{"kind":"skills","reviewedAt":"2026-09-22","sourceCount":221,"publisherCount":16,"discoverySources":[{"title":"Publisher skill repositories","url":"https://github.com/anthropics/skills","checkedAt":"2026-09-21"},{"title":"Publisher skill repositories","url":"https://github.com/openai/skills","checkedAt":"2026-09-21"},{"title":"Publisher skill repositories","url":"https://github.com/vercel-labs/agent-skills","checkedAt":"2026-09-21"},{"title":"Publisher skill repositories","url":"https://github.com/microsoft/skills","checkedAt":"2026-09-21"},{"title":"Publisher skill repositories","url":"https://github.com/supabase/agent-skills","checkedAt":"2026-09-21"},{"title":"Publisher skill repositories","url":"https://github.com/cloudflare/skills","checkedAt":"2026-09-21"},{"title":"Publisher skill repositories","url":"https://github.com/trailofbits/skills","checkedAt":"2026-09-21"},{"title":"Publisher skill repositories","url":"https://github.com/obra/superpowers","checkedAt":"2026-09-21"},{"title":"Publisher skill repositories","url":"https://github.com/remotion-dev/skills","checkedAt":"2026-09-21"},{"title":"Publisher skill repositories","url":"https://github.com/huggingface/skills","checkedAt":"2026-09-21"},{"title":"Publisher skill repositories","url":"https://github.com/openai/plugins","checkedAt":"2026-09-21"},{"title":"Publisher skill repository inspected during expanded screening","url":"https://github.com/expo/skills","checkedAt":"2026-09-21"},{"title":"Publisher skill repository inspected during expanded screening","url":"https://github.com/neondatabase/agent-skills","checkedAt":"2026-09-21"},{"title":"Publisher skill repository inspected during expanded screening","url":"https://github.com/getsentry/skills","checkedAt":"2026-09-21"},{"title":"Publisher skill repository inspected during expanded screening","url":"https://github.com/stripe/ai","checkedAt":"2026-09-21"},{"title":"Publisher repository screened for the Skills expansion","url":"https://github.com/github/awesome-copilot","checkedAt":"2026-09-21","note":"Original skill definitions and relevant supporting files informed selection; repository inclusion is not a blanket endorsement."},{"title":"Publisher repository screened for the Skills expansion","url":"https://github.com/microsoft/playwright-cli","checkedAt":"2026-09-21","note":"Original skill definitions and relevant supporting files informed selection; repository inclusion is not a blanket endorsement."},{"title":"Publisher repository screened for the Skills expansion","url":"https://github.com/googleworkspace/cli","checkedAt":"2026-09-21","note":"Original skill definitions and relevant supporting files informed selection; repository inclusion is not a blanket endorsement."},{"title":"Publisher repository screened for the Skills expansion","url":"https://github.com/google-labs-code/stitch-skills","checkedAt":"2026-09-21","note":"Original skill definitions and relevant supporting files informed selection; repository inclusion is not a blanket endorsement."},{"title":"Publisher repository screened for the Skills expansion","url":"https://github.com/dbt-labs/dbt-agent-skills","checkedAt":"2026-09-21","note":"Original skill definitions and relevant supporting files informed selection; repository inclusion is not a blanket endorsement."},{"title":"Publisher repository screened for the Skills expansion","url":"https://github.com/mattpocock/skills","checkedAt":"2026-09-21","note":"Original skill definitions and relevant supporting files informed selection; repository inclusion is not a blanket endorsement."},{"title":"Publisher repository screened for the Skills expansion","url":"https://github.com/vercel-labs/agent-browser","checkedAt":"2026-09-21","note":"Original skill definitions and relevant supporting files informed selection; repository inclusion is not a blanket endorsement."},{"title":"Publisher repository screened for the Skills expansion","url":"https://github.com/addyosmani/web-quality-skills","checkedAt":"2026-09-21","note":"Original skill definitions and relevant supporting files informed selection; repository inclusion is not a blanket endorsement."},{"title":"Publisher repository screened for the Skills expansion","url":"https://github.com/datadog-labs/agent-skills","checkedAt":"2026-09-21","note":"Original skill definitions and relevant supporting files informed selection; repository inclusion is not a blanket endorsement."},{"title":"Svelte primary source","url":"https://github.com/sveltejs/ai-tools","checkedAt":"2026-09-22","note":"Direct source screening; popularity was not treated as evidence of quality."}],"excluded":[{"name":"playwright","id":"openai-playwright","reason":"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.","sourceUrl":"https://github.com/openai/skills/blob/49f948faa9258a0c61caceaf225e179651397431/README.md"},{"name":"security-best-practices","id":"openai-security-best-practices","reason":"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.","sourceUrl":"https://github.com/openai/skills/blob/49f948faa9258a0c61caceaf225e179651397431/README.md"},{"name":"security-threat-model","id":"openai-security-threat-model","reason":"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.","sourceUrl":"https://github.com/openai/skills/blob/49f948faa9258a0c61caceaf225e179651397431/README.md"},{"name":"gh-fix-ci","id":"openai-gh-fix-ci","reason":"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.","sourceUrl":"https://github.com/openai/skills/blob/49f948faa9258a0c61caceaf225e179651397431/README.md"},{"name":"jupyter-notebook","id":"openai-jupyter-notebook","reason":"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.","sourceUrl":"https://github.com/openai/skills/blob/49f948faa9258a0c61caceaf225e179651397431/README.md"},{"name":"speech","id":"openai-speech","reason":"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.","sourceUrl":"https://github.com/openai/skills/blob/49f948faa9258a0c61caceaf225e179651397431/README.md"},{"name":"transcribe","id":"openai-transcribe","reason":"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.","sourceUrl":"https://github.com/openai/skills/blob/49f948faa9258a0c61caceaf225e179651397431/README.md"},{"name":"figma-implement-design","id":"openai-figma-implement-design","reason":"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.","sourceUrl":"https://github.com/openai/skills/blob/49f948faa9258a0c61caceaf225e179651397431/README.md"},{"id":"expo-eas-workflows","name":"Expo EAS Workflows","reason":"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.","sourceUrl":"https://github.com/expo/skills/blob/39708666ce7014def1f8e34f3d8c93e8d3f588bb/plugins/expo/skills/eas-workflows/SKILL.md"},{"id":"neon-postgres-branches","name":"Neon Postgres Branching","reason":"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.","sourceUrl":"https://github.com/neondatabase/agent-skills/blob/de48bd099a91120f20d79652e0f65540428d596a/skills/neon-postgres-branches/SKILL.md"},{"id":"sentry-skill-scanner","name":"Sentry Skill Inspection","reason":"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.","sourceUrl":"https://github.com/getsentry/skills/blob/c2f99a5b04b4cd992ec3022d7c2c3e23e938d241/skills/skill-scanner/scripts/scan_skill.py"},{"id":"neon-postgres-egress-optimizer","name":"Neon Postgres Egress Review","reason":"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.","sourceUrl":"https://github.com/neondatabase/agent-skills/blob/de48bd099a91120f20d79652e0f65540428d596a/skills/neon-postgres-egress-optimizer/SKILL.md"},{"id":"sentry-django-access-review","name":"Sentry Django Access Review","reason":"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.","sourceUrl":"https://github.com/getsentry/skills/blob/c2f99a5b04b4cd992ec3022d7c2c3e23e938d241/skills/django-access-review/references/drf-permissions.md"},{"id":"expo-expo-upgrade","name":"Expo SDK Upgrade","reason":"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.","sourceUrl":"https://github.com/expo/skills/tree/39708666ce7014def1f8e34f3d8c93e8d3f588bb/plugins/expo/skills/expo-upgrade"},{"id":"stripe-stripe-best-practices","name":"Stripe Best Practices","reason":"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.","sourceUrl":"https://github.com/stripe/ai/blob/ea6997c4551d1bfa010b70d875d1aa738a379b25/skills/stripe-best-practices/SKILL.md"},{"id":"stripe-upgrade-stripe","name":"Stripe Upgrade Workflow","reason":"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.","sourceUrl":"https://github.com/stripe/ai/blob/ea6997c4551d1bfa010b70d875d1aa738a379b25/skills/upgrade-stripe/SKILL.md"},{"id":"microsoft-playwright-cli","name":"Microsoft Playwright CLI Skill","reason":"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.","sourceUrl":"https://github.com/microsoft/playwright-cli/blob/74354ecc7a43da16d91a9bc54fa8db8283a3fcf5/skills/playwright-cli/references/test-generation.md"},{"id":"addyosmani-accessibility","name":"Addy Osmani Accessibility","reason":"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.","sourceUrl":"https://github.com/addyosmani/web-quality-skills/blob/afa8da942115f2961fdbfa80807ea0b232ff6c00/skills/accessibility/SKILL.md"},{"id":"microsoft-azure-monitor-opentelemetry-py","name":"Microsoft Azure Monitor OpenTelemetry for Python","reason":"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.","sourceUrl":"https://github.com/microsoft/skills/blob/96bbd0043d58468fe02090a1691a138e1ef0182b/.github/plugins/azure-sdk-python/skills/azure-monitor-opentelemetry-py/SKILL.md"},{"id":"obra-using-git-worktrees","name":"Superpowers Git Worktree Setup","reason":"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.","sourceUrl":"https://github.com/obra/superpowers/blob/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/using-git-worktrees/SKILL.md"},{"id":"github-create-implementation-plan","name":"GitHub Implementation Plan","reason":"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.","sourceUrl":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/skills/create-implementation-plan/SKILL.md"},{"id":"datadog-labs-dd-monitors","name":"Datadog Monitor Management","reason":"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.","sourceUrl":"https://github.com/datadog-labs/agent-skills/blob/7f8b08f4fa57211ac1b2b42d9771c9e0c4d79124/dd-monitors/SKILL.md"},{"id":"datadog-labs-triage-flaky-test","name":"Datadog Flaky-Test Triage","reason":"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.","sourceUrl":"https://github.com/datadog-labs/agent-skills/blob/7f8b08f4fa57211ac1b2b42d9771c9e0c4d79124/dd-software-delivery/triage-flaky-test/SKILL.md"},{"id":"trailofbits-modern-python","name":"Trail