallelism communication overhead across layernorms and attention projection.

 serving parallelism sequence-parallel

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates observed sequence communication latency; does not alter GPU kernel launch dispatch.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-sequence-parallelism-ring-audit/) Attributed definition available MIT
 Compare Undominated · Sequence parallelism ring audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Serving-mode attribution](/skills/undominated-serving-attribution/)

Check that an explicit claimed score belongs to its named model or serving mode. Use when a model headline may have inherited a mode-specific score.

 benchmark identity attribution

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Checks explicit claimedScore and named-subject equality only. It does not verify benchmark provenance, source truth or shared measurement conditions.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/skills/undominated-serving-attribution/) Install command in review MIT
 Compare Undominated · Serving-mode attribution Add

Evidence and evaluation · Undominated.ai

### [Undominated · Shared-lastmod audit](/skills/undominated-shared-lastmod/)

Refuse a crawl list where every page is dated on the build day, so a shared build clock is not published as a per-page fact date.

 seo sitemap lastmod

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Checks supplied dates only. One page dated on the build day can be a real change. A shared older day can be the day a record began. It does not fetch pages or decide which fact moved.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-shared-lastmod/) Attributed definition available MIT
 Compare Undominated · Shared-lastmod audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Significance tie](/skills/undominated-significance-tie/)

Treat two scores as tied when their difference falls inside the stated interval.

 scores intervals ties

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Does not invent an interval.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-significance-tie/) Attributed definition available MIT
 Compare Undominated · Significance tie Add

Evidence and evaluation · Undominated.ai

### [Undominated · Single-base audit](/skills/undominated-single-base/)

Refuse a single-base price claim when the excerpt names both sides of a cache split or a peak split. Spelling USD per million does not make cache-hit and cache-miss one rate.

 pricing cache schedule

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Checks two splits in the excerpt you supply. It does not fetch a page, read amounts, or decide which sentence is the invoice. Batch, region, and input-versus-output are outside this check. A pass is not a vendor quote.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-single-base/) Install command in review MIT
 Compare Undominated · Single-base audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Sliding Window Attention Audit](/skills/undominated-sliding-window-attention-audit/)

Audits sliding window context buffers and attention sink token retention to bound KV memory in continuous streaming.

 sliding-window attention-sink streaming

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates window buffer size and attention sink retention parameters.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-sliding-window-attention-audit/) Attributed definition available MIT
 Compare Undominated · Sliding Window Attention Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · SLO error budget depletion audit](/skills/undominated-slo-error-budget-depletion-audit/)

Audits 30-day Service Level Objective (SLO) error budget burn rates to trigger automated traffic shedding.

 serving slo error-budget

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Calculates multi-window burn rates from telemetry inputs; does not configure Prometheus alert rules.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-slo-error-budget-depletion-audit/) Attributed definition available MIT
 Compare Undominated · SLO error budget depletion audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Slug-is-not-body audit](/skills/undominated-slug-is-not-body/)

Refuse a currency or quantity claim whose words appear only in a URL, a slug, or a title. The excerpt is the body. A path named pricing-details-usd does not state USD.

 pricing provenance currency

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Reads the excerpt only. A locator is ignored. It does not fetch a page or read amounts. A pass is not a vendor quote.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-slug-is-not-body/) Install command in review MIT
 Compare Undominated · Slug-is-not-body audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · SnapKV cluster compression audit](/skills/undominated-snapkv-cluster-compression-audit/)

Audits SnapKV prompt attention feature clustering and compressed KV bank generation ratios.

 serving snapkv kv-cache

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Measures effective token compression ratios; does not evaluate clustering loss directly.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-snapkv-cluster-compression-audit/) Attributed definition available MIT
 Compare Undominated · SnapKV cluster compression audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Source-pin audit](/skills/undominated-source-pin/)

Refuse a source identity that is only a branch, a tag, or a short SHA. A full 40-hex revision is the pin. The name v7 or main does not become that revision.

 provenance revision audit

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Checks the revision string you supply. It does not fetch a repository, resolve a tag, or prove the tree was read. A pass is not a source review.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-source-pin/) Install command in review MIT
 Compare Undominated · Source-pin audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Speculative Decoding Arbitrage Audit](/skills/undominated-speculative-decoding-arbitrage/)

Computes draft model acceptance rate thresholds (alpha) and verifies whether speculative decoding delivers net throughput/cost benefit over standard autoregressive decoding.

 speculative-decoding throughput latency

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Acceptance rates vary significantly across coding, math, and conversational domains.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-speculative-decoding-arbitrage/) Attributed definition available MIT
 Compare Undominated · Speculative Decoding Arbitrage Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Spelled-meter audit](/skills/undominated-spelled-meter/)

Refuse a currency or quantity claim whose excerpt does not spell the word. A dollar sign is not USD, "per 1M" is not million, and the character 元 is not CNY.

 pricing currency units

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Checks words in the excerpt you supply. It does not fetch a page, read amounts, or decide which sentence is the rate. A pass is not a vendor quote.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-spelled-meter/) Attributed definition available MIT
 Compare Undominated · Spelled-meter audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Status-not-page audit](/skills/undominated-status-not-page/)

Check a supplied status against a conservative integer-200-only gate and refuse every quote claim based on status alone. No status proves a body was received or read. This checker sends no request.

 provenance pricing audit

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Checks a conservative status policy only. A 200 result is status-eligible; every other valid status needs review and every quote claim is refused. No status establishes that a response body was received or read; bodyVerified is always false.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/skills/undominated-status-not-page/) Install command in review MIT
 Compare Undominated · Status-not-page audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Stream Truncation & Sentinel Detector](/skills/undominated-stream-truncation-detector/)

Detects silent SSE connection drops in long-running streaming completions where no [DONE] sentinel or incomplete JSON chunk is emitted.

 streaming sse reliability

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Client implementations must buffer partial JSON frames across chunk boundaries.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-stream-truncation-detector/) Attributed definition available MIT
 Compare Undominated · Stream Truncation & Sentinel Detector Add

Evidence and evaluation · Undominated.ai

### [Undominated · Streaming framing audit](/skills/undominated-streaming-framing-audit/)

Audit Server-Sent Events (SSE) streaming protocol compliance, chunk serialization overhead, heartbeat keep-alive frequency, and terminal sentinel completeness.

 streaming sse protocol

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Audits recorded stream traces; does not open live TCP sockets.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-streaming-framing-audit/) Attributed definition available MIT
 Compare Undominated · Streaming framing audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · sudo does not read the script from stdin](/skills/undominated-sudo-not-stdin/)

Refuse sudo bash -s fed by a heredoc. That script is read as the password prompt. sudo -n bash -lc can pass.

 sudo ssh stdin

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**sudo -n bash -lc can pass. This checker does not open an SSH session.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-sudo-not-stdin/) Attributed definition available MIT
 Compare Undominated · sudo does not read the script from stdin Add

Evidence and evaluation · Undominated.ai

### [Undominated · Suggest, do not redirect](/skills/undominated-suggest-not-redirect/)

Refuse a language redirect, including when Accept-Language is absent. A missing header is not a request for another locale. Suggest, or do nothing.

 i18n redirect language

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**An absent header and a present header are both reviews when the action is redirect. The checker sends no request.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-suggest-not-redirect/) Attributed definition available MIT
 Compare Undominated · Suggest, do not redirect Add

Evidence and evaluation · Undominated.ai

### [Undominated · Synthetic data deduplication audit](/skills/undominated-synthetic-data-dedup-audit/)

Audits MinHash LSH and cosine clustering deduplication to prune repetitive synthetic training generations.

 evaluation synthetic-data deduplication

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Measures cluster diversity metrics and pruning ratios; does not train model checkpoints.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-synthetic-data-dedup-audit/) Attributed definition available MIT
 Compare Undominated · Synthetic data deduplication audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Synthetic Eval Diversity Audit](/skills/undominated-synthetic-eval-diversity-audit/)

Audits lexical and semantic diversity in synthetic evaluation sets to prevent test-set memorization and benchmark gaming.

 synthetic-eval diversity benchmark-gaming

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates pairwise n-gram overlap and embedding cosine dispersion.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-synthetic-eval-diversity-audit/) Attributed definition available MIT
 Compare Undominated · Synthetic Eval Diversity Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Synthetic Text Watermark Retention Audit](/skills/undominated-synthetic-text-watermark-retention-audit/)

Measures statistical green/red list token watermarking retention under editing, summarization, and paraphrasing.

 watermarking detection ai-provenance

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates green-token z-score significance thresholds.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-synthetic-text-watermark-retention-audit/) Attributed definition available MIT
 Compare Undominated · Synthetic Text Watermark Retention Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · System prompt extraction guard audit](/skills/undominated-system-prompt-extraction-guard-audit/)

Audits resistance against system prompt leakage attacks and multi-turn extraction attempts.

 evaluation security leakage

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates embedding similarity between candidate outputs and protected system prompts.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-system-prompt-extraction-guard-audit/) Attributed definition available MIT
 Compare Undominated · System prompt extraction guard audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · System Prompt Override Resilience Audit](/skills/undominated-system-prompt-override-resilience-audit/)

Measures system directive adherence under conflicting user instructions and adversarial persona hijacking.

 system-prompt override-attack persona-hijack

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates adherence rates on adversarial prompt override datasets.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-system-prompt-override-resilience-audit/) Attributed definition available MIT
 Compare Undominated · System Prompt Override Resilience Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Task vector orthogonality audit](/skills/undominated-task-vector-orthogonality-audit/)

Audits task vector pairwise cosine similarity to prevent subspace interference in multi-task checkpoints.

 evaluation task-vectors orthogonality

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Measures pairwise cosine similarity; does not compute forward passes.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-task-vector-orthogonality-audit/) Attributed definition available MIT
 Compare Undominated · Task vector orthogonality audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Tensor parallelism communication audit](/skills/undominated-tensor-parallelism-comm-audit/)

Audits Tensor Parallelism All-Reduce communication overhead against NVLink bus saturation.

 serving parallelism tensor-parallel

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Calculates theoretical vs measured All-Reduce communication bus times; does not modify NCCL rings directly.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-tensor-parallelism-comm-audit/) Attributed definition available MIT
 Compare Undominated · Tensor parallelism communication audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Tensor Parallelism Communication Tax Audit](/skills/undominated-tensor-parallelism-communication-tax-audit/)

Calculates All-Reduce collective communication volume and latency overhead across NVLink and PCIe interconnects to prevent negative TP scaling.

 tensor-parallelism all-reduce nvlink

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Models standard Ring All-Reduce collective communication. Does not simulate overlap with custom CUDA kernels.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-tensor-parallelism-communication-tax-audit/) Attributed definition available MIT
 Compare Undominated · Tensor Parallelism Communication Tax Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Test-Time Compute ROI Audit](/skills/undominated-test-time-compute-roi-audit/)

Calculates cost-per-accuracy return curves for Best-of-N sampling, search depth scaling, and verifier reranking vs base model upgrading.

 test-time-compute best-of-n verifier

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates candidate generation and verifier pricing. Assumes calibrated reward model ranking.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-test-time-compute-roi-audit/) Attributed definition available MIT
 Compare Undominated · Test-Time Compute ROI Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Test-time search budget audit](/skills/undominated-test-time-search-budget-audit/)

Audits test-time compute search budgets to ensure marginal accuracy gains justify token expenditure.

 evaluation reasoning test-time-compute

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates observed pass@k curves against token budgets; does not generate reasoning trees.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-test-time-search-budget-audit/) Attributed definition available MIT
 Compare Undominated · Test-time search budget audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Throughput benchmark audit](/skills/undominated-throughput-benchmark-audit/)

Audit throughput and latency claims (tokens/second, TTFT, concurrency, batch sizes) to ensure apples-to-apples comparisons and detect deceptive single-user vs batched measurements.

 throughput latency ttft

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic validation of supplied benchmark measurements; does not execute GPU benchmarks directly.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-throughput-benchmark-audit/) Attributed definition available MIT
 Compare Undominated · Throughput benchmark audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · TIES merging trim elect audit](/skills/undominated-ties-merging-trim-elect-audit/)

Audits TIES-Merging parameter trimming threshold and sign consensus across fine-tuned task vectors.

 evaluation model-merging ties-merging

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates parameter sign agreement ratios; does not perform checkpoint serialization.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-ties-merging-trim-elect-audit/) Attributed definition available MIT
 Compare Undominated · TIES merging trim elect audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Time-window rate](/skills/undominated-time-window/)

