{"version":1,"reviewedAt":"2026-10-08","recipes":[{"id":"review-a-change","title":"Review a change before merging","category":"test","summary":"Separate bug finding from test-coverage review, then reconcile the evidence.","outcome":"A review with file references, reproducible concerns and an explicit list of untested paths.","inputs":["A pinned commit or pull-request diff.","The expected behaviour and relevant tests."],"parallel":[{"title":"Bug review","detail":"Inspect the same frozen diff for correctness; cite files and lines."},{"title":"Test review","detail":"Inspect the tests independently; name missing behaviours and reproduction steps."}],"steps":["Configure read-only GitHub toolsets, retrieve a fixed revision and define the review scope. Keep the original requirements next to the diff.","Run independent bug and test reviews against that same revision. Do not let one reviewer supply the other’s verdict.","Reconcile overlapping findings, verify the material ones, and write a single review. Make changes only after that review is checked."],"boundaries":["Choose a host for each stage and verify its tool mapping. Pass evidence explicitly between stages; the listed resources do not automatically configure or invoke one another.","A compatible host and GitHub authentication are separate setup steps. Definitions do not configure MCP tool names automatically.","Request only repository access needed for the review. Do not submit comments, change issues or workflows, edit files or merge during evidence collection. Enable write tools only for a separately authorised task."],"deliverables":["Frozen review scope","Finding and reproduction ledger","Test-gap map","Merge recommendation with unresolved items"],"checks":["Both reviewers identify the same base and head revisions.","The diff includes deleted hunks; uncommitted changes are explicitly included or excluded.","Each material finding has a reproducible witness or is labelled unverified.","Test execution, static inspection and untested paths are reported separately."],"template":{"title":"Change-review handoff","sections":[{"heading":"Scope","body":"Base revision: ___\nHead revision: ___\nRequirement/source: ___\nUncommitted changes in scope: ___\nExcluded paths and reason: ___"},{"heading":"Independent findings","body":"| Reviewer | File and line | Behaviour at risk | Evidence or reproduction | Status |\n| --- | --- | --- | --- | --- |\n| ___ | ___ | ___ | ___ | not checked |"},{"heading":"Test coverage","body":"Contract: ___\nExisting assertion: ___\nMissing failure case: ___\nCommand, exit status and saved output: ___\nTests not run and why: ___"},{"heading":"Decision","body":"Confirmed findings: ___\nDisagreements and resolution: ___\nRemaining blockers: ___\nRecommendation and its scope: ___\nMerge action owner: ___"}]},"resources":[{"kind":"skills","id":"getsentry-find-bugs","purpose":"Inspect the change for concrete bugs.","name":"Sentry Find Bugs","href":"/skills/getsentry-find-bugs/","compatibility":["Claude Code","Cursor","Cline","GitHub Copilot"],"limitation":"The initial command compares committed branch history and omits uncommitted edits; inspect those separately if they are in scope.","reviewedAt":"2026-09-21","revision":"c2f99a5b04b4cd992ec3022d7c2c3e23e938d241","definitionSha256":null,"sourceUrl":"https://github.com/getsentry/skills/tree/c2f99a5b04b4cd992ec3022d7c2c3e23e938d241/skills/find-bugs","permissions":["Read branch diffs, source files and tests","Query repository metadata through GitHub CLI; the skill explicitly says not to edit files"],"cost":"Apache-licensed instructions; agent usage and any associated private-repository access follow their respective services.","license":{"name":"Apache-2.0","url":"https://github.com/getsentry/skills/blob/c2f99a5b04b4cd992ec3022d7c2c3e23e938d241/LICENSE"}},{"kind":"agents","id":"anthropic-pr-test-analyzer","purpose":"Evaluate test coverage and gaps.","name":"Pull Request Test Analyzer","href":"/agents/anthropic-pr-test-analyzer/","compatibility":["Claude Code subagents"],"limitation":"Its internal numerical criticality rubric is a prioritization instruction, not a measured quality score or a catalogue rating.","reviewedAt":"2026-09-21","revision":"c447c3207a425bc4e2a0d068435f64b0477ae981","definitionSha256":"fcb1cde9ba7b21694b508766a8d6a79bc91bed9982f828f816210059934f46b4","sourceUrl":"https://raw.githubusercontent.com/anthropics/claude-plugins-official/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/pr-review-toolkit/agents/pr-test-analyzer.md","permissions":["No tools are restricted in frontmatter; access is inherited from the host.","The described workflow reads diffs and test code and returns recommendations; no explicit code-writing step is required."],"cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","license":{"name":"Apache-2.0","url":"https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/pr-review-toolkit/LICENSE"}},{"kind":"mcp-servers","id":"github","purpose":"Retrieve authorised repository and pull-request context.","name":"GitHub MCP Server","href":"/mcp-servers/github/","compatibility":["Remote-capable MCP clients; the example below is specifically VS Code