of Bits Modern Python","reason":"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.","sourceUrl":"https://github.com/trailofbits/skills/blob/32e34f8173796e3566a51aee877dc96bc5191f64/plugins/modern-python/skills/modern-python/SKILL.md"},{"id":"huggingface-hf-cloud-aws-context-discovery","name":"Hugging Face AWS Context Discovery","reason":"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.","sourceUrl":"https://github.com/huggingface/skills/blob/abc20ae526d8b4c0e4dff89f904adce28a4a0eb6/skills/hf-cloud-aws-context-discovery/SKILL.md"},{"id":"huggingface-hf-cloud-sagemaker-iam-preflight","name":"Hugging Face SageMaker IAM Preflight","reason":"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.","sourceUrl":"https://github.com/huggingface/skills/blob/abc20ae526d8b4c0e4dff89f904adce28a4a0eb6/skills/hf-cloud-sagemaker-iam-preflight/SKILL.md"},{"id":"huggingface-huggingface-local-models","name":"Hugging Face Local Models","reason":"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.","sourceUrl":"https://github.com/huggingface/skills/blob/abc20ae526d8b4c0e4dff89f904adce28a4a0eb6/skills/huggingface-local-models/SKILL.md"},{"id":"mattpocock-resolving-merge-conflicts","name":"Matt Pocock Resolving Merge Conflicts","reason":"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.","sourceUrl":"https://github.com/mattpocock/skills/blob/c55ee46073ed923f86ce59a5eb3b6d895095d1b7/skills/engineering/resolving-merge-conflicts/SKILL.md"},{"id":"svelte-svelte-code-writer","name":"Svelte Code Writer","reason":"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.","sourceUrl":"https://github.com/sveltejs/mcp/blob/5c15fbcb5b630ac8ce0281ee1782fc2056fab853/tools/skills/svelte-code-writer/SKILL.md"}],"records":[{"id":"anthropics-claude-api","name":"Anthropic Claude API","publisher":"Anthropic","category":"AI application development","tags":["anthropic","claude","api","streaming","tool-use"],"summary":"Routes Claude API work to language-specific SDK guidance and distinguishes self-hosted tool loops from managed agent execution.","why":"Explains the operational differences among a plain API call, a tool runner, managed agents and the separate Agent SDK.","limit":"This is Anthropic-specific and its instructions can strongly influence model, SDK and architecture choices.","compatibility":["Claude Code and compatible instruction-loading agents","Official Anthropic SDKs; explicit REST paths for unsupported languages"],"language":[],"transports":[],"license":"Apache-2.0","access":"Read and edit API integration code","cost":"The skill is Apache-licensed; API calls and any managed-agent or cloud-provider resources follow the chosen service terms.","command":"npx skills add https://github.com/anthropics/skills/tree/34040c9c568585f6929bedeaad110ad08f079624/skills/claude-api","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/anthropics/skills/tree/34040c9c568585f6929bedeaad110ad08f079624/skills/claude-api","reviewedAt":"2026-09-21","sourceCount":7,"download":false,"hasConfig":false},{"id":"anthropics-doc-coauthoring","name":"Anthropic Documentation Coauthoring","publisher":"Anthropic","category":"Research and documentation","tags":["documentation","rfc","specifications","reader-review"],"summary":"Guides a human and agent through audience discovery, section-by-section drafting and a separate-reader review of a substantial document.","why":"Starts with the audience, intended impact and missing context, then lets the author curate ideas before the agent drafts each section.","limit":"Reader-model agreement is a spot check, not factual verification or a human usability study; the author still needs to verify facts and links.","compatibility":["Claude Code","Claude.ai"],"language":[],"transports":[],"license":"Not established","access":"Documents; optional connected sources","cost":"The consuming Claude account or API and any connected services have their own terms; the skill folder does not establish a separate access price.","command":null,"installUrl":"https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/README.md","sourceUrl":"https://github.com/anthropics/skills/tree/34040c9c568585f6929bedeaad110ad08f079624/skills/doc-coauthoring","reviewedAt":"2026-09-21","sourceCount":2,"download":false,"hasConfig":false},{"id":"anthropics-frontend-design","name":"Anthropic Frontend Design","publisher":"Anthropic","category":"Design and interfaces","tags":["design","typography","frontend","copywriting"],"summary":"Builds a visual direction from the product’s audience and subject, then reviews typography, layout and interface copy against that brief.","why":"Requires a compact design plan and a critique of generic choices before implementation.","limit":"This is an opinionated design process, not a component library, usability study or automated accessibility audit.","compatibility":["Claude Code and compatible instruction-loading agents"],"language":[],"transports":[],"license":"Apache-2.0","access":"Read and edit frontend source","cost":"The Apache-licensed instructions have no separate service fee; agent and frontend tooling costs remain separate.","command":"npx skills add https://github.com/anthropics/skills/tree/34040c9c568585f6929bedeaad110ad08f079624/skills/frontend-design","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/anthropics/skills/tree/34040c9c568585f6929bedeaad110ad08f079624/skills/frontend-design","reviewedAt":"2026-09-21","sourceCount":5,"download":false,"hasConfig":false},{"id":"anthropics-pdf","name":"Anthropic PDF Processing","publisher":"Anthropic","category":"Documents","tags":["pdf","forms","ocr","extraction"],"summary":"Covers PDF extraction, transformation and form filling, with separate workflows for actual form fields and image-based overlays.","why":"Form instructions require field discovery before filling, which avoids treating every PDF as the same format.","limit":"The bounding-box helper prints failures without setting a failing exit code; callers must inspect its messages.","compatibility":["Claude document-skills plugin","Python PDF libraries and optional OCR/Poppler command-line tools"],"language":[],"transports":[],"license":"Anthropic custom terms","access":"Read PDF contents and write documents or page images","cost":"Use is governed by the Anthropic service agreement; OCR and conversion require local compute.","command":"/plugin install document-skills@anthropic-agent-skills","installUrl":"https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/README.md","sourceUrl":"https://github.com/anthropics/skills/tree/34040c9c568585f6929bedeaad110ad08f079624/skills/pdf","reviewedAt":"2026-09-21","sourceCount":6,"download":false,"hasConfig":false},{"id":"anthropics-pptx","name":"Anthropic PowerPoint Presentations","publisher":"Anthropic","category":"Documents","tags":["powerpoint","pptx","slides","visual-qa"],"summary":"Guides new-slide generation and template editing with OOXML validation and rendered thumbnail checks.","why":"Explains presentation-specific failure modes in chart axes, colors and shared slide assets.","limit":"LibreOffice previews can differ from PowerPoint font rendering; the source calls for visual review.","compatibility":["Claude document-skills plugin","PptxGenJS, Python, LibreOffice and Poppler"],"language":[],"transports":[],"license":"Anthropic custom terms","access":"Read and write presentation files","cost":"Access follows the Anthropic service agreement; presentation generation and previewing use host compute.","command":"/plugin install document-skills@anthropic-agent-skills","installUrl":"https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/README.md","sourceUrl":"https://github.com/anthropics/skills/tree/34040c9c568585f6929bedeaad110ad08f079624/skills/pptx","reviewedAt":"2026-09-21","sourceCount":6,"download":false,"hasConfig":false},{"id":"anthropics-skill-creator","name":"Anthropic Skill Creator","publisher":"Anthropic","category":"Agent development","tags":["skills","evaluation","triggering","authoring"],"summary":"Develops skills through example tasks, baseline comparisons, human review and separate trigger-description evaluation.","why":"Separates whether a skill activates from whether its instructions improve the resulting work.","limit":"Full baseline and comparison workflows depend on subagents and Claude CLI; reduced Claude.ai paths omit those evaluations.","compatibility":["Claude Code","Claude.ai and Cowork with documented workflow limits"],"language":[],"transports":[],"license":"Apache-2.0","access":"Write skill directories, evaluation artifacts and temporary command files","cost":"The skill is Apache-licensed; repeated agent evaluations consume the configured service allowance or API usage.","command":"npx skills add https://github.com/anthropics/skills/tree/34040c9c568585f6929bedeaad110ad08f079624/skills/skill-creator","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/anthropics/skills/tree/34040c9c568585f6929bedeaad110ad08f079624/skills/skill-creator","reviewedAt":"2026-09-21","sourceCount":7,"download":false,"hasConfig":false},{"id":"anthropics-xlsx","name":"Anthropic Spreadsheets","publisher":"Anthropic","category":"Documents","tags":["excel","xlsx","formulas","spreadsheets"],"summary":"Keeps spreadsheet formulas editable and requires recalculation plus explicit inspection of formula-error results.","why":"Distinguishes formula expressions from cached calculated values, a common source of misleading workbook output.","limit":"Recalculation uses LibreOffice and the guide excludes several newer Excel functions that this environment cannot evaluate.","compatibility":["Claude document-skills plugin","Python openpyxl/pandas and LibreOffice"],"language":[],"transports":[],"license":"Anthropic custom terms","access":"Read and rewrite local workbooks","cost":"Access follows the Anthropic service agreement; recalculation uses local compute.","command":"/plugin install document-skills@anthropic-agent-skills","installUrl":"https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/README.md","sourceUrl":"https://github.com/anthropics/skills/tree/34040c9c568585f6929bedeaad110ad08f079624/skills/xlsx","reviewedAt":"2026-09-21","sourceCount":5,"download":false,"hasConfig":false},{"id":"anthropics-webapp-testing","name":"Anthropic Webapp Testing","publisher":"Anthropic","category":"Browser