Refuse an off-peak rate published as the all-day rate.

 pricing windows claims

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Does not fetch vendor windows.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-time-window/) Attributed definition available MIT
 Compare Undominated · Time-window rate Add

Evidence and evaluation · Undominated.ai

### [Undominated · Token blowout circuit breaker audit](/skills/undominated-token-blowout-circuit-breaker-audit/)

Audits runaway loop detection and trips circuit breaker when token expenditures exceed budget ceilings.

 pricing circuit-breaker token-budget

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Verifies token expenditure thresholds; does not kill running remote API calls.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-token-blowout-circuit-breaker-audit/) Attributed definition available MIT
 Compare Undominated · Token blowout circuit breaker audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Tokenizer density audit](/skills/undominated-tokenizer-density-audit/)

Audit tokenizer vocabulary density, tokens-per-word / tokens-per-byte expansion ratios, and real effective text processing costs.

 tokenizers density arbitrage

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Calculations based on provided word and token counts for a benchmark corpus; not a tokenizer training tool.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-tokenizer-density-audit/) Attributed definition available MIT
 Compare Undominated · Tokenizer density audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Tool allowlist](/skills/undominated-tool-allowlist/)

Decide whether a saved MCP permission map fits a task allowlist. A consistent refusal is a pass, not an error to paper over.

 mcp allowlist tools

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Uses the labels already stored in the receipt. It does not call tools or widen the allowlist.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-tool-allowlist/) Attributed definition available MIT
 Compare Undominated · Tool allowlist Add

Evidence and evaluation · Undominated.ai

### [Undominated · Tool schema tax audit](/skills/undominated-tool-schema-tax-audit/)

Calculate the hidden static token overhead imposed by injecting JSON schema and OpenAPI tool definitions into prompt payloads on every turn.

 tools schemas overhead

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic calculation over schema token metrics; does not generate tool definitions.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-tool-schema-tax-audit/) Attributed definition available MIT
 Compare Undominated · Tool schema tax audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Tool Selection Recall Audit](/skills/undominated-tool-selection-recall-audit/)

Audits tool routing accuracy across large tool inventories and detects hallucinated function invocations.

 tool-selection function-calling recall

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates precision and recall on ground-truth benchmark intent datasets.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-tool-selection-recall-audit/) Attributed definition available MIT
 Compare Undominated · Tool Selection Recall Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Tree Speculative Decoding Audit](/skills/undominated-tree-speculative-decoding-audit/)

Evaluates tree-based draft candidate verification (Medusa/Eagle-2) to verify branch acceptance probabilities.

 tree-speculative medusa eagle

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates tree acceptance statistics across test runs.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-tree-speculative-decoding-audit/) Attributed definition available MIT
 Compare Undominated · Tree Speculative Decoding Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · TTFT jitter audit](/skills/undominated-ttft-jitter-audit/)

Audit Time-To-First-Token variance, queuing delays, cold-start penalization, and tail latency distributions (p50, p95, p99).

 latency ttft jitter

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Statistical analysis of supplied latency samples; does not execute live network ping probes.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-ttft-jitter-audit/) Attributed definition available MIT
 Compare Undominated · TTFT jitter audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Ulysses all-to-all bandwidth audit](/skills/undominated-ulysses-alltoall-bandwidth-audit/)

Audits DeepSpeed Ulysses All-to-All transpose communication overhead versus interconnect saturation.

 serving ulysses context-parallelism

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates observed All-to-All transpose times against interconnect capacity.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-ulysses-alltoall-bandwidth-audit/) Attributed definition available MIT
 Compare Undominated · Ulysses all-to-all bandwidth audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Unrated sentinel](/skills/undominated-unrated-sentinel/)

Keep a missing score out of a ranked list, so unrated is not scored zero and a scored row is not dropped in silence.

 ranking unrated scores

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic check of one supplied table. It does not fetch scores or decide that a measured zero is wrong.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-unrated-sentinel/) Attributed definition available MIT
 Compare Undominated · Unrated sentinel Add

Evidence and evaluation · Undominated.ai

### [Undominated · Upstream freshness budget](/skills/undominated-freshness-budget/)

Measure each upstream source against its own declared staleness budget, so a cache nobody refetched cannot pass for current.

 freshness cache provenance

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Deterministic local check over declared budgets and supplied fetch dates and content hashes; it does not fetch, refresh or validate the sources themselves.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-freshness-budget/) Attributed definition available MIT
 Compare Undominated · Upstream freshness budget Add

Evidence and evaluation · Undominated.ai

### [Undominated · Vector Reranking Latency Tax Audit](/skills/undominated-vector-reranking-latency-tax-audit/)

Calculates cross-encoder reranking latency overhead and cost versus top-k bi-encoder retrieval recall.

 reranking cross-encoder retrieval

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates observed reranking latency and recall margin.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-vector-reranking-latency-tax-audit/) Attributed definition available MIT
 Compare Undominated · Vector Reranking Latency Tax Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Verifier Consensus Cost Audit](/skills/undominated-verifier-consensus-cost-audit/)

Calculates token expenditures and marginal certainty of majority voting consensus across parallel reasoning traces.

 majority-voting consensus verifier

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates exact vote distributions and token pricing.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-verifier-consensus-cost-audit/) Attributed definition available MIT
 Compare Undominated · Verifier Consensus Cost Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Video frame subsampling audit](/skills/undominated-video-frame-subsampling-audit/)

Audits spatio-temporal video token subsampling to prune static background tokens in long video streams.

 serving video multimodal

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Verifies token reduction ratios and task accuracy metrics; does not decode video frames.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-video-frame-subsampling-audit/) Attributed definition available MIT
 Compare Undominated · Video frame subsampling audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · WebGPU browser inference audit](/skills/undominated-webgpu-browser-inference-audit/)

Audits in-browser WebGPU execution shader compilation latency and first-token response times.

 serving webgpu browser

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates recorded browser navigation timing milestones; does not initialize WebGPU contexts.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-webgpu-browser-inference-audit/) Attributed definition available MIT
 Compare Undominated · WebGPU browser inference audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Withdrawal residue](/skills/undominated-withdrawal-residue/)

Check an explicitly observed withdrawn numeric field and its named dependents for leftover values. Use after a source value has been removed from a snapshot.

 withdrawal evidence consistency

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Requires the explicit observed withdrawnValue and named numeric dependents. It cannot verify withdrawal or discover omitted dependencies; zero remains residue and empty coverage requires review.

 Source reviewed

3 sources · 2026-10-07

[Read the full review ↗](/skills/undominated-withdrawal-residue/) Install command in review MIT
 Compare Undominated · Withdrawal residue Add

Evidence and evaluation · Undominated.ai

### [Undominated · Withheld provider names](/skills/undominated-withheld-provider/)

Check a supplied publication denylist by exact provider-name matching. A pass does not approve a provider or establish that the supplied list is complete.

 providers publication names

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Only names in the caller-supplied withheldNames list are withheld. The checker does not load or verify a production policy; a pass does not approve publication.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-withheld-provider/) Attributed definition available MIT
 Compare Undominated · Withheld provider names Add

Evidence and evaluation · Undominated.ai

### [Undominated · Workstation GPU Serving Audit](/skills/undominated-workstation-gpu-serving-audit/)

Calculates local inference throughput and hardware payback periods for desktop RTX workstations versus cloud API spend.

 workstation rtx desktop-inference

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Evaluates observed local throughput and monthly cloud subscription spend.

 Source reviewed

3 sources · 2026-10-08

[Read the full review ↗](/skills/undominated-workstation-gpu-serving-audit/) Attributed definition available MIT
 Compare Undominated · Workstation GPU Serving Audit Add

Evidence and evaluation · Undominated.ai

### [Undominated · Zero Data Retention policy audit](/skills/undominated-zdr-policy-audit/)

Audit provider Zero Data Retention (ZDR) claims against published Terms of Service, abuse monitoring windows, logging exceptions, and training opt-out guarantees.

 zdr privacy governance

**Why we selected it**Pairs a bounded workflow with an offline Python checker and explicitly synthetic example inputs.

**Weigh up**Checks documented policy fields against enterprise requirements; does not perform physical datacenter security audits.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/undominated-zdr-policy-audit/) Attributed definition available MIT
 Compare Undominated · Zero Data Retention policy audit Add

Data and analytics · dbt Labs

### [Upgrading dbt](/skills/dbt-labs-upgrading-dbt/)

Plans a dbt v1 migration to 1.12 using adapter-specific issue bundles and a recorded verification gate.

 dbt migration warehouses

**Why we selected it**Separates sequential pre-1.8 changes from detected behavior flags and preserves unresolved outside-repository job changes.

**Weigh up**Its stated target is 1.12, not a promise to reach whichever release is newest. Starting versions 1.3–1.7 have bundles; later versions have narrower flag handling. Parsing alone does not prove migration correctness.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/dbt-labs-upgrading-dbt/) Install command in review Apache-2.0
 Compare Upgrading dbt Add

Model evaluation · Braintrust

### [Validate an Eval Scorer](/skills/braintrustdata-braintrust-validate-eval-scorer/)

Checks an LLM judge or scorer against expert-reviewed labels, using agreement with uncertainty and severity-weighted errors.

 evaluation llm-as-judge agreement

**Why we selected it**It requires naming the reference tier first, says a strong-model reference supports iteration only, and calibrates fitness bands to adjudicated human labels.

**Weigh up**The body cites fitness bands in reference.md, a file not present in the skill directory at this revision. The header points to references/validation-recipe.md, which was not opened.

 Source reviewed

5 sources · 2026-10-13

[Read the full review ↗](/skills/braintrustdata-braintrust-validate-eval-scorer/) Install command in review Apache-2.0
 Compare Validate an Eval Scorer Add

Security and privacy · Trail of Bits

### [Variant Analysis](/skills/trailofbits-variant-analysis/)

Expands a confirmed vulnerability into related-code searches while preserving root-cause evidence and triage decisions.

 variant-analysis codeql semgrep

**Why we selected it**Starts from a verified instance and broadens one abstraction at a time, with explicit false-positive review.

**Weigh up**Pattern matches are candidates, not confirmed vulnerabilities; reachability, sanitization and impact still need review.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-variant-analysis/) Install command in review CC-BY-SA-4.0
 Compare Variant Analysis Add

Testing and reliability · Trail of Bits

### [Vector Forge](/skills/trailofbits-trailmark-vector-forge/)

Finds implementations of a cryptographic algorithm, runs mutation testing to locate escaped mutants, generates test vectors that exercise the uncovered paths, and compares mutation kill rates before and after.

 test-vectors wycheproof mutation-testing

**Why we selected it**Finds a crypto implementation, runs mutation testing to identify escaped mutants, then generates test vectors that exercise the uncovered code paths.

**Weigh up**It installs the tools it needs: `uv tool install trailmark` when missing, and mutation frameworks per references/mutation-frameworks.md, whose Installation Policy says they MUST be installed (cargo install, brew, go install …@latest, sudo package managers).

 Source reviewed

6 sources · 2026-10-22

[Read the full review ↗](/skills/trailofbits-trailmark-vector-forge/) Upstream setup linked CC-BY-SA-4.0
 Compare Vector Forge Add

Cloud operations · Vercel

### [Vercel Optimize](/skills/vercel-labs-vercel-optimize/)

Runs a metrics-first Vercel audit: collects usage signals before reading source, gates candidates deterministically, then produces ranked cost and performance recommendations.

 vercel cost-optimization performance

**Why we selected it**Enforces an observability-first pipeline: no source file is inspected until signals.json exists and a deterministic gate names a route, file, or setting, which blocks speculative rewrites.

**Weigh up**Needs Vercel project access and usage metrics; without signals the workflow stops by design and produces nothing.

 Source reviewed

8 sources · 2026-10-13

[Read the full review ↗](/skills/vercel-labs-vercel-optimize/) Install command in review MIT declared in README; no LICENSE file at 063bee94
 Compare Vercel Optimize Add

Web development · Vercel

### [Vercel React Best Practices](/skills/vercel-labs-react-best-practices/)

Organizes React and Next.js performance reviews around request waterfalls, bundles, server work and rendering costs.

 react nextjs performance

**Why we selected it**Pairs rules with incorrect and corrected code, making recommendations easier to inspect.

**Weigh up**Published impact labels and example speedups are not measurements of your application.

 Source reviewed

7 sources · 2026-10-14

[Read the full review ↗](/skills/vercel-labs-react-best-practices/) Install command in review MIT (declared in upstream README)
 Compare Vercel React Best Practices Add

Web development · Vercel

### [Vercel React Composition Patterns](/skills/vercel-labs-composition-patterns/)

Replaces growing boolean-mode APIs with explicit component composition and provider-owned state contracts.

 react component-design context

**Why we selected it**Shows complete before-and-after component variants rather than only naming the compound-component pattern.