configuration.","Local stdio clients using the documented binary or container."],"limitation":"Write-capable toolsets can change repositories, issues, pull requests and workflows; read-only mode is an explicit configuration choice.","reviewedAt":"2026-09-21","revision":"85598ba6e1256f7ebf4867b95d63b833c4549264","definitionSha256":null,"sourceUrl":"https://github.com/github/github-mcp-server","permissions":["Reads private repository content allowed by the authenticated identity.","Enabled tools may create or modify issues, pull requests, files, releases and workflows."],"cost":"GitHub account entitlements and API/service limits apply; the local source licence does not include a model subscription.","license":{"name":"MIT","url":"https://github.com/github/github-mcp-server/blob/85598ba6e1256f7ebf4867b95d63b833c4549264/LICENSE"}}]},{"id":"debug-a-browser-regression","title":"Investigate a browser regression","category":"test","summary":"Collect a reproducible browser trace and independently check the suspected change.","outcome":"A minimal reproduction with observed results, console or trace evidence, and a verified fix proposal.","inputs":["A local or authorised staging URL.","Reproduction steps, expected behaviour and the suspected revision."],"parallel":[{"title":"Source investigation","detail":"Inspect the suspect change without controlling the shared browser."},{"title":"Reproduction design","detail":"Draft the expected assertions from the requirements and supplied reproduction."}],"steps":["Use a temporary browser profile, such as Chrome DevTools MCP with --isolated, without production credentials. Record the browser and application context and confirm the application is ready; an open TCP port alone does not establish readiness.","Collect browser evidence in one controlled session. Source review and assertion design can run separately while that session is owned by one operator.","Apply a reviewed change, then repeat the original reproduction and check nearby behaviour. State what was actually tested."],"boundaries":["Choose a host for each stage and verify its tool mapping. Pass evidence explicitly between stages; the listed resources do not automatically configure or invoke one another.","The supplied agent’s tool aliases may require adaptation to your host and installed browser server.","Do not let parallel workers drive the same browser session. Browser traces can contain private page content; inspect them before sharing."],"deliverables":["Minimal reproduction","Browser evidence bundle","Source-linked hypothesis","Before/after regression receipt"],"checks":["The URL, application revision, browser version and viewport are recorded.","The original steps reproduce the symptom before the fix.","One operator owns the browser session and traces are checked for private data.","The original failure and a nearby unaffected behaviour are rerun after the change."],"template":{"title":"Browser-regression worksheet","sections":[{"heading":"Reproduction","body":"Revision and URL: ___\nBrowser/version and viewport: ___\nInitial storage/login state: ___\nSteps: ___\nExpected: ___\nObserved: not run"},{"heading":"Evidence","body":"Screenshot/trace paths: ___\nConsole/network event and timestamp: ___\nApplication readiness check: ___\nRedactions made: ___"},{"heading":"Hypothesis","body":"Suspect source and line: ___\nMechanism explaining the observation: ___\nA test that would disprove it: ___\nAlternative explanation: ___"},{"heading":"Retest","body":"Fix revision: ___\nOriginal reproduction result: not run\nNeighbouring behaviour result: not run\nCommand/exit or browser assertion evidence: ___\nUntested browsers or devices: ___"}]},"resources":[{"kind":"skills","id":"anthropics-webapp-testing","purpose":"Structure browser observations and assertions.","name":"Anthropic Webapp Testing","href":"/skills/anthropics-webapp-testing/","compatibility":["Claude Code","Python Playwright"],"limitation":"The server helper checks only whether a TCP port accepts a connection, not whether the expected application is healthy.","reviewedAt":"2026-09-21","revision":"34040c9c568585f6929bedeaad110ad08f079624","definitionSha256":null,"sourceUrl":"https://github.com/anthropics/skills/tree/34040c9c568585f6929bedeaad110ad08f079624/skills/webapp-testing","permissions":["Launch and terminate development-server processes","Execute a user-selected automation command","Read rendered pages and write screenshots or logs"],"cost":"The example skill is Apache-licensed; browser compute, the consuming agent and any services contacted by the tested app have separate costs.","license":{"name":"Apache-2.0","url":"https://github.com/anthropics/skills/blob/34040c9c568585f6929bedeaad110ad08f079624/skills/webapp-testing/LICENSE.txt"}},{"kind":"agents","id":"github-devtools-regression-investigator","purpose":"Investigate the regression using browser evidence.","name":"Devtools Regression Investigator","href":"/agents/github-devtools-regression-investigator/","compatibility":["GitHub Copilot custom agents in VS Code"],"limitation":"Chrome DevTools MCP and optional Playwright are described but not installed or explicitly named in the tool allowlist; configure