testing","tags":["playwright","browser","local-development","screenshots"],"summary":"Guides local browser checks with Playwright and includes a wrapper that starts development servers around an automation command.","why":"Uses rendered-page reconnaissance before choosing selectors for dynamic applications.","limit":"The server helper checks only whether a TCP port accepts a connection, not whether the expected application is healthy.","compatibility":["Claude Code","Python Playwright"],"language":[],"transports":[],"license":"Apache-2.0","access":"Local shell and browser automation","cost":"The example skill is Apache-licensed; browser compute, the consuming agent and any services contacted by the tested app have separate costs.","command":"npx skills add https://github.com/anthropics/skills/tree/34040c9c568585f6929bedeaad110ad08f079624/skills/webapp-testing","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/anthropics/skills/tree/34040c9c568585f6929bedeaad110ad08f079624/skills/webapp-testing","reviewedAt":"2026-09-21","sourceCount":7,"download":false,"hasConfig":false},{"id":"anthropics-docx","name":"Anthropic Word Documents","publisher":"Anthropic","category":"Documents","tags":["word","docx","tracked-changes","ooxml"],"summary":"Separates new Word-document generation from editing existing OOXML, with explicit checks for tables, comments and tracked changes.","why":"Documents the different create, edit and read paths instead of treating Word files as plain text.","limit":"Restricted Anthropic terms apply; this is a source-available reference, not an open-source document package.","compatibility":["Claude document-skills plugin","Node docx, Python and local Office-conversion tools"],"language":[],"transports":[],"license":"Anthropic custom terms","access":"Read and write local documents","cost":"Access follows the applicable Anthropic service arrangement; local converters and agent execution are separate resources.","command":"/plugin install document-skills@anthropic-agent-skills","installUrl":"https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/README.md","sourceUrl":"https://github.com/anthropics/skills/tree/34040c9c568585f6929bedeaad110ad08f079624/skills/docx","reviewedAt":"2026-09-21","sourceCount":6,"download":false,"hasConfig":false},{"id":"github-bug-receipt","name":"Bug Receipt","publisher":"GitHub community","category":"Testing and reliability","tags":["debugging","verification","incident-handoff","evidence"],"summary":"Creates an evidence-bearing defect or incident handoff that distinguishes verified, partial and blocked outcomes.","why":"Requires the observed baseline, root-cause evidence, changed artifacts and relevant checks to accompany a completion status.","limit":"The validator checks supplied fields and status consistency; it cannot prove that a command actually ran or that a claimed observation is correct.","compatibility":["GitHub Copilot"],"language":[],"transports":[],"license":"MIT","access":"Repository instructions and host-provided tools","cost":"MIT-licensed collection; agent usage and any project testing or incident tooling costs are separate.","command":"npx skills add https://github.com/github/awesome-copilot/tree/a19b3101cc797a35de8b1c1698c13d1344703522/skills/bug-receipt --skill bug-receipt","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/github/awesome-copilot/blob/a19b3101cc797a35de8b1c1698c13d1344703522/skills/bug-receipt/SKILL.md","reviewedAt":"2026-09-22","sourceCount":10,"download":false,"hasConfig":false},{"id":"github-build-evidence-map","name":"Build Evidence Map","publisher":"GitHub community","category":"Research and evidence","tags":["evidence","research","decision-records","source-traceability"],"summary":"Builds a structured map of claims, evidence and unresolved gaps, with a local validator for the map’s structure.","why":"Preserves supporting, contradicting, qualifying and missing evidence as separate relationships instead of flattening a contested choice into confident prose.","limit":"The bundled validator checks structure and declared excerpts; it does not establish that a source is true or that the excerpt supports the claim.","compatibility":["GitHub Copilot"],"language":[],"transports":[],"license":"MIT","access":"Repository instructions and host-provided tools","cost":"MIT-licensed collection; agent usage and any separately chosen verification service or CLI terms are additional.","command":"npx skills add https://github.com/github/awesome-copilot/tree/a19b3101cc797a35de8b1c1698c13d1344703522/skills/build-evidence-map --skill build-evidence-map","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/github/awesome-copilot/blob/a19b3101cc797a35de8b1c1698c13d1344703522/skills/build-evidence-map/SKILL.md","reviewedAt":"2026-09-22","sourceCount":10,"download":false,"hasConfig":false},{"id":"cloudflare-agents-sdk","name":"Cloudflare Agents SDK","publisher":"Cloudflare","category":"Agent development","tags":["cloudflare","agents","durable-state","mcp"],"summary":"Guides stateful Cloudflare agent applications through current SDK documentation, persistence, scheduling and approval-aware tool flows.","why":"Treats installed SDK versions and current docs as the basis for implementation.","limit":"This is specific to Cloudflare’s Agents SDK and runtime, not a general multi-provider agent framework.","compatibility":["Cloudflare Workers and agents package","Compatible JavaScript/TypeScript coding agents"],"language":[],"transports":[],"license":"Apache-2.0","access":"Read and edit agent code, bindings and migrations","cost":"The skill is Apache-licensed; Workers resources, storage and any model/provider services are billed independently.","command":"npx skills add https://github.com/cloudflare/skills/tree/b052c32bab7dd493513260228a36c88294f343f1/skills/agents-sdk","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/cloudflare/skills/tree/b052c32bab7dd493513260228a36c88294f343f1/skills/agents-sdk","reviewedAt":"2026-09-21","sourceCount":7,"download":false,"hasConfig":false},{"id":"cloudflare-durable-objects","name":"Cloudflare Durable Objects","publisher":"Cloudflare","category":"Cloud development","tags":["cloudflare","durable-objects","sqlite","coordination"],"summary":"Designs per-entity state and coordination with explicit persistence, concurrency and runtime-test guidance.","why":"Defines where Durable Objects fit and where stateless Workers or independent requests fit better.","limit":"A single coordination object can become a bottleneck; object boundaries must fit the workload.","compatibility":["Cloudflare Workers Durable Objects","Cloudflare Vitest integration for runtime tests"],"language":[],"transports":[],"license":"Apache-2.0","access":"Read and edit persistent-state code and configuration","cost":"The Apache-licensed skill is separate from Cloudflare compute, storage and agent-service usage.","command":"npx skills add https://github.com/cloudflare/skills/tree/b052c32bab7dd493513260228a36c88294f343f1/skills/durable-objects","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/cloudflare/skills/tree/b052c32bab7dd493513260228a36c88294f343f1/skills/durable-objects","reviewedAt":"2026-09-21","sourceCount":7,"download":false,"hasConfig":false},{"id":"cloudflare-web-perf","name":"Cloudflare Web Performance Audit","publisher":"Cloudflare","category":"Web performance","tags":["core-web-vitals","devtools","lighthouse","network"],"summary":"Builds a performance review from browser traces, request details and relevant source instead of generic optimization advice.","why":"Starts by discovering available measurement tools and records measurements it could not collect.","limit":"A lab trace does not establish real-user Core Web Vitals or prove a resource is unused in every interaction.","compatibility":["Chrome DevTools MCP or equivalent available browser tools","Websites accessible to the browser"],"language":[],"transports":[],"license":"Apache-2.0","access":"Navigate pages and inspect requests, DOM and traces","cost":"The Apache-licensed guide uses the selected agent and browser tooling; no separate measurement service is bundled.","command":"npx skills add https://github.com/cloudflare/skills/tree/b052c32bab7dd493513260228a36c88294f343f1/skills/web-perf","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/cloudflare/skills/tree/b052c32bab7dd493513260228a36c88294f343f1/skills/web-perf","reviewedAt":"2026-09-21","sourceCount":5,"download":false,"hasConfig":false},{"id":"cloudflare-workers-best-practices","name":"Cloudflare Workers Best Practices","publisher":"Cloudflare","category":"Cloud development","tags":["workers","cloudflare","streaming","runtime"],"summary":"Reviews Workers code against its configured runtime, focusing on request lifetime, state isolation, streaming and binding contracts.","why":"Uses installed types and compatibility settings instead of assuming the newest package defines the current runtime.","limit":"Workers-specific guidance is not interchangeable with a Node server checklist.","compatibility":["Cloudflare Workers","JavaScript/TypeScript with generated binding types"],"language":[],"transports":[],"license":"Apache-2.0","access":"Read and edit Worker code and config","cost":"The instructions are Apache-licensed; deployed Workers, observability and agent services have separate usage terms.","command":"npx skills add https://github.com/cloudflare/skills/tree/b052c32bab7dd493513260228a36c88294f343f1/skills/workers-best-practices","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/cloudflare/skills/tree/b052c32bab7dd493513260228a36c88294f343f1/skills/workers-best-practices","reviewedAt":"2026-09-21","sourceCount":6,"download":false,"hasConfig":false},{"id":"cloudflare-wrangler","name":"Cloudflare Wrangler Workflow","publisher":"Cloudflare","category":"Cloud operations","tags":["wrangler","cloudflare","deployment","secrets"],"summary":"Runs Workers configuration and deployment work against the project’s installed Wrangler version and an explicitly identified target.","why":"Distinguishes local simulation from remote bindings so development commands are not assumed to be harmless.","limit":"The skill authorizes no cloud action by itself; commands can deploy or mutate real resources.","compatibility":["Cloudflare Workers projects","Project-local Wrangler and package manager"],"language":[],"transports":[],"license":"Apache-2.0","access":"Read/edit Worker config and generate types","cost":"The Apache-licensed workflow has no