**Weigh up**Context and compound components can add indirection to a simple component; apply the pattern where variation warrants it.

 Source reviewed

7 sources · 2026-10-14

[Read the full review ↗](/skills/vercel-labs-composition-patterns/) Install command in review MIT (declared in upstream README)
 Compare Vercel React Composition Patterns Add

Mobile development · Vercel

### [Vercel React Native Skills](/skills/vercel-labs-react-native-skills/)

Provides React Native and Expo patterns for scrolling, animations, native navigation and dependency layout.

 react-native expo mobile

**Why we selected it**Rules are split by priority, with list performance marked critical and each rule living in its own file.

**Weigh up**SKILL.md is an index; applying a rule without opening its rules/*.md file skips the incorrect and correct examples.

 Source reviewed

7 sources · 2026-10-14

[Read the full review ↗](/skills/vercel-labs-react-native-skills/) Install command in review MIT (declared in upstream README)
 Compare Vercel React Native Skills Add

Design and interfaces · Vercel

### [Vercel Web Interface Guidelines](/skills/vercel-labs-web-design-guidelines/)

Reviews interface code against a freshly fetched guideline set and returns file-specific findings.

 accessibility forms ui-review

**Why we selected it**The review procedure is short and explicit: fetch the guideline file, read the named UI files, and emit line findings.

**Weigh up**The rules are not in this repository; every review must fetch an unpinned main URL, so the rule set can change without this commit changing.

 Source reviewed

6 sources · 2026-10-14

[Read the full review ↗](/skills/vercel-labs-web-design-guidelines/) Install command in review MIT (declared in upstream README)
 Compare Vercel Web Interface Guidelines Add

Creative production · affaan-m

### [Video Editing](/skills/affaan-m-video-editing/)

Runs a layered AI video-editing pipeline — transcript-driven structuring, deterministic FFmpeg cuts from an edit decision list, Remotion composition, selective asset generation, human polish — for turning long recordings into published video.

 video-editing ffmpeg remotion

**Why we selected it**Separates the pipeline into layers with strict jobs — the model structures, FFmpeg cuts deterministically, Remotion composes, humans supply taste — instead of pretending one tool does everything.

**Weigh up**The later layers call third-party services (ElevenLabs with an API key from the environment, fal.ai, VideoDB, Screen Studio, Descript); only the FFmpeg and Remotion layers run without one.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/affaan-m-video-editing/) Install command in review MIT
 Compare Video Editing Add

Languages and tooling · JetBrains

### [Vite](/skills/jetbrains-vite/)

Vite build-tool guidance pinned to the Vite 8 transition: vite.config.ts discipline, import.meta.glob and asset queries, the plugin API and virtual modules, library mode and SSR builds, the multi-environment API, and Rolldown/Oxc migration.

 vite bundler vite-config

**Why we selected it**Pinned to the Vite 8 transition — Rolldown bundler and Oxc transformer replacing esbuild plus Rollup — with a dedicated rolldown-migration reference, which is exactly the migration agents are being asked to perform.

**Weigh up**The mirror generation is dated 2026-01-31 against Vite 8 beta; the upstream antfu/skills generator has since regenerated against Vite 8.3.1 stable (2026-09-25).

 Source reviewed

6 sources · 2026-10-07

[Read the full review ↗](/skills/jetbrains-vite/) Install command in review MIT (upstream antfu/skills)
 Compare Vite Add

Web development · JetBrains

### [VitePress](/skills/jetbrains-vitepress/)

Documentation-site guidance for VitePress: .vitepress configuration, file-based routing and rewrites, Markdown extensions, Vue components inside Markdown, build-time data loaders, dynamic routes, theming, internationalization, SSR compatibility, and deployment recipes.

 vitepress documentation-sites static-site-generator

**Why we selected it**Covers the documentation-site generator end to end — config, file-based routing, Markdown containers and includes, Vue-in-Markdown, data loaders, dynamic routes — each routed to its own reference file.

**Weigh up**The mirror generation is dated 2026-01-28 and based on VitePress 1.x; the upstream generator has since produced a VitePress 2.0.0-alpha.20 revision (2026-09-25).

 Source reviewed

6 sources · 2026-10-07

[Read the full review ↗](/skills/jetbrains-vitepress/) Install command in review MIT (upstream antfu/skills)
 Compare VitePress Add

Testing and reliability · JetBrains

### [Vitest](/skills/jetbrains-vitest/)

Routes an agent through Vitest one topic at a time: configuration shared with the Vite pipeline, the test/describe/expect APIs and hooks, mocking with the vi utilities, snapshot testing, V8 versus Istanbul coverage, fixtures via test.extend, environments, and type-level testing.

 vitest unit-testing jest-compatible

**Why we selected it**Splits the parts of Vitest that agents get wrong into dedicated reference files — vi mocking of modules, timers and dates, snapshot testing, and coverage provider choice — instead of compressing them into prose.

**Weigh up**The mirror carries the January 2026 generation, based on Vitest 3.x; the upstream antfu/skills generator has since produced a Vitest 5.0.1 revision (2026-09-25) that the pinned mirror revision does not include.

 Source reviewed

6 sources · 2026-10-07

[Read the full review ↗](/skills/jetbrains-vitest/) Install command in review MIT (upstream antfu/skills)
 Compare Vitest Add

Testing and reliability · vLLM project

### [vLLM Bench Serve](/skills/vllm-project-vllm-bench-serve/)

vllm bench serve reference for measuring throughput, TTFT, TPOT and goodput against vLLM or any OpenAI-compatible endpoint.

 vllm inference-benchmark latency

**Why we selected it**It documents the load-shape controls that change results: the default --request-rate inf sends every request at once, while a fixed rate, burstiness and ramp-up model steadier traffic.

**Weigh up**The table lists defaults of 1000 prompts and no warm-up requests. Pointed at a paid remote API, a run spends quota at the provider's rates, and the file gives no cost warning.

 Source reviewed

3 sources · 2026-10-13

[Read the full review ↗](/skills/vllm-project-vllm-bench-serve/) Install command in review Apache-2.0
 Compare vLLM Bench Serve Add

Design and interfaces · Microsoft

### [VS Code Accessibility](/skills/microsoft-vscode-accessibility/)

VS Code’s required accessibility discipline for feature work: help dialogs, accessible views and verbosity settings for new interactive surfaces, plus ARIA live-region, keyboard-navigation and labelling rules for any UI change.

 accessibility aria screen-readers

**Why we selected it**Turns screen-reader support into a buildable contract: every new interactive surface must ship an accessibility help dialog and a verbosity setting, plus an accessible view when it renders rich visual content, with a per-feature checklist that names the registration points.

**Weigh up**The implementation sections are written against VS Code’s internal accessibility framework (IAccessibleViewImplementation, AccessibleViewProviderId, accessibilityConfiguration), not portable web APIs.

 Source reviewed

5 sources · 2026-10-15

[Read the full review ↗](/skills/microsoft-vscode-accessibility/) Install command in review MIT
 Compare VS Code Accessibility Add

Localization · GitHub community

### [VS Code Extension Localization](/skills/github-vscode-ext-localization/)

Localizes VS Code extensions by routing each string to its correct target: package manifest files, walkthrough markdown, or code l10n bundles.

 localization vscode-extensions i18n

**Why we selected it**Three localization approaches keyed to resource type (manifest, walkthrough, code strings) instead of one blanket rule applied to all strings.

**Weigh up**VS Code extensions only; not a general i18n-framework guide and silent on pluralization, ICU formats and RTL layout.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/github-vscode-ext-localization/) Install command in review MIT
 Compare VS Code Extension Localization Add

Testing and reliability · GitHub community

### [Vue 3 Pinia Unit Testing](/skills/github-unit-test-vue-pinia/)

Writes and reviews unit tests for Vue 3 + TypeScript + Vitest + Pinia codebases: behavior-first assertions on components, composables and stores, with createTestingPinia setups from a checked-in pattern cookbook.

 vue-3 composition-api pinia

**Why we selected it**Structures the work around the behavior boundary first — component UI, composable or store — and restricts wrapper.vm access to exceptional cases, enforcing black-box assertions over implementation details.

**Weigh up**Assumes the Vitest + @pinia/testing + Vue Test Utils stack; projects on Jest or without Pinia are out of scope.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/github-unit-test-vue-pinia/) Install command in review MIT
 Compare Vue 3 Pinia Unit Testing Add

Security review · Trail of Bits

### [Vulnerability Triage Brocards](/skills/trailofbits-vulnerability-triage-brocards/)

Runs an incoming vulnerability report or automated finding through seven pass, dismiss or needs-more-info tests and returns a one-table triage summary with an accept, dismiss or needs-more-info verdict.

 triage vulnerability-research threat-modeling

**Why we selected it**Each of the seven brocards is written as a falsifiable quick test, such as whether the report can say "an attacker with [capability] can [action] to achieve [impact]".

**Weigh up**By default it stops at the first DISMISS; all seven brocards are evaluated only when the user asks for a full evaluation, although the summary template has a row for each.

 Source reviewed

6 sources · 2026-10-21

[Read the full review ↗](/skills/trailofbits-vulnerability-triage-brocards/) Upstream setup linked CC-BY-SA-4.0
 Compare Vulnerability Triage Brocards Add

Model evaluation · Weights & Biases

### [W&B EvalTable Previews](/skills/wandb-wandb-eval-tables/)

Converts existing W&B Table artifacts into new EvalTable previews without overwriting source runs, with stated size caps.

 wandb evaluation eval-tables

**Why we selected it**The workflow runs a read-only scan first, previews one table key per invocation, and reports success only when verify-preview returns verified: true.

**Weigh up**Conversion relies on scripts/table_artifact_to_eval_table.py and references/EVAL_TABLES.md, which were not opened. preview creates W&B runs, EvalTables and Weave evaluations.

 Source reviewed

3 sources · 2026-10-13

[Read the full review ↗](/skills/wandb-wandb-eval-tables/) Install command in review Apache-2.0
 Compare W&B EvalTable Previews Add

Languages and tooling · JetBrains

### [Wasm Inspector](/skills/jetbrains-wasm-inspector/)

Inspects WebAssembly binaries through JetBrains’ Hexana MCP server: imports, exports, memories, globals and tables read from the binary itself, ABI diffs between two builds, crash-frame triage, and host or supply-chain import audits.

 webassembly wasm binary-analysis

**Why we selected it**Grounds every structural claim in tool output read from the binary itself, explicitly preferring the MCP server over objdump/strings/hexdump shell probing — the discipline that keeps wasm analysis from hallucinating.

**Weigh up**Depends entirely on the bundled Hexana MCP server; the SKILL.md is an operating manual for that tool, not standalone guidance.

 Source reviewed

5 sources · 2026-10-07

[Read the full review ↗](/skills/jetbrains-wasm-inspector/) Upstream setup linked JetBrains Free Plugin License Agreement
 Compare Wasm Inspector Add

Observability · Weights & Biases

### [Weave Instrumentation](/skills/wandb-weave-instrument/)

Adds Weave tracing to Python or TypeScript agents one path at a time, with read-back checks of the stored spans.

 weave tracing opentelemetry

**Why we selected it**The file stops before any edit when no valid W&B login exists, forbids running wandb login in the agent session, and says not to read, print or ask for an API key.

**Weigh up**Mechanism choice and verification rely on six reference files that were not opened for this review.

 Source reviewed

3 sources · 2026-10-13

[Read the full review ↗](/skills/wandb-weave-instrument/) Install command in review Apache-2.0
 Compare Weave Instrumentation Add

Databases · Weaviate

### [Weaviate](/skills/weaviate-weaviate/)

Weaviate skill that runs bundled Python scripts against a Weaviate Cloud cluster to list, inspect and create collections, search them, ask the Query Agent, and import files or example data.

 weaviate vector-db vector-search

**Why we selected it**SKILL.md indexes a reference file per operation (Query Agent ask and search modes, hybrid search as the default, semantic and keyword search, listing, inspecting, exploring and creating collections, fetch and filter, file import, example data). Its recommendations name the bundled script to run with uv run for listing, inspecting, exploring and creating collections, importing, example data and each search mode; fetch and filter appears only as a link to its reference.