the required browser tools separately.","reviewedAt":"2026-09-21","revision":"ad4c196b933c5ca7f82a5ba78969ddcd2603ba80","definitionSha256":"3abbdc407b6a16d0df387ed1e4257668e5b031ddb9ebf870059df73b9c69e0fb","sourceUrl":"https://raw.githubusercontent.com/github/awesome-copilot/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/devtools-regression-investigator.agent.md","permissions":["Instructed: use listed Copilot tools including runCommands, runTests, runTasks, openSimpleBrowser, fetch, codebase search; prefer Chrome DevTools MCP (not in tools); use Playwright optionally (not in tools); do not implement a fix unless the user asks. Commands are requested; containment is not."],"cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","license":{"name":"MIT","url":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/LICENSE"}},{"kind":"mcp-servers","id":"chrome-devtools","purpose":"Inspect the browser and collect diagnostic evidence.","name":"Chrome DevTools MCP","href":"/mcp-servers/chrome-devtools/","compatibility":["MCP clients that can launch a local stdio process; the example uses the documented mcpServers schema.","Google Chrome or Chrome for Testing with the documented Node.js and npm requirements."],"limitation":"The connected assistant can inspect and modify browser content. The documented default uses a persistent browser profile; use --isolated when launching Chrome with a temporary profile and avoid unrelated sensitive sessions.","reviewedAt":"2026-09-21","revision":"d5b4daf511731bacd5e1d1c45254e7fced2c9a34","definitionSha256":null,"sourceUrl":"https://github.com/ChromeDevTools/chrome-devtools-mcp","permissions":["Reads page content, network details, console output and the connected browser’s state.","Can automate interactions and modify page/browser data; configured tools may write diagnostic artifacts."],"cost":"Repository source is Apache-2.0 licensed. The MCP client, model service and local computing resources are separate.","license":{"name":"Apache-2.0","url":"https://github.com/ChromeDevTools/chrome-devtools-mcp/blob/d5b4daf511731bacd5e1d1c45254e7fced2c9a34/LICENSE"}}]},{"id":"investigate-a-postgres-query","title":"Investigate a slow PostgreSQL query","category":"data","summary":"Review SQL and query-plan evidence before proposing a database change.","outcome":"A justified query or index proposal with a test plan and an explicit permission boundary.","inputs":["The SQL, relevant schema and a redacted query plan.","Workload context and a representative non-production dataset."],"parallel":[{"title":"Query analysis","detail":"Review the supplied plan and SQL without executing changes."},{"title":"Schema analysis","detail":"Review indexes and access patterns from the supplied schema."}],"steps":["Start with saved plans or a read-only test connection. Identify the exact database and role before using any server tools.","Compare independent query and schema findings. Treat missing workload evidence as an open question.","Test the agreed proposal on a representative non-production copy, inspect its plan and results, and prepare a separate deployment and rollback decision."],"boundaries":["Choose a host for each stage and verify its tool mapping. Pass evidence explicitly between stages; the listed resources do not automatically configure or invoke one another.","Use a restricted database role and verify the server’s access mode. A catalogue pairing does not make unrestricted SQL safe.","EXPLAIN ANALYZE executes the query. Index creation, schema changes and production execution require a separate authorised step."],"deliverables":["SQL and plan snapshot","Query/index proposal","Result-equivalence evidence","Migration and rollback note"],"checks":["Database version, role, schema and representative parameters are recorded.","Compared queries return equivalent results for the selected fixtures, including null and duplicate cases.","Plans and timings use the same dataset and stated cache/concurrency conditions.","Index write cost, lock exposure and rollback are considered before production changes."],"template":{"title":"PostgreSQL investigation worksheet","sections":[{"heading":"Workload","body":"Engine/version: ___\nSQL and parameter sample: ___\nSchema snapshot: ___\nDataset size/distribution source: ___\nRole and allowed operations: ___"},{"heading":"Baseline","body":"Saved plan path: ___\nWas ANALYZE executed: ___\nExecution environment and cache state: ___\nObserved timing/rows with source: ___\nMissing workload evidence: ___"},{"heading":"Proposal","body":"Bottleneck supported by plan: ___\nQuery or index diff: ___\nResult-equivalence cases: ___\nWrite/lock/storage trade-offs: ___"},{"heading":"Validation and rollout","body":"Test command and observed result: not run\nBefore/after evidence paths: ___\nProduction decision owner/window: ___\nRollback and backup reference: ___"}]},"resources":[{"kind":"skills","id":"supabase-supabase-postgres-best-practices","purpose":"Check PostgreSQL design and performance patterns.","name":"Supabase Postgres Best Practices","href":"/skills/supabase-supabase-postgres-best-practices/","compatibility":["Agent Skills-compatible coding agents","PostgreSQL; Supabase-specific