separate service fee; Cloudflare resource usage and agent access are separate.","command":"npx skills add https://github.com/cloudflare/skills/tree/b052c32bab7dd493513260228a36c88294f343f1/skills/wrangler","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/cloudflare/skills/tree/b052c32bab7dd493513260228a36c88294f343f1/skills/wrangler","reviewedAt":"2026-09-21","sourceCount":5,"download":false,"hasConfig":false},{"id":"mattpocock-to-spec","name":"Conversation to Specification","publisher":"Matt Pocock","category":"Planning and delivery","tags":["specification","planning","github","gitlab","handoff"],"summary":"Turns an already-discussed change into a repository-aware specification for the configured issue tracker.","why":"Uses existing project context, glossary and architecture decisions before synthesizing requirements.","limit":"This is synthesis after discussion, not a discovery interview or a check that every stakeholder requirement is present.","compatibility":["Claude Code","Codex"],"language":[],"transports":[],"license":"MIT","access":"Repository instructions and host-provided tools","cost":"MIT-licensed instructions; agent usage and any issue-tracker account terms are separate.","command":"npx skills add https://github.com/mattpocock/skills/tree/c55ee46073ed923f86ce59a5eb3b6d895095d1b7 --skill to-spec --skill setup-matt-pocock-skills","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/mattpocock/skills/blob/c55ee46073ed923f86ce59a5eb3b6d895095d1b7/skills/engineering/to-spec/SKILL.md","reviewedAt":"2026-09-22","sourceCount":14,"download":false,"hasConfig":false},{"id":"dbt-labs-maintaining-dbt-documentation","name":"dbt Documentation Maintenance","publisher":"dbt Labs","category":"Databases","tags":["dbt","documentation","sql","data-models","manifest"],"summary":"Audits descriptions in a dbt manifest and drafts missing model or column documentation in the project’s existing style.","why":"Uses dbt’s resolved manifest rather than guessing YAML layout, and clearly limits column coverage to columns declared in that manifest.","limit":"The audit measures nonempty descriptions, not their correctness or every physical warehouse column; imported model nodes can also appear in a manifest.","compatibility":["Agent Skills-compatible coding agents","Claude Code"],"language":[],"transports":[],"license":"Apache-2.0","access":"dbt source and manifest files","cost":"Apache-licensed instructions and helper; agent calls and any optional dbt platform or warehouse compute are separate.","command":"npx skills add https://github.com/dbt-labs/dbt-agent-skills/tree/a8607fc02a679e81a2b0fe7fcb32a7568802e16a/skills/dbt/skills/maintaining-dbt-documentation","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/dbt-labs/dbt-agent-skills/tree/a8607fc02a679e81a2b0fe7fcb32a7568802e16a/skills/dbt/skills/maintaining-dbt-documentation","reviewedAt":"2026-09-21","sourceCount":8,"download":false,"hasConfig":false},{"id":"mattpocock-diagnosing-bugs","name":"Diagnosing Bugs","publisher":"Matt Pocock","category":"Testing and reliability","tags":["debugging","reproduction","regression-tests","hypotheses"],"summary":"A debugging procedure that establishes a reproducible symptom, tests competing explanations and preserves a regression check.","why":"Requires a red-capable reproduction before edits, so an apparent improvement has a concrete behavior to compare against.","limit":"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.","compatibility":["Claude Code","Codex"],"language":[],"transports":[],"license":"MIT","access":"Repository instructions and host-provided tools","cost":"MIT-licensed instructions; agent usage and test or infrastructure compute are separate.","command":"npx skills add https://github.com/mattpocock/skills/tree/c55ee46073ed923f86ce59a5eb3b6d895095d1b7/skills/engineering/diagnosing-bugs --skill diagnosing-bugs","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/mattpocock/skills/blob/c55ee46073ed923f86ce59a5eb3b6d895095d1b7/skills/engineering/diagnosing-bugs/SKILL.md","reviewedAt":"2026-09-22","sourceCount":8,"download":false,"hasConfig":false},{"id":"google-labs-code-extract-design-md","name":"Google Stitch Design-System Extraction","publisher":"Google Labs / Stitch","category":"Design and interfaces","tags":["design-systems","design-tokens","css","stitch","documentation"],"summary":"Reads frontend source and theme files to draft a structured DESIGN.md for design-system documentation or later Stitch use.","why":"Starts with tokens and theme definitions, then inspects representative components to separate intended conventions from scattered overrides.","limit":"Source extraction does not verify rendered appearance, accessibility or the effects of runtime themes. Descriptions of intent remain interpretation.","compatibility":["Codex","Claude Code","Cursor","Gemini CLI"],"language":[],"transports":[],"license":"Apache-2.0","access":"Frontend source; optional Stitch handoff","cost":"Apache-licensed skill instructions; the consuming agent and any optional Stitch service access have their own terms.","command":null,"installUrl":"https://github.com/google-labs-code/stitch-skills/blob/0337446dadde6f8c94210444e2aa9d546126480f/README.md","sourceUrl":"https://github.com/google-labs-code/stitch-skills/tree/0337446dadde6f8c94210444e2aa9d546126480f/plugins/stitch-design/skills/extract-design-md","reviewedAt":"2026-09-21","sourceCount":9,"download":false,"hasConfig":false},{"id":"huggingface-huggingface-datasets","name":"Hugging Face Dataset Workflows","publisher":"Hugging Face","category":"Data and research","tags":["datasets","hugging-face","parquet","search"],"summary":"Explores Hub dataset splits and rows through the Dataset Viewer API and documents separate dataset-upload workflows.","why":"Starts with subset/split discovery before pagination, search or filtering.","limit":"Although the opening describes read-only exploration, later sections create repositories and upload files or raw agent traces.","compatibility":["Agent Skills-compatible agents","Dataset Viewer API; optional Hugging Face CLI or Hub JavaScript CLI"],"language":[],"transports":[],"license":"Apache-2.0","access":"Read public or authorized private dataset contents","cost":"The skill is Apache-licensed; private storage, hosted services and the consuming agent follow their own account terms.","command":"npx skills add https://github.com/huggingface/skills/tree/abc20ae526d8b4c0e4dff89f904adce28a4a0eb6/skills/huggingface-datasets","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/huggingface/skills/tree/abc20ae526d8b4c0e4dff89f904adce28a4a0eb6/skills/huggingface-datasets","reviewedAt":"2026-09-21","sourceCount":5,"download":false,"hasConfig":false},{"id":"huggingface-huggingface-llm-trainer","name":"Hugging Face LLM Trainer","publisher":"Hugging Face","category":"Model development","tags":["fine-tuning","trl","hugging-face","gpu","training"],"summary":"Prepares and submits managed training jobs with dataset checks, monitoring and explicit persistence of trained artifacts.","why":"Treats dataset shape, credentials and model persistence as prerequisites rather than leaving them until a job fails.","limit":"The skill directs immediate job submission for training requests; make the target, hardware and spending scope explicit before invocation.","compatibility":["Hugging Face Jobs MCP workflow","Python/uv, TRL or documented Unsloth path"],"language":[],"transports":[],"license":"Apache-2.0","access":"Submit billable GPU jobs and install their dependencies","cost":"The Apache-licensed skill is separate from the required eligible Hugging Face plan, metered job compute and storage.","command":"npx skills add https://github.com/huggingface/skills/tree/abc20ae526d8b4c0e4dff89f904adce28a4a0eb6/skills/huggingface-llm-trainer","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/huggingface/skills/tree/abc20ae526d8b4c0e4dff89f904adce28a4a0eb6/skills/huggingface-llm-trainer","reviewedAt":"2026-09-21","sourceCount":8,"download":false,"hasConfig":false},{"id":"huggingface-huggingface-community-evals","name":"Hugging Face Local Model Evaluations","publisher":"Hugging Face","category":"Model evaluation","tags":["evaluations","inspect-ai","lighteval","vllm","hugging-face"],"summary":"Chooses a local evaluation framework and inference backend, starting with a small smoke run before scaling evaluation work.","why":"Separates local GPU inference from a locally launched client that calls remote Inference Providers.","limit":"The provider-backed helper still sends inference requests over the network; local script execution does not mean local inference.","compatibility":["Python/uv","Inspect AI or LightEval with a supported local or provider backend"],"language":[],"transports":[],"license":"Apache-2.0","access":"Download model/task dependencies and read evaluation data","cost":"The skill is Apache-licensed; local hardware, provider inference and any separately chosen hosted jobs have their own costs.","command":"npx skills add https://github.com/huggingface/skills/tree/abc20ae526d8b4c0e4dff89f904adce28a4a0eb6/skills/huggingface-community-evals","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/huggingface/skills/tree/abc20ae526d8b4c0e4dff89f904adce28a4a0eb6/skills/huggingface-community-evals","reviewedAt":"2026-09-21","sourceCount":7,"download":false,"hasConfig":false},{"id":"huggingface-huggingface-papers","name":"Hugging Face Paper Reading","publisher":"Hugging Face","category":"Data and research","tags":["papers","arxiv","literature-research","metadata"],"summary":"Retrieves AI research-paper text and structured metadata, with fallbacks to the original arXiv page or PDF when Hub text is incomplete.","why":"Separates paper text from metadata such as authors and linked code, models and datasets, helping a research task collect the right evidence.","limit":"Hub indexing and HTML availability vary; confirm that the fetched text is the actual paper before summarizing methods or results.","compatibility":["Claude Code","Codex","Gemini CLI","Cursor"],"language":[],"transports":[],"license":"Apache-2.0","access":"Public paper sources; optional Hub writes","cost":"Apache-licensed instructions; consuming agent/API usage and any separately selected Hub account features are distinct.","command":"npx skills add