**Weigh up**skills/weaviate last changed in a commit dated 2026-10-16; the pinned revision is dated 2026-10-20.

 Source reviewed

8 sources · 2026-10-21

[Read the full review ↗](/skills/weaviate-weaviate/) Upstream setup linked BSD-3-Clause
 Compare Weaviate Add

Web development · Addy Osmani

### [Web Best Practices](/skills/addyosmani-best-practices/)

Audits a rendered page against Lighthouse best-practices failures and fixes the implicated code — CSP with nonces and a report-only rollout, Trusted Types, SRI-pinned third-party scripts, hidden source maps with sourcesContent stripped, deprecated APIs.

 security-headers csp trusted-types

**Why we selected it**The security reference goes beyond checklist headers: CSP as defense in depth with nonces or hashes tested report-only first, Trusted Types as the modern DOM-XSS layer, and an explicit instruction not to send X-XSS-Protection because the legacy auditor itself introduced vulnerabilities.

**Weigh up**Lighthouse best-practices scope: the skill itself states a high score is not proof an application is secure and that this is not a complete security assessment.

 Source reviewed

6 sources · 2026-10-15

[Read the full review ↗](/skills/addyosmani-best-practices/) Install command in review MIT
 Compare Web Best Practices Add

Web development · Addy Osmani

### [Web Quality Audit](/skills/addyosmani-web-quality-audit/)

Runs an evidence-led site audit across performance, accessibility, SEO, best practices and agentic browsing, routing each check to live traces first with CLI fallbacks, and closes with re-run verification.

 web-quality lighthouse accessibility

**Why we selected it**Measured findings and code-only hypotheses are kept in separate columns, and the Performance section tracks the Lighthouse move to shared Performance Insights instead of requiring retired audit IDs.

**Weigh up**Its own reference list points at the sibling accessibility skill withheld in wave 1 over a px-versus-pt contrast-table error; follow this audit's ratio-only checks and current WCAG text instead of that table.

 Source reviewed

8 sources · 2026-10-15

[Read the full review ↗](/skills/addyosmani-web-quality-audit/) Install command in review MIT
 Compare Web Quality Audit Add

Web development · JetBrains

### [WebGPU Three.js TSL](/skills/jetbrains-webgpu-threejs-tsl/)

Develops WebGPU-enabled Three.js applications with TSL node materials and compute shaders, covering renderer setup, WGSL integration, device-loss handling and WebGPU limits through checked-in docs, examples and templates.

 webgpu threejs tsl

**Why we selected it**The compute-shader reference captures the TSL trap that matters most — property assignment on nodes is intercepted, JavaScript variable reassignment is not — with a works/doesn't-works table instead of prose.

**Weigh up**No licence file exists in the JetBrains catalog repository or in the original dgreenheck/webgpu-claude-skill repository it snapshots; treat the definition as all-rights-reserved until clarified — this record attaches no redistributable artifact.

 Source reviewed

5 sources · 2026-10-07

[Read the full review ↗](/skills/jetbrains-webgpu-threejs-tsl/) Install command in review Not established
 Compare WebGPU Three.js TSL Add

Data and analytics · dbt Labs

### [Working with dbt Mesh](/skills/dbt-labs-working-with-dbt-mesh/)

Judges a dbt change by who consumes it, and states that cross-project refs require dbt Cloud Enterprise.

 dbt mesh contracts

**Why we selected it**A heading says cross-project refs require dbt Cloud Enterprise.

**Weigh up**Enterprise availability was not verified against an account.

 Source reviewed

3 sources · 2026-10-15

[Read the full review ↗](/skills/dbt-labs-working-with-dbt-mesh/) Install command in review Apache-2.0
 Compare Working with dbt Mesh Add

Development workflow · Trail of Bits

### [Writing Lean proofs](/skills/trailofbits-writing-lean-proofs/)

Writes Lean 4 proofs in Mathlib style, gates sorry with the kernel rather than grep, and defers to a project's own CONTRIBUTING file when it conflicts.

 lean proofs formal-methods

**Why we selected it**Unproved obligations are gated with collectAxioms or #print axioms, not grep, because grep matches comments and misses unproved helpers.

**Weigh up**A verified-software project with its own house style takes precedence over Mathlib conventions; the skill says to read CONTRIBUTING first.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-writing-lean-proofs/) Install command in review CC-BY-SA-4.0
 Compare Writing Lean proofs Add

Security review · Trail of Bits

### [YARA rule authoring](/skills/trailofbits-yara-rule-authoring/)

Authors YARA-X rules that must be tested on the intended samples and on goodware, and forbids speculative nocase, wide, and unbounded regex.

 yara detection malware

**Why we selected it**Requires evidence for case or encoding variants before adding nocase or wide modifiers; measure their cost on the target corpus.

**Weigh up**When NOT to Use sends disassembly to Ghidra or IDA, dynamic analysis to a sandbox, network detection to Suricata or Snort, and memory forensics to Volatility.

 Source reviewed

2 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-yara-rule-authoring/) Install command in review CC-BY-SA-4.0
 Compare YARA rule authoring Add

Security review · Trail of Bits

### [Zeroize audit](/skills/trailofbits-zeroize-audit/)

Looks for secrets that source claims to wipe but the compiler deleted.

 cryptography zeroize compilers

**Why we selected it**The description names compiler-removed zeroization, not only a missing function call.

**Weigh up**CC-BY-SA-4.0 applies to adaptations you redistribute.

 Source reviewed

3 sources · 2026-10-14

[Read the full review ↗](/skills/trailofbits-zeroize-audit/) Install command in review CC-BY-SA-4.0
 Compare Zeroize audit Add

03 / BEHIND THE SELECTION

## The review is part of the product.

A useful recommendation tells you why it fits—and what still needs checking.

### What we inspect

We inspect the skill instructions and relevant supporting material, look for a concrete workflow and useful checks, and record dependencies, permissions and limitations. Each review names the files actually examined. Directory popularity is a discovery signal, not a quality verdict.

### What a selection means

Each resource has a concrete use case, original selection reasons, named limitations and a dated review record. We favour specific instructions, useful scope and inspectable setup. The list is curated; it is not a census of everything available or an independently benchmarked league table.

### Before using it

Read the complete review, check the upstream revision and match the resource to your own host and permissions. Review notes apply to the material named at the recorded date. Installation commands may retrieve a newer upstream version.

### Where we looked

 - [Publisher skill repositories ↗](https://github.com/anthropics/skills)
- [Publisher skill repositories ↗](https://github.com/openai/skills)
- [Publisher skill repositories ↗](https://github.com/vercel-labs/agent-skills)
- [Publisher skill repositories ↗](https://github.com/microsoft/skills)
- [Publisher skill repositories ↗](https://github.com/supabase/agent-skills)
- [Publisher skill repositories ↗](https://github.com/cloudflare/skills)
- [Publisher skill repositories ↗](https://github.com/trailofbits/skills)
- [Publisher skill repositories ↗](https://github.com/obra/superpowers)
- [Publisher skill repositories ↗](https://github.com/remotion-dev/skills)
- [Publisher skill repositories ↗](https://github.com/huggingface/skills)
- [Publisher skill repositories ↗](https://github.com/openai/plugins)
- [Publisher skill repository inspected during expanded screening ↗](https://github.com/expo/skills)
- [Publisher skill repository inspected during expanded screening ↗](https://github.com/neondatabase/agent-skills)
- [Publisher skill repository inspected during expanded screening ↗](https://github.com/getsentry/skills)
- [Publisher skill repository inspected during expanded screening ↗](https://github.com/stripe/ai)
- [Publisher repository screened for the Skills expansion ↗](https://github.com/github/awesome-copilot) Original skill definitions and relevant supporting files informed selection; repository inclusion is not a blanket endorsement.
- [Publisher repository screened for the Skills expansion ↗](https://github.com/microsoft/playwright-cli) Original skill definitions and relevant supporting files informed selection; repository inclusion is not a blanket endorsement.
- [Publisher repository screened for the Skills expansion ↗](https://github.com/googleworkspace/cli) Original skill definitions and relevant supporting files informed selection; repository inclusion is not a blanket endorsement.
- [Publisher repository screened for the Skills expansion ↗](https://github.com/google-labs-code/stitch-skills) Original skill definitions and relevant supporting files informed selection; repository inclusion is not a blanket endorsement.
- [Publisher repository screened for the Skills expansion ↗](https://github.com/dbt-labs/dbt-agent-skills) Original skill definitions and relevant supporting files informed selection; repository inclusion is not a blanket endorsement.
- [Publisher repository screened for the Skills expansion ↗](https://github.com/mattpocock/skills) Original skill definitions and relevant supporting files informed selection; repository inclusion is not a blanket endorsement.
- [Publisher repository screened for the Skills expansion ↗](https://github.com/vercel-labs/agent-browser) Original skill definitions and relevant supporting files informed selection; repository inclusion is not a blanket endorsement.
- [Publisher repository screened for the Skills expansion ↗](https://github.com/addyosmani/web-quality-skills) Original skill definitions and relevant supporting files informed selection; repository inclusion is not a blanket endorsement.
- [Publisher repository screened for the Skills expansion ↗](https://github.com/datadog-labs/agent-skills) Original skill definitions and relevant supporting files informed selection; repository inclusion is not a blanket endorsement.
- [Svelte primary source ↗](https://github.com/sveltejs/ai-tools) Direct source screening; popularity was not treated as evidence of quality.
- [Grafana skills repository ↗](https://github.com/grafana/skills)
- [HashiCorp agent skills ↗](https://github.com/hashicorp/agent-skills)
- [Prisma skills ↗](https://github.com/prisma/skills)
- [Wave-5 screening 2026-10-07 ↗](https://github.com/JetBrains/skills) Pinned-revision source reviews; popularity not treated as quality evidence.
- [FastAPI repository ↗](https://github.com/fastapi/fastapi) Skill path fastapi/.agents/skills/fastapi at the reviewed commit.
- [Hono skills ↗](https://github.com/honojs/skills/tree/8b1938be37331c68a02c3b75896b2ea3839d7d09) Read skills/hono/SKILL.md and the MIT licence. The hono-jsx skill and the live hono.dev pages were not opened.
- [Effect skills ↗](https://github.com/Effect-TS/skills/tree/2309e6f27d9955b434c0e3f394b945c136e89fd2) Read the v3-to-v4 migration skill and the MIT licence. The generated migration guide was not opened.
- [Docker skills ↗](https://github.com/docker/skills/tree/f79172733725e2fd236343ee7b963c446ed85d09) Read the destructive-command guardrail and the Apache-2.0 licence. The flag reference and the sibling Compose and build skills were not opened.
- [PlanetScale skills ↗](https://github.com/planetscale/skills/tree/999045cfbad79222f38a99599eb96bc736feabee) Read the Postgres safety review and the MIT licence. The query-insights sibling and the live docs were not opened.
- [Axiom skills ↗](https://github.com/axiomhq/skills/tree/93d60c7d08838921e74b078b73d83936ec3f41bd)
- [Grafana skills ↗](https://github.com/grafana/skills/tree/1ccacf29049fde66637fe01ab93a83a772da323b)
- [Gemini API skills ↗](https://github.com/google-gemini/gemini-skills/tree/ee9da52195752ca83c2fca701d96bcb5a9c08d2d) Read gemini-api-dev and gemini-live-api-dev, the README, the plugin manifests and the Apache-2.0 licence. gemini-omni-flash-api was not reviewed.
- [LangSmith skills ↗](https://github.com/langchain-ai/langsmith-skills/tree/1fb52e836f2d9f8d95c9f0b27d796ab20dac34d1) Read langsmith-evaluator, langsmith-trace and langsmith-dataset, the README and the MIT licence.
- [LangChain skills ↗](https://github.com/langchain-ai/langchain-skills/tree/16a992f09ab3ccfb642dd4f08d350d833d1990bf) Read eval-engineering, the README and the MIT licence. The other LangChain, LangGraph and Deep Agents skills were not reviewed.
- [Weights & Biases skills ↗](https://github.com/wandb/skills/tree/4efbb9fd82e8076cbe5d2332167b19f2bba90d85) Read weave-instrument and wandb-eval-tables, the README and the Apache-2.0 licence.
- [Arize skills ↗](https://github.com/Arize-ai/arize-skills/tree/f92b15a001790a4894f5b17e34d3f8f3c5e13514) Read arize-evaluator, arize-instrumentation-health with references/checks.md, the README and the MIT licence.
- [Braintrust eval library ↗](https://github.com/braintrustdata/eval-library/tree/04486b39047b5ba230f795e52f2935fef651e789) Read braintrust-validate-eval-scorer and braintrust-size-eval-dataset, the README and the Apache-2.0 licence.
- [LlamaParse agent skills ↗](https://github.com/run-llama/llamaparse-agent-skills/tree/2dcef7c62417bd2ec4671fce4621bb1e8cce48d0) Read liteparse and llamaparse, the README and the MIT licence; both were withheld.
- [Cloudflare security audit skill ↗](https://github.com/cloudflare/security-audit-skill/tree/c1c8a8c1471069fb0e188eeaff69b8e8db6564a8) Read SKILL.md, the README and the MIT licence.
- [Anthropic defending-code reference harness ↗](https://github.com/anthropics/defending-code-reference-harness/tree/d3bea6b5793b5f3d59a75ebe69a58efa88383145) Read the README and licence; withheld as unmaintained.
- [Hugging Face transformers-to-mlx ↗](https://github.com/huggingface/transformers-to-mlx/tree/1800e733dc99edf6b33c4c631c813e880dc9cb8f) Repository tree and README checked for a licence; none found.
- [MongoDB agent skills ↗](https://github.com/mongodb/agent-skills/tree/c370a63b27075008a92134686b24af3817edeb00) Read mongodb-search-and-ai, the README and the Apache-2.0 licence.
- [Elastic agent skills ↗](https://github.com/elastic/agent-skills/tree/baa511126ba2dc37b52e273b52734f8e4e0d323c) Read observability-llm-obs, the README and the Apache-2.0 licence.
- [Google skills ↗](https://github.com/google/skills/tree/4601752b28d601d54efb39b06a37488107fc6b1f) Read agent-platform-eval-flywheel and agent-platform-inference, the README and the Apache-2.0 licence.
- [Pulumi agent skills ↗](https://github.com/pulumi/agent-skills/tree/2517e28e4bc029424e9c9ee48016394296be0f6a) Read pulumi-debug-failed-operation, the README and the Apache-2.0 licence.
- [Temporal developer skill ↗](https://github.com/temporalio/skill-temporal-developer/tree/3041178b597dddb1b54f49e5e73fbae644fba283) Read SKILL.md, references/core/ai-patterns.md, the README and the MIT licence.
- [OpenRouter skills ↗](https://github.com/OpenRouterTeam/skills/tree/33597a44e38b0cdc38ea1256ef8bcf50c2704e3d) Repository tree and README checked for a licence; none found. openrouter-models and openrouter-benchmarks frontmatter read.
- [vLLM skills ↗](https://github.com/vllm-project/vllm-skills/tree/c99623410c1531148ff9b39fe1dcb27efbf4bf23) Read vllm-bench-serve and vllm-prefix-cache-bench, the README and the Apache-2.0 licence.
- [Together AI skills ↗](https://github.com/togethercomputer/skills/tree/f59f28e7e7d5937e50581fcfef87b957e8ee8636) Read together-ai SKILL.md, domains/embeddings.md, the README and the MIT licence.
- [Replicate skills ↗](https://github.com/replicate/skills/tree/2f36e415965ae63baa1c9f6635888092bcd771d3) Read compare-models and run-models, the README and the Apache-2.0 licence.
- [Agent Toolkit for AWS ↗](https://github.com/aws/agent-toolkit-for-aws/tree/c34fbdfde6779593f651f2c85629a85d27231498) Read amazon-bedrock SKILL.md, the README and the Apache-2.0 licence.
- [Microsoft Azure skills ↗](https://github.com/microsoft/azure-skills/tree/5aa6e04819634ca4945ef57d6aa059eb4f5944e7) Read azure-aigateway and the MIT licence; withheld.
- [Databricks agent skills ↗](https://github.com/databricks/databricks-agent-skills/tree/f774134a8cc679459f0d7a52cfca54a4ed7c5efd) Read databricks-mlflow-evaluation, the README and the Databricks License; withheld.
- [MLflow skills ↗](https://github.com/mlflow/skills/tree/51a42ea2b07fadb45fb34c7cecf0c87edbe05686) Read build-a-scorer, the README and the Apache-2.0 licence.
- [Hugging Face skills, re-checked for skills added since the last pass ↗](https://github.com/huggingface/skills/tree/c3ff942be3e07116b475253f0a8fc4f54682c1a8) Compared the tree with catalogued records. Read hf-mem and huggingface-best, the README and the Apache-2.0 licence.
- [Anthropic skills, re-checked for skills added since the last pass ↗](https://github.com/anthropics/skills/tree/dbd4588f9e1033efb41dad4bef2f7947c8993d44) Compared the tree with catalogued records. Read discernment-nudge with its LICENSE.txt, the README and the plugin marketplace file.
- [MotherDuck publisher-maintained agent skills ↗](https://github.com/motherduckdb/agent-skills) Selected migration and governance workflows after pinned instruction, reference and helper inspection.
- [Braintrust publisher skill index at the inspected revision ↗](https://github.com/braintrustdata/eval-library/blob/04486b39047b5ba230f795e52f2935fef651e789/skills/README.md) Three distinct missing definitions; the existing size-dataset and validate-scorer definitions were not reacquired.
- [Hugging Face publisher skill index at the inspected revision ↗](https://github.com/huggingface/skills/blob/c3ff942be3e07116b475253f0a8fc4f54682c1a8/README.md) Credential-context discovery and execution-role preflight are separate definitions, not aliases of the existing deployment-planner skill.
 [Download this index as JSON ↗](/data/resources/skills.json)

 Selections we withheld (106)

These are documented decisions from this review, not a blacklist of the wider ecosystem.

 - **playwright:** The publisher explicitly deprecated this repository and directs current skill/plugin users to openai/plugins. Its source was inspected but it is not selected as a current recommendation. [Source ↗](https://github.com/openai/skills/blob/49f948faa9258a0c61caceaf225e179651397431/README.md)
- **security-best-practices:** The publisher explicitly deprecated this repository and directs current skill/plugin users to openai/plugins. Its source was inspected but it is not selected as a current recommendation. [Source ↗](https://github.com/openai/skills/blob/49f948faa9258a0c61caceaf225e179651397431/README.md)
- **security-threat-model:** The publisher explicitly deprecated this repository and directs current skill/plugin users to openai/plugins. Its source was inspected but it is not selected as a current recommendation. [Source ↗](https://github.com/openai/skills/blob/49f948faa9258a0c61caceaf225e179651397431/README.md)
- **gh-fix-ci:** The publisher explicitly deprecated this repository and directs current skill/plugin users to openai/plugins. Its source was inspected but it is not selected as a current recommendation. [Source ↗](https://github.com/openai/skills/blob/49f948faa9258a0c61caceaf225e179651397431/README.md)
- **jupyter-notebook:** The publisher explicitly deprecated this repository and directs current skill/plugin users to openai/plugins. Its source was inspected but it is not selected as a current recommendation. [Source ↗](https://github.com/openai/skills/blob/49f948faa9258a0c61caceaf225e179651397431/README.md)
- **speech:** The publisher explicitly deprecated this repository and directs current skill/plugin users to openai/plugins. Its source was inspected but it is not selected as a current recommendation. [Source ↗](https://github.com/openai/skills/blob/49f948faa9258a0c61caceaf225e179651397431/README.md)
- **transcribe:** The publisher explicitly deprecated this repository and directs current skill/plugin users to openai/plugins. Its source was inspected but it is not selected as a current recommendation. [Source ↗](https://github.com/openai/skills/blob/49f948faa9258a0c61caceaf225e179651397431/README.md)
- **figma-implement-design:** The publisher explicitly deprecated this repository and directs current skill/plugin users to openai/plugins. Its source was inspected but it is not selected as a current recommendation. [Source ↗](https://github.com/openai/skills/blob/49f948faa9258a0c61caceaf225e179651397431/README.md)
- **Expo EAS Workflows:** Withheld pending clearer setup and trigger guidance. The helper depends on import.meta.main but declares no Node.js version requirement. The embedded key list describes a trigger as required, while the current service schema requires only jobs and official documentation allows manual runs without on. Resolve these differences before relying on the installed instructions. [Source ↗](https://github.com/expo/skills/blob/39708666ce7014def1f8e34f3d8c93e8d3f588bb/plugins/expo/skills/eas-workflows/SKILL.md)
- **Neon Postgres Branching:** Withheld at the inspected revision: its lifecycle policy returns no changes for every existing branch, while the subsequent guidance says to apply that policy to an existing branch. The branching and reset material remains useful background, but this reconciliation path needs correction before recommending the installable workflow. [Source ↗](https://github.com/neondatabase/agent-skills/blob/de48bd099a91120f20d79652e0f65540428d596a/skills/neon-postgres-branches/SKILL.md)
- **Sentry Skill Inspection:** Withheld at the inspected revision: the helper copies a matching source line into its secret-detection evidence without redacting the matched value, despite a masking comment. It also reads files before reporting symlinks. Resolve these output and input-handling concerns before running it on sensitive or untrusted material. [Source ↗](https://github.com/getsentry/skills/blob/c2f99a5b04b4cd992ec3022d7c2c3e23e938d241/skills/skill-scanner/scripts/scan_skill.py)
- **Neon Postgres Egress Review:** Withheld pending clearer operational examples. The bundled compute policy returns no changes for every existing branch while the next command is described as applying it to the current branch. Its query rankings use row and call counts rather than network bytes, and resetting statistics discards the existing measurement window. These need reconciliation before a guided cost-reduction recommendation. [Source ↗](https://github.com/neondatabase/agent-skills/blob/de48bd099a91120f20d79652e0f65540428d596a/skills/neon-postgres-egress-optimizer/SKILL.md)
- **Sentry Django Access Review:** Withheld pending clarification of the examples and reference loading. The DRF reference places an unscoped return before the scoped return in the same function, making the latter unreachable if copied. The main definition also does not link its four useful references. The investigation method has value, but the installable material needs more precise guidance before selection. [Source ↗](https://github.com/getsentry/skills/blob/c2f99a5b04b4cd992ec3022d7c2c3e23e938d241/skills/django-access-review/references/drf-permissions.md)
- **Expo SDK Upgrade:** Withheld after inspecting the complete references: the main workflow says to migrate uses before removing expo-av, while the video reference tells readers to uninstall it before installing expo-video. Reconcile this migration order against the target app and current Expo documentation before adoption. [Source ↗](https://github.com/expo/skills/tree/39708666ce7014def1f8e34f3d8c93e8d3f588bb/plugins/expo/skills/expo-upgrade)
- **Stripe Best Practices:** Withheld at the inspected revision: required payment and security reference links point to documentation URLs that returned HTTP 404 during this review. Related files exist in the repository, but the installed workflow needs its reference routing checked before recommendation. [Source ↗](https://github.com/stripe/ai/blob/ea6997c4551d1bfa010b70d875d1aa738a379b25/skills/stripe-best-practices/SKILL.md)
- **Stripe Upgrade Workflow:** Withheld pending reconciliation: the useful live-version and no-downgrade guidance is paired with legacy global/module-level SDK examples, while the companion current best-practices skill explicitly rejects those patterns. Follow current SDK documentation instead of copying the bundled examples unchanged. [Source ↗](https://github.com/stripe/ai/blob/ea6997c4551d1bfa010b70d875d1aa738a379b25/skills/upgrade-stripe/SKILL.md)
- **Microsoft Playwright CLI Skill:** Withheld at the inspected revision: its test-generation guide requires scenario files inside tests/<group>/ but imports ./fixtures even though the shown fixture lives at tests/fixtures.ts. The same guide gives conflicting sequential/parallel instructions. Correct those examples before relying on its generation workflow. [Source ↗](https://github.com/microsoft/playwright-cli/blob/74354ecc7a43da16d91a9bc54fa8db8283a3fcf5/skills/playwright-cli/references/test-generation.md)
- **Addy Osmani Accessibility:** Withheld at the inspected revision: its contrast table uses CSS pixels where WCAG’s large-text exception uses points. Applying that lower size threshold could accept insufficient contrast; verify the current W3C criterion rather than copying the table. [Source ↗](https://github.com/addyosmani/web-quality-skills/blob/afa8da942115f2961fdbfa80807ea0b232ff6c00/skills/accessibility/SKILL.md)
- **Microsoft Azure Monitor OpenTelemetry for Python:** Withheld pending correction: the main definition presents instrumentations as an allow-list, while its own reference and Microsoft’s current API documentation use instrumentation_options with enable/disable entries. The configuration and default behavior need reconciliation before recommendation. [Source ↗](https://github.com/microsoft/skills/blob/96bbd0043d58468fe02090a1691a138e1ef0182b/.github/plugins/azure-sdk-python/skills/azure-monitor-opentelemetry-py/SKILL.md)
- **Superpowers Git Worktree Setup:** Withheld at the inspected revision: the ignore check succeeds when either .worktrees or worktrees is ignored, rather than checking the directory actually selected. This can let an unignored local worktree path pass the stated safety check. [Source ↗](https://github.com/obra/superpowers/blob/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/using-git-worktrees/SKILL.md)
- **GitHub Implementation Plan:** Withheld pending reconciliation: the required GOAL example is not a declaration under the skill’s own rules, and its separate regex checks miss cross-form duplicates. The advertised template-validation contract therefore does not match the checks provided. [Source ↗](https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/skills/create-implementation-plan/SKILL.md)
- **Datadog Monitor Management:** Withheld at the inspected revision: the noisy-monitor audit sorts state-change timestamps rather than alert counts, and its ownership test looks for a literal team: tag rather than a team-prefixed tag. Those examples can misclassify the monitors they claim to audit. [Source ↗](https://github.com/datadog-labs/agent-skills/blob/7f8b08f4fa57211ac1b2b42d9771c9e0c4d79124/dd-monitors/SKILL.md)
- **Datadog Flaky-Test Triage:** Withheld pending reconciliation: one step sends an unknown cause to quarantine while a later decision table sends a low-rate unknown cause to escalation. The same inputs can produce different actions, including a shared test-management state change. [Source ↗](https://github.com/datadog-labs/agent-skills/blob/7f8b08f4fa57211ac1b2b42d9771c9e0c4d79124/dd-software-delivery/triage-flaky-test/SKILL.md)
- **Trail of Bits Modern Python:** Withheld at the inspected revision: the requirements migration loop continues after an individual dependency import fails, then instructs removal of the old requirements files and environment. Confirm a complete dependency migration before following that destructive cleanup. [Source ↗](https://github.com/trailofbits/skills/blob/32e34f8173796e3566a51aee877dc96bc5191f64/plugins/modern-python/skills/modern-python/SKILL.md)
- **Hugging Face AWS Context Discovery:** Withheld at this revision: the identity branch treats an IAM Identity Center/SSO ARN as evidence that IAM roles cannot be created. Effective permissions depend on the assigned permission set and policies, so the identity alone cannot settle the preflight. [Source ↗](https://github.com/huggingface/skills/blob/abc20ae526d8b4c0e4dff89f904adce28a4a0eb6/skills/hf-cloud-aws-context-discovery/SKILL.md)
- **Hugging Face SageMaker IAM Preflight:** Withheld at this revision: the workflow inherits the assumption that an SSO principal cannot create a role and tells the user to stop on that basis. Check actual assigned IAM permissions instead of deriving this restriction from the sign-in type. [Source ↗](https://github.com/huggingface/skills/blob/abc20ae526d8b4c0e4dff89f904adce28a4a0eb6/skills/hf-cloud-sagemaker-iam-preflight/SKILL.md)
- **Hugging Face Local Models:** Withheld at this revision: the llama.cpp setup still instructs users to run make, while the current upstream Makefile explicitly rejects that removed build path and directs users to CMake. [Source ↗](https://github.com/huggingface/skills/blob/abc20ae526d8b4c0e4dff89f904adce28a4a0eb6/skills/huggingface-local-models/SKILL.md)
- **Matt Pocock Resolving Merge Conflicts:** Withheld for broad use: the compact workflow directs the agent to always resolve, never abort, and stage everything before committing. It does not bound those writes to the requested conflict or protect unrelated work in a shared checkout. [Source ↗](https://github.com/mattpocock/skills/blob/c55ee46073ed923f86ce59a5eb3b6d895095d1b7/skills/engineering/resolving-merge-conflicts/SKILL.md)