https://github.com/huggingface/skills/tree/abc20ae526d8b4c0e4dff89f904adce28a4a0eb6/skills/huggingface-papers","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/huggingface/skills/tree/abc20ae526d8b4c0e4dff89f904adce28a4a0eb6/skills/huggingface-papers","reviewedAt":"2026-09-21","sourceCount":6,"download":false,"hasConfig":false},{"id":"huggingface-huggingface-trackio","name":"Hugging Face Trackio","publisher":"Hugging Face","category":"Model development","tags":["experiments","training-metrics","alerts","trackio","observability"],"summary":"Adds training metrics and diagnostic alerts, then retrieves run data through Trackio’s CLI or a local or hosted dashboard.","why":"Separates logging, alerting and retrieval into focused references, including a route from an alert to metrics around the relevant training step.","limit":"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.","compatibility":["Claude Code","Codex","Gemini CLI","Cursor"],"language":[],"transports":[],"license":"Apache-2.0","access":"Training files; optional Spaces and webhooks","cost":"Apache-licensed skill instructions; local training compute, hosted storage/compute, consuming agents and any external webhook services have their own terms.","command":"npx skills add https://github.com/huggingface/skills/tree/abc20ae526d8b4c0e4dff89f904adce28a4a0eb6/skills/huggingface-trackio","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/huggingface/skills/tree/abc20ae526d8b4c0e4dff89f904adce28a4a0eb6/skills/huggingface-trackio","reviewedAt":"2026-09-21","sourceCount":9,"download":false,"hasConfig":false},{"id":"mattpocock-codebase-design","name":"Matt Pocock Codebase Design","publisher":"Matt Pocock","category":"Web development","tags":["architecture","interfaces","refactoring","test-design"],"summary":"Evaluates module boundaries through caller complexity, dependency seams and alternative interface designs.","why":"Defines a deep module by what callers can accomplish through a small interface, rather than by its line count.","limit":"The adapter and interface rules are design heuristics, not universal requirements; local substitutes do not prove production integration behavior.","compatibility":["Claude Code","Codex"],"language":[],"transports":[],"license":"MIT","access":"Code, tests and design notes","cost":"MIT-licensed instructions; agent and optional subagent calls consume the host account or API allowance.","command":"npx skills add https://github.com/mattpocock/skills/tree/c55ee46073ed923f86ce59a5eb3b6d895095d1b7 --skill codebase-design --skill setup-matt-pocock-skills","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/mattpocock/skills/tree/c55ee46073ed923f86ce59a5eb3b6d895095d1b7/skills/engineering/codebase-design","reviewedAt":"2026-09-21","sourceCount":14,"download":false,"hasConfig":false},{"id":"mattpocock-domain-modeling","name":"Matt Pocock Domain Modeling","publisher":"Matt Pocock","category":"Research and documentation","tags":["domain-modeling","glossary","architecture-decisions","planning"],"summary":"Builds a project glossary and short architecture decision records while testing domain terms against code and concrete edge cases.","why":"Distinguishes canonical domain terms from implementation notes and uses conflicting examples to expose overloaded language.","limit":"The root and bounded-context instructions do not fully agree on glossary and ADR placement; agree the target paths and numbering convention first.","compatibility":["Claude Code","Codex"],"language":[],"transports":[],"license":"MIT","access":"Repository documentation","cost":"MIT-licensed instructions; agent usage and any separately chosen collaboration tools have their own costs.","command":"npx skills add https://github.com/mattpocock/skills/tree/c55ee46073ed923f86ce59a5eb3b6d895095d1b7 --skill domain-modeling --skill setup-matt-pocock-skills","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/mattpocock/skills/tree/c55ee46073ed923f86ce59a5eb3b6d895095d1b7/skills/engineering/domain-modeling","reviewedAt":"2026-09-21","sourceCount":14,"download":false,"hasConfig":false},{"id":"mattpocock-grilling","name":"Matt Pocock Grilling","publisher":"Matt Pocock","category":"Research and documentation","tags":["planning","requirements","decision-making","interview"],"summary":"Interviews the user through dependency-ordered decisions before the agent acts on a plan or idea.","why":"Only asks decisions whose prerequisites are settled, so answers do not depend on unanswered questions from the same round.","limit":"The interview has no built-in round cap and can be too demanding for a small task; choose its scope deliberately.","compatibility":["Claude Code","Codex"],"language":[],"transports":[],"license":"MIT","access":"Conversation; optional environment research","cost":"MIT-licensed instructions; agent and delegated research calls use the selected host or API.","command":"npx skills add https://github.com/mattpocock/skills/tree/c55ee46073ed923f86ce59a5eb3b6d895095d1b7 --skill grilling --skill setup-matt-pocock-skills","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/mattpocock/skills/tree/c55ee46073ed923f86ce59a5eb3b6d895095d1b7/skills/productivity/grilling","reviewedAt":"2026-09-21","sourceCount":12,"download":false,"hasConfig":false},{"id":"microsoft-azure-cost","name":"Microsoft Azure Cost Management","publisher":"Microsoft","category":"Cloud operations","tags":["azure","cost-management","finops","resource-usage"],"summary":"Connects Azure cost reports to actual billing queries, utilization evidence and separately identified savings estimates.","why":"Requires the total bill and service breakdown alongside optimization suggestions.","limit":"Requires Azure billing/monitoring permissions and supporting CLI or MCP tools.","compatibility":["Microsoft Azure skill/plugin hosts","Azure CLI; Azure MCP where available"],"language":[],"transports":[],"license":"MIT","access":"Read billing details, resource inventory and utilization metrics","cost":"The MIT-licensed skill has no independent subscription; Azure usage, diagnostics and the consuming agent follow their respective account terms.","command":"npx skills add https://github.com/microsoft/skills/tree/96bbd0043d58468fe02090a1691a138e1ef0182b/.github/plugins/azure-skills/skills/azure-cost","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/microsoft/skills/tree/96bbd0043d58468fe02090a1691a138e1ef0182b/.github/plugins/azure-skills/skills/azure-cost","reviewedAt":"2026-09-21","sourceCount":8,"download":false,"hasConfig":false},{"id":"microsoft-azure-diagnostics","name":"Microsoft Azure Diagnostics","publisher":"Microsoft","category":"Cloud operations","tags":["azure","aks","logs","kql","incident-response"],"summary":"Routes Azure incidents through resource health, recent changes, logs and service-specific troubleshooting guides.","why":"Separates App Service, Functions, AKS, compute and messaging investigations.","limit":"The AKS helper selects Azure resources by arguments but uses the existing kubectl context; confirm both point to the same cluster.","compatibility":["Azure CLI and optional Azure MCP","kubectl for the AKS baseline path"],"language":[],"transports":[],"license":"MIT","access":"Read cloud configuration, activity, metrics and logs","cost":"The instructions are MIT-licensed; Azure logging/query services, affected resources and agent access have their own billing.","command":"npx skills add https://github.com/microsoft/skills/tree/96bbd0043d58468fe02090a1691a138e1ef0182b/.github/plugins/azure-skills/skills/azure-diagnostics","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/microsoft/skills/tree/96bbd0043d58468fe02090a1691a138e1ef0182b/.github/plugins/azure-skills/skills/azure-diagnostics","reviewedAt":"2026-09-21","sourceCount":7,"download":false,"hasConfig":false},{"id":"microsoft-microsoft-docs","name":"Microsoft Docs Research","publisher":"Microsoft","category":"Research and documentation","tags":["microsoft","azure","dotnet","documentation","mcp"],"summary":"Finds current Microsoft documentation with task-specific queries and retrieves full pages when excerpts are insufficient.","why":"Asks for version, platform and task context in documentation searches.","limit":"This is a retrieval workflow, not an implementation validator; official documentation still needs to match the installed version and target environment.","compatibility":["Microsoft Learn MCP-compatible hosts","Node/npm for the mslearn fallback"],"language":[],"transports":[],"license":"MIT","access":"Send documentation queries to Microsoft Learn","cost":"The MIT-licensed instructions describe no separate paid data subscription; the agent and chosen tool host may have their own costs.","command":"npx skills add https://github.com/microsoft/skills/tree/96bbd0043d58468fe02090a1691a138e1ef0182b/.github/skills/microsoft-docs","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/microsoft/skills/tree/96bbd0043d58468fe02090a1691a138e1ef0182b/.github/skills/microsoft-docs","reviewedAt":"2026-09-21","sourceCount":5,"download":false,"hasConfig":false},{"id":"microsoft-wiki-researcher","name":"Microsoft Wiki Researcher","publisher":"Microsoft","category":"Research and documentation","tags":["codebase-research","architecture","documentation","mermaid"],"summary":"Traces architecture and data flow through source code to produce an explanation with file references, diagrams and stated uncertainties.","why":"Requires code-reading before architectural claims and traces actual calls and data flow rather than trusting directory names.","limit":"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.","compatibility":["GitHub Copilot"],"language":[],"transports":[],"license":"MIT","access":"Repository source research","cost":"MIT-licensed instructions; the consuming agent and any optional documentation services are separate.","command":"npx skills add https://github.com/microsoft/skills/tree/96bbd0043d58468fe02090a1691a138e1ef0182b/.github/plugins/deep-wiki/skills/wiki-researcher","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/microsoft/skills/tree/96bbd0043d58468fe02090a1691a138e1ef0182b/.github/plugins/deep-wiki/skills/wiki-researcher","reviewedAt":"2026-09-21","sourceCount":6,"download":false,"hasConfig":false},{"id":"openai-agents-sdk","name":"OpenAI Agents SDK Workflow","publisher":"OpenAI","category":"AI application development","tags":["openai","agents-sdk","tools","evaluations","local-deployment"],"summary":"Builds a small Agents SDK application around an explicit workflow contract, then checks the real agent path and optional local deployment.","why":"Starts with