- **Svelte Code Writer:** Withheld at this revision: the Bash documentation example expands rune names inside double quotes, while the inline-code example preserves an unwanted backslash inside single quotes. Both examples need corrected shell quoting before they are reliable installation/use guidance. [Source ↗](https://github.com/sveltejs/mcp/blob/5c15fbcb5b630ac8ce0281ee1782fc2056fab853/tools/skills/svelte-code-writer/SKILL.md)
- **Terraform Test:** The pinned main guide documents terraform test -no-cleanup and a positional test-file invocation, and treats -filter as a run-block name. The current official Terraform test command contract documents option-only invocation and -filter=testfile. Correct upstream commands before recommending this execution guide. [Source ↗](https://github.com/hashicorp/agent-skills/blob/f706481af9b8fedb66de909f6243ad29601afa0c/plugins/terraform/skills/terraform-test/SKILL.md)
- **Security Code Review:** The pinned Do Not Flag list excludes code paths that require prior authentication. That blanket exclusion can hide authenticated authorization and privilege-escalation vulnerabilities, contradicting the stated broad security-review scope. The separate Django access review explicitly handles these cases. [Source ↗](https://github.com/getsentry/skills/blob/d18b7aa8ba878354e5c348310230e652f7690f9c/skills/security-review/SKILL.md)
- **libFuzzer:** The recommended byte-to-uint32 harness uses potentially unaligned pointer casts, so a harness can generate its own undefined behavior. The troubleshooting guidance also conflates ASan virtual address reservation with RSS and recommends disabling the RSS guard for out-of-memory. Require corrected harness and resource-limit guidance. [Source ↗](https://github.com/trailofbits/skills/blob/82fe8226252622fa807643bdca1710901198553a/plugins/testing-handbook-skills/skills/libfuzzer/SKILL.md)
- **Prometheus cardinality troubleshooter:** Its series-per-instance example uses sum of sample values rather than count of series, and it asserts a fixed 14x benefit per removed label plus conclusive causation from temporal correlation. Those statements can misdirect operational diagnosis; cardinality depends on distinct label combinations. [Source ↗](https://github.com/grafana/skills/blob/1ccacf29049fde66637fe01ab93a83a772da323b/skills/grafana-cloud/prometheus-cardinality-troubleshooter/SKILL.md)
- **Hugging Face Local Models at the reviewed revision:** Withheld: the llama.cpp source-build example invokes make, while current upstream build guidance uses CMake. The shown installation path was not accepted as reliable. [Source ↗](https://github.com/huggingface/skills/blob/ca0325bb20b2d0a1b2efa893670c4c72f79e707b/skills/huggingface-local-models/SKILL.md)
- **Hugging Face Tool Builder at the reviewed revision:** Withheld after reviewing bundled scripts: model-card frontmatter parsing uses fragile string splitting, the private-card helper omits authentication on the card fetch, and the paper-search helper does not perform its claimed paper filter. [Source ↗](https://github.com/huggingface/skills/blob/ca0325bb20b2d0a1b2efa893670c4c72f79e707b/skills/huggingface-tool-builder/SKILL.md)
- **Anthropic MCP Builder bundled evaluation harness:** Withheld as a complete installable package: the evaluation loop handles only the first tool call in a multi-call model response and attempts direct JSON serialization of MCP content objects. It also exposes every discovered tool without a read-only enforcement layer or call budget; the planning guide alone does not resolve these runtime concerns. [Source ↗](https://github.com/anthropics/skills/blob/683bc88e56f3e09ba94f7055977f3d3aa499f202/skills/mcp-builder/scripts/evaluation.py)
- **clickhouse-best-practices:** At ClickHouse/agent-skills commit 356a8c1b9a7392adb389a132f5ad3fec38532a03 the skill says it contains 31 rules and later says a schema review covers all 28 rules. Two rule files were opened and were not the reason for exclusion. The Apache copyright appendix at that commit is the unfilled template. [Source ↗](https://github.com/ClickHouse/agent-skills/blob/356a8c1b9a7392adb389a132f5ad3fec38532a03/skills/clickhouse-best-practices/SKILL.md)
- **langfuse:** At langfuse/skills commit b86532b77f16f1e27c7cffa32bb632aa3cd9a352 the description says to query or modify Langfuse data and to invoke the skill for any AI engineering task even when Langfuse is not mentioned. The allowed-tools list is narrower: WebFetch on langfuse.com, curl to langfuse.com, and langfuse-cli api limited to schema, help, list, and get. The reference workflows were not opened. [Source ↗](https://github.com/langfuse/skills/blob/b86532b77f16f1e27c7cffa32bb632aa3cd9a352/skills/langfuse/SKILL.md)
- **building-pydantic-ai-agents:** The Pydantic AI building skill at pydantic/skills commit 238d97102650c1caa51f35027aee13c469c59542 prints specific run results, including a RunUsage cost, that were not executed. It also shows logfire.instrument_httpx(capture_all=True), which the same file says can capture prompts and secrets. The reference set the procedure routes to was not line-reviewed. [Source ↗](https://github.com/pydantic/skills/blob/238d97102650c1caa51f35027aee13c469c59542/plugins/ai/skills/building-pydantic-ai-agents/SKILL.md)
- **langsmith-trace:** At langchain-ai/langsmith-skills commit 1fb52e8 the setup calls passing --api-key on the command line the preferred method and repeats --api-key $LANGSMITH_API_KEY in its examples, while the sibling langsmith-evaluator at the same commit says not to place keys in commands or logs. It installs the CLI by piping an unpinned main-branch script to sh. [Source ↗](https://github.com/langchain-ai/langsmith-skills/blob/1fb52e836f2d9f8d95c9f0b27d796ab20dac34d1/config/skills/langsmith-trace/SKILL.md)
- **langsmith-dataset:** At commit 1fb52e8 the file prefers --api-key on the command line, as langsmith-trace does, and tells non-interactive runs to pass --yes, which skips the CLI confirmation before dataset deletes and overwrites. [Source ↗](https://github.com/langchain-ai/langsmith-skills/blob/1fb52e836f2d9f8d95c9f0b27d796ab20dac34d1/config/skills/langsmith-dataset/SKILL.md)
- **liteparse:** At run-llama/llamaparse-agent-skills commit 2dcef7c the ranked-search fallback runs ./.claude/skills/effective-liteparse/scripts/search.py, but the skill directory is skills/liteparse, so the documented helper path does not match an installed copy. Its parse example writes to the fixed path /tmp/doc.txt. [Source ↗](https://github.com/run-llama/llamaparse-agent-skills/blob/2dcef7c62417bd2ec4671fce4621bb1e8cce48d0/skills/liteparse/SKILL.md)
- **llamaparse:** At commit 2dcef7c the image-download step sends LLAMA_CLOUD_API_KEY as a Bearer header to each presigned image URL, passing the account key to whatever host that URL names. The step heading says it requires httpx while the code uses fetch. [Source ↗](https://github.com/run-llama/llamaparse-agent-skills/blob/2dcef7c62417bd2ec4671fce4621bb1e8cce48d0/skills/llamaparse/SKILL.md)
- **defending-code-reference-harness skills:** The README at commit d3bea6b states the repository is not maintained and is not accepting contributions. Its skills (threat-model, vuln-scan, triage, patch and others) are written for the repository's own harness and are run by opening that checkout in Claude Code. [Source ↗](https://github.com/anthropics/defending-code-reference-harness/blob/d3bea6b5793b5f3d59a75ebe69a58efa88383145/README.md)
- **transformers-to-mlx:** No LICENSE file exists in the repository tree at commit 1800e73, and neither the README nor SKILL.md names a licence, so reuse and redistribution terms are not established. [Source ↗](https://github.com/huggingface/transformers-to-mlx/tree/1800e733dc99edf6b33c4c631c813e880dc9cb8f)
- **openrouter-models:** No LICENSE file exists in OpenRouterTeam/skills at commit 33597a4 and the README names no licence, so reuse terms for the definition are not established. [Source ↗](https://github.com/OpenRouterTeam/skills/blob/33597a44e38b0cdc38ea1256ef8bcf50c2704e3d/skills/openrouter-models/SKILL.md)
- **openrouter-benchmarks:** No LICENSE file exists at commit 33597a4. The skill also reports Artificial Analysis and Design Arena rankings through OpenRouter's endpoint; this project treats Artificial Analysis redistribution as unresolved. [Source ↗](https://github.com/OpenRouterTeam/skills/blob/33597a44e38b0cdc38ea1256ef8bcf50c2704e3d/skills/openrouter-benchmarks/SKILL.md)
- **azure-aigateway:** At microsoft/azure-skills commit 5aa6e04 the quick-reference table states 60-80% cost savings for semantic caching with no source, and the troubleshooting table answers no cache hits by lowering score-threshold to 0.7 without noting that a looser match can return a cached answer to a different prompt. [Source ↗](https://github.com/microsoft/azure-skills/blob/5aa6e04819634ca4945ef57d6aa059eb4f5944e7/skills/azure-aigateway/SKILL.md)
- **huggingface-best:** At huggingface/skills commit c3ff942 the error handling falls back to "the curated fallback table above", which the file does not contain, and to models ranked by trendingScore when leaderboards fail. Device budgets use a parameters-per-GB rule of thumb that leaves out context and KV-cache memory. [Source ↗](https://github.com/huggingface/skills/blob/c3ff942be3e07116b475253f0a8fc4f54682c1a8/skills/huggingface-best/SKILL.md)
- **databricks-mlflow-evaluation:** At databricks/databricks-agent-skills commit f774134 the LICENSE is the Databricks License, which limits use to connecting with Databricks Services and lets Databricks terminate it on notice. The skill names the Apache-2.0 mlflow/skills repository as the canonical source for the generic workflow; build-a-scorer from that repository is listed instead. [Source ↗](https://github.com/databricks/databricks-agent-skills/blob/f774134a8cc679459f0d7a52cfca54a4ed7c5efd/skills/databricks-mlflow-evaluation/SKILL.md)
- **vllm-prefix-cache-bench:** Its online path repeats vllm bench serve, which is listed. Its offline path at commit c996234 runs benchmarks/benchmark_prefix_caching.py from a vLLM source checkout and downloads an unfiltered ShareGPT dump from an anonymous Hugging Face account. [Source ↗](https://github.com/vllm-project/vllm-skills/blob/c99623410c1531148ff9b39fe1dcb27efbf4bf23/plugins/vllm-skills/skills/vllm-prefix-cache-bench/SKILL.md)
- **run-models:** At replicate/skills commit 2f36e41 the file tells the agent to fire off multiple predictions concurrently without waiting, and has no step that confirms cost before billed predictions run. compare-models from the same repository is listed. [Source ↗](https://github.com/replicate/skills/blob/2f36e415965ae63baa1c9f6635888092bcd771d3/skills/run-models/SKILL.md)
- **Hugging Face Local Models:** Deferred: the reviewed quick start uses a plain make build, while current llama.cpp build documentation specifies CMake. The setup path needs reconciliation before inclusion. [Source ↗](https://github.com/huggingface/skills/blob/c3ff942be3e07116b475253f0a8fc4f54682c1a8/skills/huggingface-local-models/SKILL.md)
- **Trail of Bits Devcontainer Setup:** Not selected as a general isolated-workspace recommendation: the inspected post-install script sets bypassPermissions, the template forwards host credentials, and the container receives NET_ADMIN and NET_RAW. These defaults require a narrower threat model and explicit adaptation. [Source ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/devcontainer-setup/skills/devcontainer-setup/resources/post_install.py)
- **MotherDuck DuckDB SQL:** Deferred: the syntax reference shows date_sub(date, interval), but the official DuckDB signature is date_sub(part, startdate, enddate). A SQL repair reference needs this example corrected before inclusion. [Source ↗](https://github.com/motherduckdb/agent-skills/blob/f97855858bee6cff552031358666824cf01754c5/skills/motherduck-duckdb-sql/references/SYNTAX_REFERENCE.md)
- **Databricks agent skills:** LICENSE at databricks/databricks-agent-skills commit e7a6f218af2fc25b4b896d1e8a0cb4858b20cb75 is a Databricks License whose agreement definition points at the Master Cloud Services Agreement. It is not MIT, Apache-2.0, BSD, ISC, CC-BY-4.0, CC-BY-SA-4.0, or MPL-2.0. [Source ↗](https://github.com/databricks/databricks-agent-skills/blob/e7a6f218af2fc25b4b896d1e8a0cb4858b20cb75/LICENSE)
- **Trigger.dev skills:** README at triggerdotdev/skills commit e0f9f87153d1502fd9f6298e2eb1d58cfd7f9871 says the repository is an automatic mirror of skills maintained in the Trigger.dev monorepo. LICENSE and LICENSE.md at that commit return HTTP 404, so this repository has no licence file to review. [Source ↗](https://github.com/triggerdotdev/skills/blob/e0f9f87153d1502fd9f6298e2eb1d58cfd7f9871/README.md)
- **Angular skills:** README at angular/skills commit d5cdb148f23a74cd6788d983c931f3b3a9860e6f exists and names angular-developer and angular-new-app. LICENSE, LICENSE.md, and COPYING at that commit return HTTP 404. Skill bodies were not fetched because no licence file was present. [Source ↗](https://github.com/angular/skills/blob/d5cdb148f23a74cd6788d983c931f3b3a9860e6f/README.md)
- **prisma-postgres:** prisma-postgres/SKILL.md at prisma/skills commit be16a8740d01363d13552b317042431ee8dfc581 says it is a deprecated compatibility name for prisma-postgres-setup and tells the reader to load that other skill. It does not contain the setup recipes. The repository LICENSE is MIT; the exclusion is the deprecated alias, not the licence. [Source ↗](https://github.com/prisma/skills/blob/be16a8740d01363d13552b317042431ee8dfc581/prisma-postgres/SKILL.md)
- **better-auth skills:** At better-auth/skills commit 20c9e88a5c007461a703f1c213572b073196113e, root README.md and LICENSE both return HTTP 404. No skill body was reviewed. [Source ↗](https://github.com/better-auth/skills/blob/20c9e88a5c007461a703f1c213572b073196113e/README.md)
- **dbt command runner:** The preferences say always use --select and never run the whole project without approval, and always use --quiet. The static-analysis examples are dbt run --static-analysis=off and dbt run --static-analysis=unsafe, with neither --select nor --quiet. [Source ↗](https://github.com/dbt-labs/dbt-agent-skills/blob/7c7b5fa39e61694f1ae2b8ea1b8065e195c814ce/skills/dbt/skills/running-dbt-commands/SKILL.md)
- **Grafana database observability:** The description says the skill creates a least-privilege monitoring user. The PostgreSQL example sets the password to the literal secret, and the MySQL example creates grafana_monitoring@% with SELECT, PROCESS, and REPLICATION CLIENT on *.*, which the same file still calls least privilege. [Source ↗](https://github.com/grafana/skills/blob/1ccacf29049fde66637fe01ab93a83a772da323b/skills/grafana-cloud/database-observability/SKILL.md)
- **AppInsights instrumentation guide:** The file says it is reference material and that azure-prepare orchestrates actual changes, and it sends any request to change or add components to azure-prepare. The guidelines then say to manually instrument the app by creating the Application Insights resource and updating the application's code. [Source ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-skills/skills/appinsights-instrumentation/SKILL.md)
- **Azure app onboard:** The quick reference says the pipeline is self-contained and makes no external skill calls. Step 3 of the same workflow requires invoking the separate azure-app-onboard-prereq skill, while the deploy note forbids invoking azure-deploy. The file therefore both prohibits external skill calls and requires one. [Source ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-skills/skills/azure-app-onboard/SKILL.md)
- **Azure app onboard prepare:** Step 9 writes prepare-plan.json and step 10 returns the orchestrator summary, while step 11 says the four plan checks must all pass before writing. The same step 11 row also says to fix the plan inline on failure, which writes after a failed check. [Source ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-skills/skills/azure-app-onboard/prepare/SKILL.md)
- **Azure app onboard scaffold:** The file boundary says the scaffold only writes files and runs no install or build commands. The same file then requires az bicep build and tells the main thread to run the conformance script when a shell exists. [Source ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-skills/skills/azure-app-onboard/scaffold/SKILL.md)
- **Microsoft Foundry:** The file contradicts itself: Tool Usage Conventions say to reference official documentation URLs instead of embedding CLI command syntax, but the network-isolation section embeds an az cognitiveservices account show command. [Source ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-skills/skills/microsoft-foundry/SKILL.md)
- **Capacity Discovery:** The description says a quota-increase request is out of scope and should be sent to the Azure Portal, but the no-quota path says to hand that same increase request to the quota skill. [Source ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-skills/skills/microsoft-foundry/models/deploy-model/capacity/SKILL.md)
- **Deploy Model to Optimal Region:** The description says custom capacity configuration belongs in the customize skill, but Advanced Usage still shows a deployment create that sets --sku-capacity. [Source ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-skills/skills/microsoft-foundry/models/deploy-model/preset/SKILL.md)
- **Azure Prepare:** The description says to use the skill only for azd and not for non-azd deployments, but Phase 1 says to choose AZD, AZCLI, Bicep, or Terraform. The description also lists creating and deploying to Azure, while the body says this skill must not run azd up, azd deploy, or terraform apply. Rule 1 says the plan skeleton is the very first action, and Step 0 says invoking a specialized skill is the mandatory first action. [Source ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-skills/skills/azure-prepare/SKILL.md)
- **Azure Quotas:** The scripts section says to use check-quota.ps1 or check-quota.sh instead of constructing commands manually for usage queries and capacity calculation. Workflow 2 then constructs az quota show and az quota usage show by hand to calculate available capacity across regions. [Source ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-skills/skills/azure-quotas/SKILL.md)
- **Azure Reliability:** The sample re-assessment leaves health probes partial and then says multi-region is offered next. Step 3 says not to ask about multi-region unless zone-redundant compute, ZRS or GZRS storage, and health probes are all on, and not to ask when any core feature is not on. [Source ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-skills/skills/azure-reliability/SKILL.md)
- **IRQL incident response queries:** The description says the skill translates natural language hunting questions into IRQL pipelines and lists failed logins as a WHEN trigger, but the body says it is not a natural-language-to-IRQL converter and not to activate for a generic failed-logins query unless the user explicitly asks for IRQL. [Source ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-kusto-graph-skills/skills/azure-kusto-irql/SKILL.md)
- **Azure Cosmos DB NoSQL Python:** The Security Requirements say to use DefaultAzureCredential in Azure and never store keys in code, and the later Security list says zero secrets in code. The next requirement says to hardcode the well-known emulator key for local development. The emulator samples do not hardcode a key: they pass COSMOS_KEY or settings.cosmos_key, after the authentication block said to avoid account and API keys in every code sample. [Source ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-python/skills/azure-cosmos-db-py/SKILL.md)
- **Azure Bot Service SDK:** The authentication rules say DefaultAzureCredential works in Azure with no code change and that production should constrain that same chain with AZURE_TOKEN_CREDENTIALS, but best practice 3 says to use DefaultAzureCredential only for local code and a specific token credential in Azure. [Source ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-python/skills/azure-mgmt-botservice-py/SKILL.md)
- **Azure Fabric management SDK:** The authentication rules say DefaultAzureCredential works in Azure with no code change and that production should constrain that same chain with AZURE_TOKEN_CREDENTIALS, but best practice 3 says to use DefaultAzureCredential only for local code and a specific token credential in Azure. [Source ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-python/skills/azure-mgmt-fabric-py/SKILL.md)
- **Azure Monitor ingestion SDK:** The authentication rules say DefaultAzureCredential works in Azure with no code change and that production should constrain that same chain with AZURE_TOKEN_CREDENTIALS, but best practice 3 says to use DefaultAzureCredential only for local code and a specific token credential in Azure. [Source ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-python/skills/azure-monitor-ingestion-py/SKILL.md)
- **Grafana skill authoring:** The score-variance section says to ship only on three consecutive local scores of 100. The later fix section says not to stop until all five local runs hit 100, and it points back to that score-variance section as the reason. Those are different stop conditions for the same local review. [Source ↗](https://github.com/grafana/skills/blob/1ccacf29049fde66637fe01ab93a83a772da323b/skills/grafana-core/skill-authoring/SKILL.md)
- **Grafana Cloud k6 manage:** The opening rule says the only header set by hand on Loki queries, browser screenshot and file fetches, and Tempo queries is X-K6TestRun-Id, and that any other header is overwritten or causes conflicts. The screenshot and file section then requires a hand-set Content-Type on the pre-signed URL request and says that header matters. [Source ↗](https://github.com/grafana/skills/blob/1ccacf29049fde66637fe01ab93a83a772da323b/skills/grafana-k6/k6-manage/SKILL.md)
- **Migrate a dbt project across platforms:** Success criteria and Step 5 require dbtf compile to finish with 0 warnings and say warnings are blockers. The same step says adapter warnings from profiles.yml are not blockers. Step 4 says to remove platform-specific configs such as snowflake_warehouse when switching targets, while Known Limitations says not to pre-remove those keys until Fusion flags them. [Source ↗](https://github.com/dbt-labs/dbt-agent-skills/blob/7c7b5fa39e61694f1ae2b8ea1b8065e195c814ce/skills/dbt-migration/skills/migrating-dbt-project-across-platforms/SKILL.md)
- **SRED project organizer:** Step 4 creates a private Notion document called "SRED Project Descriptions", and Step 6 links to that plural title. Step 5 says each project document is a child of the "SRED Project Description" document created in Step 4. [Source ↗](https://github.com/getsentry/skills/blob/d18b7aa8ba878354e5c348310230e652f7690f9c/skills/sred-project-organizer/SKILL.md)
- **Writing Hookify Rules:** plugins/hookify/README.md ends with the heading License and the line MIT License. plugins/hookify/LICENSE is the Apache License, Version 2.0, and it matches the repository LICENSE. The plugin README and the licence file do not name the same licence. [Source ↗](https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/hookify/skills/writing-rules/SKILL.md)
- **Math Olympiad Solver:** The file says to launch 8-12 attempt agents, calls the tight-budget workflow 8 solvers, and sets the model-tier table to 8, 4, and 3 solvers for Haiku, Sonnet, and Opus. Olympiad verification is called 5-pass, while that table gives Haiku 3 verify passes. Abstention is both up to 3 revise cycles and, in the same table, 2, 3, or 4 revise failures by model. The description says pure reasoning with no tools, while deep mode allows local Bash and Python. [Source ↗](https://github.com/anthropics/claude-plugins-official/blob/41f32e407b450055044f167db7ded5e8ff67d203/plugins/math-olympiad/skills/math-olympiad/SKILL.md)
- **Cairo vulnerability scanner:** Section 6 defines pattern 4 as overconstrained L1-to-L2 interaction. A later rationalization says the boundary between felt252 and the sized integer types is where pattern 4 lives. The file assigns pattern 4 two different subjects. [Source ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/building-secure-contracts/skills/cairo-vulnerability-scanner/SKILL.md)