a single agent and adds tools, delegation or sandboxing only when the application needs them.","limit":"A companion credential gate can pause work before implementation even when a key already exists.","compatibility":["Codex OpenAI Developers plugin","Python or TypeScript Agents SDK","Local Docker or process deployment through the documented manager"],"language":[],"transports":[],"license":"Proprietary (declared in plugin manifest)","access":"Read and write application/evaluation files","cost":"API usage is separate from Codex access; local deployment consumes host compute and the proprietary plugin follows its service terms.","command":null,"installUrl":"https://github.com/openai/plugins/tree/1dc195897af4161d039b80d8471ec0a10c9bbc89/plugins/openai-developers","sourceUrl":"https://github.com/openai/plugins/tree/1dc195897af4161d039b80d8471ec0a10c9bbc89/plugins/openai-developers/skills/agents-sdk","reviewedAt":"2026-09-21","sourceCount":6,"download":false,"hasConfig":false},{"id":"openai-openai-api-troubleshooting","name":"OpenAI API Troubleshooting","publisher":"OpenAI","category":"AI application development","tags":["openai","api","errors","rate-limits","authentication"],"summary":"Classifies a failed OpenAI request using its actual transport or API error and routes credentials, billing, throttling and access issues separately.","why":"Distinguishes exhausted quota from ordinary rate limiting even when the HTTP status is the same.","limit":"It relies on companion documentation and credential skills; it does not provision or rotate keys itself.","compatibility":["Codex OpenAI Developers plugin","Applications making OpenAI API requests"],"language":[],"transports":[],"license":"Proprietary (declared in plugin manifest)","access":"Inspect redacted request errors and relevant configuration","cost":"The proprietary plugin follows Codex terms; request retries can consume API usage and ChatGPT subscriptions do not establish API credit.","command":null,"installUrl":"https://github.com/openai/plugins/tree/1dc195897af4161d039b80d8471ec0a10c9bbc89/plugins/openai-developers","sourceUrl":"https://github.com/openai/plugins/tree/1dc195897af4161d039b80d8471ec0a10c9bbc89/plugins/openai-developers/skills/openai-api-troubleshooting","reviewedAt":"2026-09-21","sourceCount":6,"download":false,"hasConfig":false},{"id":"openai-threat-model","name":"OpenAI Codex Security Threat Model","publisher":"OpenAI","category":"Security","tags":["threat-modeling","codex-security","trust-boundaries","source-review"],"summary":"Creates or reuses a repository threat model bound to the actual target and revision, preserving supplied context and explicit review gaps.","why":"Binds reusable models to repository/version identity and avoids mixing scan-specific context into a shared cache.","limit":"This is one phase in the Codex Security plugin, not a standalone full security scan.","compatibility":["Codex Security plugin in a supported Codex host"],"language":[],"transports":[],"license":"Proprietary (declared in plugin manifest)","access":"Read authorized source and security-policy files","cost":"The proprietary plugin follows the applicable Codex service terms; this source does not establish a separate per-skill charge.","command":null,"installUrl":"https://github.com/openai/plugins/tree/1dc195897af4161d039b80d8471ec0a10c9bbc89/plugins/codex-security","sourceUrl":"https://github.com/openai/plugins/tree/1dc195897af4161d039b80d8471ec0a10c9bbc89/plugins/codex-security/skills/threat-model","reviewedAt":"2026-09-21","sourceCount":7,"download":false,"hasConfig":false},{"id":"openai-jupyter-notebooks","name":"OpenAI Data Analytics Notebooks","publisher":"OpenAI","category":"Data and research","tags":["jupyter","sql","python","reproducibility","analytics"],"summary":"Turns SQL or Python analysis into a traceable notebook whose conclusions are tied to executed outputs and stated assumptions.","why":"Records query links, input versions, filters and cohort definitions next to the analysis.","limit":"Warehouse and operational-log placeholders depend on the host’s configured connectors; exports or supplied data are fallback paths.","compatibility":["Codex Data Analytics plugin","Python/Jupyter and optionally SQL data connectors"],"language":[],"transports":[],"license":"Proprietary (declared in plugin manifest)","access":"Read data and write notebook artifacts","cost":"The proprietary plugin follows its host service terms; warehouse queries, notebook compute and other connected services can incur separate charges.","command":null,"installUrl":"https://github.com/openai/plugins/tree/1dc195897af4161d039b80d8471ec0a10c9bbc89/plugins/data-analytics","sourceUrl":"https://github.com/openai/plugins/tree/1dc195897af4161d039b80d8471ec0a10c9bbc89/plugins/data-analytics/skills/jupyter-notebooks","reviewedAt":"2026-09-21","sourceCount":5,"download":false,"hasConfig":false},{"id":"openai-evaluate-skill","name":"OpenAI Evaluate Skill","publisher":"OpenAI","category":"Agent development","tags":["skills","evaluation","token-usage","plugin-eval"],"summary":"Connects a local skill review to structural checks, budget explanations and an explicitly separate live benchmark workflow.","why":"Distinguishes static instruction-size estimates from observed usage collected by real agent runs.","limit":"Static scores and budget bands are tool heuristics, not proof of task quality or safety.","compatibility":["Codex plugin-eval plugin","Local Node.js CLI with the upstream-required runtime version"],"language":[],"transports":[],"license":"MIT (declared in plugin manifest)","access":"Read target skill/plugin files and write local reports","cost":"MIT is declared in the plugin manifest; static inspection runs locally, while live benchmarks use the configured Codex service.","command":null,"installUrl":"https://github.com/openai/plugins/blob/1dc195897af4161d039b80d8471ec0a10c9bbc89/plugins/plugin-eval/README.md","sourceUrl":"https://github.com/openai/plugins/tree/1dc195897af4161d039b80d8471ec0a10c9bbc89/plugins/plugin-eval/skills/evaluate-skill","reviewedAt":"2026-09-21","sourceCount":8,"download":false,"hasConfig":false},{"id":"remotion-remotion-best-practices","name":"Remotion Video Workflows","publisher":"Remotion","category":"Creative production","tags":["video","remotion","react","rendering","captions"],"summary":"Routes video work to focused Remotion guides for creation, preview, rendering, media and reusable video applications.","why":"Keeps new-project scaffolding separate from adding a composition to an existing project.","limit":"This is a router into a larger reference package, so copying the definition alone loses the working guidance.","compatibility":["Claude Code, Codex, Kimi Code and Cursor are named by the publisher","Node.js/Git and a Remotion React project"],"language":[],"transports":[],"license":"No redistribution license found","access":"Create or edit React video code and install project dependencies","cost":"Skill repository installation is documented without a price; Remotion runtime licensing and local or cloud rendering are separate considerations.","command":"npx skills add https://github.com/remotion-dev/skills/tree/bbb139d5ba3709b1ffeb27184e9579c681230a08/skills/remotion-best-practices","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/remotion-dev/skills/tree/bbb139d5ba3709b1ffeb27184e9579c681230a08/skills/remotion-best-practices","reviewedAt":"2026-09-21","sourceCount":6,"download":false,"hasConfig":false},{"id":"getsentry-document-api-endpoint","name":"Sentry API Endpoint Documentation","publisher":"Sentry","category":"Research and documentation","tags":["openapi","django-rest-framework","sentry","api-documentation"],"summary":"Aligns a Sentry API endpoint’s runtime response, TypedDict definitions and drf-spectacular OpenAPI schema.","why":"Checks runtime serialization against types and schema, including the difference between an absent field and a nullable one.","limit":"The file paths, ownership checks and validation commands are specific to Sentry; this is not a drop-in guide for every Django API.","compatibility":["Claude Code","Cursor","Cline","GitHub Copilot"],"language":[],"transports":[],"license":"Apache-2.0","access":"Sentry source and generated API documentation","cost":"Apache-licensed instructions; local development resources, agent calls and any hosted Sentry access are separate.","command":"npx skills add https://github.com/getsentry/skills/tree/c2f99a5b04b4cd992ec3022d7c2c3e23e938d241/skills/document-api-endpoint","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/getsentry/skills/tree/c2f99a5b04b4cd992ec3022d7c2c3e23e938d241/skills/document-api-endpoint","reviewedAt":"2026-09-21","sourceCount":7,"download":false,"hasConfig":false},{"id":"getsentry-find-bugs","name":"Sentry Find Bugs","publisher":"Sentry","category":"Testing and reliability","tags":["code-review","git-diff","security-review","github"],"summary":"Reviews a branch diff against surrounding code and existing tests, reporting only substantiated issues and explicit coverage limits.","why":"Requires the complete diff to be read before findings and follows changed behavior into surrounding implementations and tests.","limit":"The initial command compares committed branch history and omits uncommitted edits; inspect those separately if they are in scope.","compatibility":["Claude Code","Cursor","Cline","GitHub Copilot"],"language":[],"transports":[],"license":"Apache-2.0","access":"Local git and GitHub repository metadata","cost":"Apache-licensed instructions; agent usage and any associated private-repository access follow their respective services.","command":"npx skills add https://github.com/getsentry/skills/tree/c2f99a5b04b4cd992ec3022d7c2c3e23e938d241/skills/find-bugs","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/getsentry/skills/tree/c2f99a5b04b4cd992ec3022d7c2c3e23e938d241/skills/find-bugs","reviewedAt":"2026-09-21","sourceCount":6,"download":false,"hasConfig":false},{"id":"mattpocock-to-tickets","name":"Specification to Dependency-Aware Tickets","publisher":"Matt Pocock","category":"Planning and delivery","tags":["tickets","dependencies","planning","github","gitlab"],"summary":"Splits an agreed plan into small vertical slices, with explicit blocking relationships and a review before publication.","why":"Asks for user agreement on the proposed breakdown before creating the tickets.","limit":"Ticket publication is not transactional: partial failures or repeated runs can leave duplicates and incomplete dependency links.","compatibility":["Claude Code","Codex"],"language":[],"transports":[],"license":"MIT","access":"Repository instructions and host-provided tools","cost":"MIT-licensed instructions; agent and tracker account costs remain separate.","command":"npx skills add https://github.com/mattpocock/skills/tree/c55ee46073ed923f86ce59a5eb3b6d895095d1b7 --skill to-tickets --skill setup-matt-pocock-skills","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/mattpocock/skills/blob/c55ee46073ed923f86ce59a5eb3b6d895095d1b7/skills/engineering/to-tickets/SKILL.md","reviewedAt":"2026-09-22","sourceCount":14,"download":false,"hasConfig":false},{"id":"supabase-supabase-postgres-best-practices","name":"Supabase Postgres Best Practices","publisher":"Supabase","category":"Databases","tags":["postgresql","sql","indexes","row-level-security"],"summary":"Connects Postgres schema and query decisions to worked SQL examples, connection guidance and row-level security checks.","why":"Pairs incorrect and corrected SQL with query-plan examples instead of offering only generic database advice.","limit":"Illustrative speedups and blanket indexing rules are not measurements of your workload; inspect actual plans and write costs.","compatibility":["Agent Skills-compatible coding agents","PostgreSQL; Supabase-specific examples are identified"],"language":[],"transports":[],"license":"MIT","access":"Database files; optional database access","cost":"The instruction package is MIT-licensed; database hosting, query execution and agent usage have their own costs.","command":"npx skills add https://github.com/supabase/agent-skills/tree/8331f910845103c08d51f6ca1d86ebb7d1f745e3/skills/supabase-postgres-best-practices","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/supabase/agent-skills/tree/8331f910845103c08d51f6ca1d86ebb7d1f745e3/skills/supabase-postgres-best-practices","reviewedAt":"2026-09-21","sourceCount":7,"download":false,"hasConfig":false},{"id":"obra-receiving-code-review","name":"Superpowers Receiving Code Review","publisher":"Jesse Vincent / Superpowers","category":"Testing and reliability","tags":["review-feedback","regressions","verification","collaboration"],"summary":"Checks review feedback against the code and project constraints before making and testing each requested change.","why":"Treats reviewer suggestions as hypotheses to verify, with explicit checks for existing behavior, platform constraints and unused functionality.","limit":"Its conversational tone rules are a style preference, and its pause-on-ambiguity rule may be too restrictive for independent review items.","compatibility":["Claude Code","Codex"],"language":[],"transports":[],"license":"MIT","access":"Review comments, code and tests","cost":"MIT-licensed instructions; agent, test infrastructure and optional GitHub service usage are separate.","command":"npx skills add https://github.com/obra/superpowers/tree/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/receiving-code-review","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/obra/superpowers/tree/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/receiving-code-review","reviewedAt":"2026-09-21","sourceCount":6,"download":false,"hasConfig":false},{"id":"obra-systematic-debugging","name":"Superpowers Systematic Debugging","publisher":"Jesse Vincent / Superpowers","category":"Testing and reliability","tags":["debugging","root-cause","reproduction","regressions"],"summary":"Moves debugging from reproducible evidence through a single hypothesis to a verified fix, with a stop point for repeated failed attempts.","why":"Asks for evidence at component boundaries and backward tracing of bad values before proposing a patch.","limit":"The bundled polluter helper assumes npm tests, hides their output and swallows their failing exit statuses.","compatibility":["Superpowers-supported coding agents","The optional polluter helper assumes Bash and npm"],"language":[],"transports":[],"license":"MIT","access":"Read source, logs and recent changes","cost":"The MIT-licensed process uses the configured agent and local or external test resources.","command":"npx skills add https://github.com/obra/superpowers/tree/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/systematic-debugging","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/obra/superpowers/tree/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/systematic-debugging","reviewedAt":"2026-09-21","sourceCount":7,"download":false,"hasConfig":false},{"id":"obra-test-driven-development","name":"Superpowers Test-Driven Development","publisher":"Jesse Vincent / Superpowers","category":"Testing and reliability","tags":["tdd","regression-tests","test-design","superpowers"],"summary":"Makes an observed failing behavior test the entry point for implementation and checks that assertions can detect real production mistakes.","why":"Requires verifying why a test fails before changing implementation, then running the project suite after the fix.","limit":"The workflow is deliberately prescriptive: it tells an agent to discard implementation written before tests and seek permission for exceptions.","compatibility":["Superpowers-supported coding agents","Project-specific test runners"],"language":[],"transports":[],"license":"MIT","access":"Repository edits and test commands","cost":"The skill is MIT-licensed; agent calls, local test resources and external test services remain separate.","command":"npx skills add https://github.com/obra/superpowers/tree/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/test-driven-development","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/obra/superpowers/tree/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/test-driven-development","reviewedAt":"2026-09-21","sourceCount":6,"download":false,"hasConfig":false},{"id":"obra-verification-before-completion","name":"Superpowers Verification Before Completion","publisher":"Jesse Vincent / Superpowers","category":"Testing and reliability","tags":["verification","evidence","builds","agent-review"],"summary":"Requires a fresh command result or direct check for each completion claim and distinguishes passing tests from fulfilling requirements.","why":"Maps common claims to appropriate evidence, including compiler/build status, original bug reproduction and requirements checks.","limit":"This is a behavioral checklist, not an automatic enforcement mechanism or runtime test harness.","compatibility":["Superpowers-supported coding agents"],"language":[],"transports":[],"license":"MIT","access":"Project checks and result inspection","cost":"The MIT-licensed instructions have no separate service fee; verification can consume agent, compute or external CI resources.","command":"npx skills add https://github.com/obra/superpowers/tree/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/verification-before-completion","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/obra/superpowers/tree/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/verification-before-completion","reviewedAt":"2026-09-21","sourceCount":5,"download":false,"hasConfig":false},{"id":"obra-writing-plans","name":"Superpowers Writing Plans","publisher":"Jesse Vincent / Superpowers","category":"Research and documentation","tags":["implementation-planning","specifications","tests","handoff"],"summary":"Turns an agreed specification into file-specific implementation tasks with verification steps and a structured plan review.","why":"Makes each task name concrete files, expected behavior and meaningful failing/passing checks rather than leaving implementation placeholders.","limit":"Detailed code in a plan can become stale as the repository changes; planned checks are not evidence that tests have run.","compatibility":["Claude Code","Codex"],"language":[],"transports":[],"license":"MIT","access":"Repository planning and review","cost":"MIT-licensed instructions; planning and review use the consuming agent or API.","command":"npx skills add https://github.com/obra/superpowers/tree/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/writing-plans","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/obra/superpowers/tree/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/writing-plans","reviewedAt":"2026-09-21","sourceCount":7,"download":false,"hasConfig":false},{"id":"svelte-svelte-core-bestpractices","name":"Svelte Core Best Practices","publisher":"Svelte","category":"Framework development","tags":["svelte","reactivity","components","ssr","performance"],"summary":"Svelte-maintained guidance for reactivity, component composition and integration with browser APIs.","why":"Explains when to derive state instead of synchronizing it with effects, and when reactive wrappers or subscriptions are needed.","limit":"The references span several Svelte releases and include experimental async behavior. Check the installed compiler version and required flags before applying an example.","compatibility":["Claude Code","Codex","GitHub Copilot CLI","OpenCode"],"language":[],"transports":[],"license":"MIT","access":"Repository instructions and host-provided tools","cost":"MIT-licensed instructions; host/model usage and project tooling remain separate.","command":"npx skills add https://github.com/sveltejs/ai-tools/tree/5c15fbcb5b630ac8ce0281ee1782fc2056fab853/tools/skills/svelte-core-bestpractices --skill svelte-core-bestpractices","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/sveltejs/ai-tools/blob/5c15fbcb5b630ac8ce0281ee1782fc2056fab853/tools/skills/svelte-core-bestpractices/SKILL.md","reviewedAt":"2026-09-22","sourceCount":16,"download":false,"hasConfig":false},{"id":"trailofbits-audit-context-building","name":"Trail of Bits Audit Context Building","publisher":"Trail of Bits","category":"Security","tags":["audit","code-understanding","invariants","call-paths"],"summary":"Builds a cited dossier of function invariants, assumptions and dependencies before a separate vulnerability-hunting pass.","why":"Follows callees and unsuccessful paths instead of trusting names such as validate or authorize.","limit":"The skill is a router into a plugin workflow and named function analyzer; a copied standalone SKILL.md is insufficient.","compatibility":["Trail of Bits plugin hosts with Workflow/Task and schema-bound agent support"],"language":[],"transports":[],"license":"CC-BY-SA-4.0","access":"Read repository functions and dependencies","cost":"The