- **Cosmos vulnerability scanner:** The embedded agent prompt says to report every pattern in the reference file and not to skip any. The completeness check expects 8 core patterns from sections 1–9 because it excludes section 8 as legacy-only, while the agent table assigns that scanner sections 1–9. Reporting section 8 misses the expected total, and omitting it violates the prompt. [Source ↗](https://github.com/trailofbits/skills/blob/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/building-secure-contracts/skills/cosmos-vulnerability-scanner/SKILL.md)
- **Hugging Face datasets:** Canonical definition already selected in both inventories as huggingface-huggingface-datasets. A newer pin or shorter ID would not be an acquisition. [Source ↗](https://github.com/huggingface/skills/tree/c3ff942be3e07116b475253f0a8fc4f54682c1a8/skills/huggingface-datasets)
- **Hugging Face community evals:** Canonical definition already selected in both inventories as huggingface-huggingface-community-evals. [Source ↗](https://github.com/huggingface/skills/tree/c3ff942be3e07116b475253f0a8fc4f54682c1a8/skills/huggingface-community-evals)
- **Docker Sandboxes network and credentials:** Missing from the older integration snapshot but already present in the shared-root catalogue as docker-sandboxes-network-credentials. Do not duplicate under a new ID. [Source ↗](https://github.com/docker/skills/tree/f79172733725e2fd236343ee7b963c446ed85d09/skills/docker-sandboxes-network-credentials)
- **Cloudflare sandbox stable:** Already present in the shared-root catalogue as cloudflare-sandbox-stable; not a new canonical resource. [Source ↗](https://github.com/cloudflare/skills/tree/53395984c3ea1925d00fce03b266112302f050e6/skills/sandbox-stable)
- **Google GKE Batch and HPC:** Not accepted in this packet. The inspected definition applies an unpinned Kueue latest-release manifest and an MPI Operator master manifest, creates node pools, and names MCP tools without binding their implementation. Those external executable configurations and their permissions were not fully pinned and inspected. This is a review-coverage deferral, not a finding that the publisher is unsafe. [Source ↗](https://github.com/google/skills/blob/e569129c25c9f660db4902431b59d2aeefafe55e/skills/cloud/gke-batch-hpc/SKILL.md)
- **Dagster expert skill:** Publisher tree discovery only. The large reference surface includes deployment, secret, run-launch and deletion operations, and plugin MCP configuration. Definition, licence and the complete referenced execution boundary were not inspected; not promoted on the strength of the repository name. [Source ↗](https://github.com/dagster-io/skills/tree/8547cac541aa420137b26b2de8141ebdefb06511/plugins/dagster/skills/dagster-expert)
- **example-command:** Reference implementation and example placeholder; not a production security skill. [Source ↗](https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/example-plugin/skills/example-command/SKILL.md)
- **example-skill:** Reference example template; not a standalone operational skill. [Source ↗](https://raw.githubusercontent.com/anthropics/claude-plugins-official/41f32e407b450055044f167db7ded5e8ff67d203/plugins/example-plugin/skills/example-skill/SKILL.md)
- **panel-review:** Test fixture in review-panel test suite, not a standalone skill. [Source ↗](https://raw.githubusercontent.com/trailofbits/skills/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/code-improver/tests/fixtures/review-panel/skills/panel-review/SKILL.md)
- **review-pr:** Test fixture in code-improver tests directory, not an operational skill. [Source ↗](https://raw.githubusercontent.com/trailofbits/skills/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/code-improver/tests/fixtures/pr-review-toolkit/skills/review-pr/SKILL.md)
- **Ollama serve:** No publisher skill to review at the inspected revision: the repository contains no SKILL.md and no skills, agents or claude directories, so there is no Ollama-published skill covering local model serving. [Source ↗](https://github.com/ollama/ollama/tree/00bef57a9f5b1abadbdfa40222c9bf7a5a1cd657)
- **Phoenix phoenix-evals:** Withheld at the inspected revision: the skill frontmatter claims Apache-2.0 while the repository root LICENSE is Elastic License 2.0, which is non-sublicensable and limits hosted use, so the skill cannot be recorded as Apache-2.0 redistributable pending upstream clarification. [Source ↗](https://github.com/Arize-ai/phoenix/blob/3c4763287c4d655840d91b5d80a090e2030e09d5/.agents/skills/phoenix-evals/SKILL.md)
- **Ragas evals:** No publisher skill to review at the inspected revision: the repository contains no SKILL.md and no skills directory, only contributor slash commands and editor rules, so any Ragas skill found elsewhere is third-party rather than publisher-served. [Source ↗](https://github.com/explodinggradients/ragas/tree/298b68274234c060deacab3cf5fb52aa3a20e885)
- **Snowflake cortex-code-skills:** Withheld as one candidate: the collection is community-contributed for educational and reference use with no correctness guarantee, and it carries no single licence, with per-skill files varying between Apache-2.0 and a service-gated Snowflake Skills License that bars extraction, reproduction, derivatives and distribution. [Source ↗](https://github.com/Snowflake-Labs/coco-skills/blob/2bcd5726917eb7b80199ba6de832dc0c72d4d046/README.md)
- **FastAPI Router:** Overlaps fastapi-fastapi, FastAPI's own skill, which already covers router-level prefix, tags and shared dependencies, Annotated dependencies, and return types versus response_model. This 72-line file does the same job (routers with auth dependencies, response models and status codes) through a template and integration steps that assume a src/backend/app/ layout. Its samples declare response_model together with the same return type, which the FastAPI skill reserves for when the two differ. Its template's update and delete endpoints are documented as requiring authentication and ownership, but the update's ownership check is commented out and the delete has none. [Source ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-python/skills/fastapi-router-py/SKILL.md)
- **Pydantic Models:** Overlaps fastapi-fastapi, whose skill is for working with FastAPI APIs and Pydantic models and sets its own rules for model fields. This 71-line file's pattern is the same API request and response schema work, split into Base, Create, Update, Response and InDB variants, with integration steps that assume a src/backend/app/models/ layout and matching TypeScript types. Its required fields are written Field(..., alias=...), which the FastAPI skill says not to do. [Source ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-python/skills/pydantic-models-py/SKILL.md)
- **Azure Identity library for Java:** Withheld pending correction: the Token Caching section (SKILL.md lines 244-258) says "Enable persistent token caching for better performance", but its code calls DefaultAzureCredentialBuilder().enableAccountIdentifierLogging() under the comment "Enable token caching (in-memory by default)" (lines 249-251). The Logging section shows the same call labelled "Log account info" (line 305). A reader who follows the caching advice with that builder turns on what the same file's Logging section calls account-info logging. [Source ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-java/skills/azure-identity-java/SKILL.md)
- **Azure Key Vault Keys library for Rust:** Teaches an unsafe data encryption key. The envelope-encryption sample (SKILL.md lines 133-184) generates its "symmetric data encryption key (DEK)" as random::<u32>().to_le_bytes() (lines 158-159): 4 bytes (32 bits), far below a safe size for a key that protects data, so code copied from the sample generates data keys that weak. The value comes from the rand crate (line 144), which the install line (line 28) does not add. The same section says "the private key never leaves the HSM" (line 135) but creates its key encryption key as KeyType::Rsa (line 148), not KeyType::RsaHsm. [Source ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-rust/skills/azure-keyvault-keys-rust/SKILL.md)
- **Azure Key Vault Secrets (Java):** Teaches unsafe handling of the secrets it manages. Four samples print secret values to standard output: "Secret value: " + value (SKILL.md line 88), the first five characters of every enabled secret while listing (line 131), the async get (line 221) and the error-handling read (line 290). Samples also hardcode literal secret values such as "P@ssw0rd123!" (line 62), "sk_live_abc123xyz" (line 68) and "CertP@ss!" (line 361). The Purge block (lines 177-187) purges old-secret, then calls getDeletedSecret under the comment "Get deleted secret info first" and purges it a second time. [Source ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-java/skills/azure-security-keyvault-secrets-java/SKILL.md)
- **let-fate-decide:** Not selected: the skill picks a direction by drawing a random 12-house Tarot spread, and its description says to prefer the draw over asking clarifying questions when the user sounds casual. Its own SKILL.md says that in security and correctness work the reading is never sufficient by itself, and that cards can suggest what to inspect while only evidence can dismiss a concern. The technical-context lenses translate a reading into which evidence to gather next; the skill produces none of that evidence itself. [Source ↗](https://raw.githubusercontent.com/trailofbits/skills/8e54050ae63c2f62224c35b1616efe71865b4777/plugins/let-fate-decide/skills/let-fate-decide/SKILL.md)
- **Azure AI Content Understanding SDK for Python:** Withheld pending correction: the main definition and its own reference disagree on the custom-analyzer API. SKILL.md (lines 169-211) creates the analyzer with client.create_analyzer(analyzer_id=..., analyzer={...}) and reads result.fields["vendor_name"]. references/non-hero-scenarios.md (lines 62-111) calls client.begin_create_analyzer(analyzer_id=..., resource=ContentAnalyzer(...)), which it says returns an LRO poller to wait on, and reads content.fields["vendor_name"].value_string from result.contents[0]. They also name different base classes for DocumentContent and AudioVisualContent: MediaContent at SKILL.md line 263, AnalysisContent at line 163 of the reference. Neither file says which is current. [Source ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-python/skills/azure-ai-contentunderstanding-py/SKILL.md)

04 / PRACTICAL ANSWERS

## Before you add it.

 What is an AI skill?

A skill packages instructions for a repeatable task. It may also include scripts, reference documents or other files. The host decides when and how to use it; a skill does not replace the underlying model or guarantee its output.

 What does “source reviewed” mean here?

We examined the material named in the review record and wrote our own reasons, findings and limitations. This is not an installation test, a security certification or a measured improvement in model performance. Untested aspects are listed on each detail page.

 How do I install a listed skill?

Open its review and use the documented command or upstream setup guide. Skills installed through the Skills CLI can include supporting files, so copying only SKILL.md may be incomplete. Choose the intended host and project scope, and inspect the permissions before running the skill.

 Are the skills ranked by downloads?

No. The default order is alphabetical. These are editorial selections with named reasons and trade-offs, drawn from multiple publishers and sources. Installation counts and star counts do not establish that a skill is right for your task.

## Continue your investigation

 - [Choose a toolkit](/tools/)
- [Inspect execution hosts](/agents/)
- [Check tool access](/mcp-servers/)
- [Check project dependencies](/check-repo/)