package is CC-BY-SA-licensed; delegated analysis uses the chosen agent service and can consume substantial context.","command":null,"installUrl":"https://github.com/trailofbits/skills/blob/123037ec8aed26f0d86327cc39137ee5043e5deb/README.md","sourceUrl":"https://github.com/trailofbits/skills/tree/123037ec8aed26f0d86327cc39137ee5043e5deb/plugins/audit-context-building/skills/audit-context-building","reviewedAt":"2026-09-21","sourceCount":8,"download":false,"hasConfig":false},{"id":"trailofbits-differential-review","name":"Trail of Bits Differential Security Review","publisher":"Trail of Bits","category":"Security","tags":["diff-review","git-history","security","regressions"],"summary":"Reviews security-relevant changes against their baseline, removed protections, callers and concrete attacker scenarios.","why":"Uses git history to ask why a removed check existed and whether a previous fix is being undone.","limit":"The methodology includes checking out the baseline and head; use a suitable worktree so the review does not disrupt uncommitted work.","compatibility":["Claude Code and documented Codex plugin compatibility","Git repositories with a meaningful baseline"],"language":[],"transports":[],"license":"CC-BY-SA-4.0","access":"Read diffs, history, callers and tests","cost":"The package uses CC-BY-SA terms; agent review and any validation infrastructure are separate costs.","command":null,"installUrl":"https://github.com/trailofbits/skills/blob/123037ec8aed26f0d86327cc39137ee5043e5deb/README.md","sourceUrl":"https://github.com/trailofbits/skills/tree/123037ec8aed26f0d86327cc39137ee5043e5deb/plugins/differential-review/skills/differential-review","reviewedAt":"2026-09-21","sourceCount":7,"download":false,"hasConfig":false},{"id":"trailofbits-mutation-testing","name":"Trail of Bits Mutation Analysis","publisher":"Trail of Bits","category":"Testing and reliability","tags":["mutation-testing","test-gaps","mewt","muton","security-testing"],"summary":"Interprets mutation campaign results and turns survivors into qualified test-gap reports or separately reproduced bug findings.","why":"Separates test-gap analysis from bug hunting, so an uncaught mutation is not automatically presented as a vulnerability.","limit":"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.","compatibility":["Claude Code","Codex"],"language":[],"transports":[],"license":"CC-BY-SA-4.0","access":"Source, tests and mutation campaign data","cost":"CC BY-SA 4.0-licensed skill collection; mutation-engine terms, repeated local/CI test compute and agent usage remain separate.","command":"npx skills add https://github.com/trailofbits/skills/tree/32e34f8173796e3566a51aee877dc96bc5191f64/plugins/mutation-testing/skills/mutation-testing","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/trailofbits/skills/tree/32e34f8173796e3566a51aee877dc96bc5191f64/plugins/mutation-testing/skills/mutation-testing","reviewedAt":"2026-09-21","sourceCount":15,"download":false,"hasConfig":false},{"id":"trailofbits-property-based-testing","name":"Trail of Bits Property-Based Testing","publisher":"Trail of Bits","category":"Testing and reliability","tags":["property-testing","hypothesis","invariants","shrinking"],"summary":"Chooses meaningful invariants and generators for tests that explore an input domain, while rejecting tautological or vacuous assertions.","why":"Explains how tests can pass while restating implementation or filtering away nearly every input.","limit":"Property selection still needs a valid specification; an incorrect invariant can generate misleading failures.","compatibility":["Agent Skills-compatible coding agents","Property-testing libraries documented by the complete plugin"],"language":[],"transports":[],"license":"CC-BY-SA-4.0","access":"Read and edit test code","cost":"The skill is CC-BY-SA-licensed; generated test runs use project compute and the consuming agent.","command":null,"installUrl":"https://github.com/trailofbits/skills/blob/123037ec8aed26f0d86327cc39137ee5043e5deb/README.md","sourceUrl":"https://github.com/trailofbits/skills/tree/123037ec8aed26f0d86327cc39137ee5043e5deb/plugins/property-based-testing/skills/property-based-testing","reviewedAt":"2026-09-21","sourceCount":6,"download":false,"hasConfig":false},{"id":"trailofbits-sharp-edges","name":"Trail of Bits Sharp Edges","publisher":"Trail of Bits","category":"Security","tags":["api-design","secure-defaults","configuration","misuse-resistance"],"summary":"Examines APIs and configuration for cases where ordinary developer mistakes can disable a security boundary.","why":"Looks at zero, empty, negative and mixed-up values rather than only intended happy-path usage.","limit":"This is a design-review method, not a general implementation bug scanner.","compatibility":["Trail of Bits plugin hosts","APIs and configuration source available for inspection"],"language":[],"transports":[],"license":"CC-BY-SA-4.0","access":"Read and search source, schemas and examples","cost":"The CC-BY-SA instruction package is separate from the chosen agent’s usage costs.","command":null,"installUrl":"https://github.com/trailofbits/skills/blob/123037ec8aed26f0d86327cc39137ee5043e5deb/README.md","sourceUrl":"https://github.com/trailofbits/skills/tree/123037ec8aed26f0d86327cc39137ee5043e5deb/plugins/sharp-edges/skills/sharp-edges","reviewedAt":"2026-09-21","sourceCount":6,"download":false,"hasConfig":false},{"id":"vercel-labs-react-best-practices","name":"Vercel React Best Practices","publisher":"Vercel","category":"Web development","tags":["react","nextjs","performance","bundles"],"summary":"Organizes React and Next.js performance reviews around request waterfalls, bundles, server work and rendering costs.","why":"Pairs rules with incorrect and corrected code, making recommendations easier to inspect.","limit":"Published impact labels and example speedups are not measurements of your application.","compatibility":["Agent Skills-compatible agents","React and Next.js projects"],"language":[],"transports":[],"license":"MIT (declared in upstream README)","access":"Read and edit frontend/server code","cost":"MIT is declared upstream; the instructions add no hosted service, while agent and development tooling costs remain separate.","command":"npx skills add https://github.com/vercel-labs/agent-skills/tree/063bee94c3f4df8453406c830b0a7df0f2860278/skills/react-best-practices","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/vercel-labs/agent-skills/tree/063bee94c3f4df8453406c830b0a7df0f2860278/skills/react-best-practices","reviewedAt":"2026-09-21","sourceCount":7,"download":false,"hasConfig":false},{"id":"vercel-labs-composition-patterns","name":"Vercel React Composition Patterns","publisher":"Vercel","category":"Web development","tags":["react","component-design","context","architecture"],"summary":"Replaces growing boolean-mode APIs with explicit component composition and provider-owned state contracts.","why":"Shows complete before-and-after component variants rather than only naming the compound-component pattern.","limit":"Context and compound components can add indirection to a simple component; apply the pattern where variation warrants it.","compatibility":["Agent Skills-compatible agents","React; newer API guidance requires a matching React version"],"language":[],"transports":[],"license":"MIT (declared in upstream README)","access":"Read and refactor component APIs and state providers","cost":"MIT is declared upstream; this is an instruction package without an additional hosted service.","command":"npx skills add https://github.com/vercel-labs/agent-skills/tree/063bee94c3f4df8453406c830b0a7df0f2860278/skills/composition-patterns","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/vercel-labs/agent-skills/tree/063bee94c3f4df8453406c830b0a7df0f2860278/skills/composition-patterns","reviewedAt":"2026-09-21","sourceCount":7,"download":false,"hasConfig":false},{"id":"vercel-labs-react-native-skills","name":"Vercel React Native Skills","publisher":"Vercel","category":"Mobile development","tags":["react-native","expo","mobile","animations"],"summary":"Provides React Native and Expo patterns for scrolling, animations, native navigation and dependency layout.","why":"Includes worked mobile-specific examples rather than reusing browser performance guidance.","limit":"The list rule recommends virtualization even for short lists; that is a prescriptive default, not a measured requirement for every screen.","compatibility":["Agent Skills-compatible agents","React Native and Expo"],"language":[],"transports":[],"license":"MIT (declared in upstream README)","access":"Read and edit mobile application code","cost":"MIT is declared upstream; simulators, builds, agent usage and external mobile services remain separate.","command":"npx skills add https://github.com/vercel-labs/agent-skills/tree/063bee94c3f4df8453406c830b0a7df0f2860278/skills/react-native-skills","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/vercel-labs/agent-skills/tree/063bee94c3f4df8453406c830b0a7df0f2860278/skills/react-native-skills","reviewedAt":"2026-09-21","sourceCount":7,"download":false,"hasConfig":false},{"id":"vercel-labs-web-design-guidelines","name":"Vercel Web Interface Guidelines","publisher":"Vercel","category":"Design and interfaces","tags":["accessibility","forms","ui-review","web"],"summary":"Reviews interface code against a freshly fetched guideline set and returns file-specific findings.","why":"Covers concrete interaction details such as focus visibility, form labeling, asynchronous announcements and URL state.","limit":"The skill fetches a mutable external rules file at runtime; pinning the skill alone does not freeze the guidance.","compatibility":["Agents with web retrieval and repository read access","Web application source"],"language":[],"transports":[],"license":"MIT (declared in upstream README)","access":"Fetch public guidelines","cost":"MIT is declared for the skill repository; the workflow uses the configured agent and retrieval tooling.","command":"npx skills add https://github.com/vercel-labs/agent-skills/tree/063bee94c3f4df8453406c830b0a7df0f2860278/skills/web-design-guidelines","installUrl":"https://github.com/vercel-labs/skills/blob/7407f3893ad4dceab546ac002c3ef806e4000c73/README.md","sourceUrl":"https://github.com/vercel-labs/agent-skills/tree/063bee94c3f4df8453406c830b0a7df0f2860278/skills/web-design-guidelines","reviewedAt":"2026-09-21","sourceCount":6,"download":false,"hasConfig":false}]}