examples are identified"],"limitation":"Illustrative speedups and blanket indexing rules are not measurements of your workload; inspect actual plans and write costs.","reviewedAt":"2026-09-21","revision":"8331f910845103c08d51f6ca1d86ebb7d1f745e3","definitionSha256":null,"sourceUrl":"https://github.com/supabase/agent-skills/tree/8331f910845103c08d51f6ca1d86ebb7d1f745e3/skills/supabase-postgres-best-practices","permissions":["Read schema, SQL and query plans","Write migration or policy files when authorized","Executing suggested SQL can create indexes or alter permissions"],"cost":"The instruction package is MIT-licensed; database hosting, query execution and agent usage have their own costs.","license":{"name":"MIT","url":"https://github.com/supabase/agent-skills/blob/8331f910845103c08d51f6ca1d86ebb7d1f745e3/LICENSE"}},{"kind":"agents","id":"wshobson-database-optimizer","purpose":"Analyse query and schema trade-offs.","name":"Database Cloud Optimization Database Optimizer","href":"/agents/wshobson-database-optimizer/","compatibility":["Claude Code subagents"],"limitation":"This is an implementation-capable role and it declares no tool allowlist; database credentials and migration authority must be scoped in the host.","reviewedAt":"2026-09-21","revision":"4236bb91f8395b0435f1d8b8baf9e8e4c69a8620","definitionSha256":"4be26ef22f389a267b6b61bdc0d661101b602aa2fed162ade7110df3fe124488","sourceUrl":"https://raw.githubusercontent.com/wshobson/agents/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/plugins/database-cloud-optimization/agents/database-optimizer.md","permissions":["Declared: none; model inherit. Instructed: analyze, rewrite queries, add indexes, cache, migrate, shard. Not enforced: requiring a backup or EXPLAIN before DDL. High-impact if parent has DB credentials."],"cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","license":{"name":"MIT","url":"https://github.com/wshobson/agents/blob/4236bb91f8395b0435f1d8b8baf9e8e4c69a8620/LICENSE"}},{"kind":"mcp-servers","id":"postgres","purpose":"Inspect an authorised PostgreSQL environment.","name":"Postgres MCP Pro","href":"/mcp-servers/postgres/","compatibility":["An MCP client supporting stdio, SSE, Streamable HTTP.","uv/Python and a reachable PostgreSQL database."],"limitation":"The default access mode is unrestricted and allows data/schema changes.","reviewedAt":"2026-09-21","revision":"15c8e33353546148acc2d8bd784551cf3905d1e2","definitionSha256":null,"sourceUrl":"https://github.com/crystaldba/postgres-mcp","permissions":["Reads database metadata, query results and diagnostic information.","Unrestricted mode can modify database data and schema."],"cost":"Database hosting and diagnostic-query resource use determine cost.","license":{"name":"MIT","url":"https://github.com/crystaldba/postgres-mcp/blob/15c8e33353546148acc2d8bd784551cf3905d1e2/LICENSE"}}]},{"id":"document-an-api","title":"Document an API or codebase","category":"publish","summary":"Combine source inspection, documentation structure and version-specific reference lookup.","outcome":"A documentation draft whose examples and claims can be checked against the actual project.","inputs":["A fixed source revision and the intended reader.","The API or library versions used by the project."],"parallel":[{"title":"Source inventory","detail":"List real entry points, configuration and observable behaviour from project files."},{"title":"Reference lookup","detail":"Find documentation for the matching library versions; keep source URLs with each claim."}],"steps":["Define the audience, intended task and source revision before drafting.","Gather code facts and external references independently. Resolve version mismatches before turning either into instructions.","Draft the document, check each example against the project, and have a reader follow the instructions. Keep untested examples labelled."],"boundaries":["Choose a host for each stage and verify its tool mapping. Pass evidence explicitly between stages; the listed resources do not automatically configure or invoke one another.","Context7 supplies reference material; it does not establish what your own application actually implements.","The agent definition may need host-tool adaptation. Review the upstream skill’s current licence and terms before redistribution."],"deliverables":["Versioned API inventory","Task-oriented documentation draft","Example execution receipts","Unverified-claim ledger"],"checks":["Every endpoint, option and default maps to the chosen source revision.","External references match the installed library version or name the mismatch.","Examples are run with an authorised runner or explicitly marked untested.","A fresh reader can identify prerequisites, expected output and recovery from an error."],"template":{"title":"API documentation brief","sections":[{"heading":"Audience and source","body":"Reader and task: ___\nRepository revision: ___\nAPI/library versions: ___\nSupported environment: ___"},{"heading":"Contract inventory","body":"| Entry point | Required input | Output/error contract | Source location |\n| --- | --- | --- | --- |\n| ___ | ___ | ___ | ___ |"},{"heading":"Example proof","body":"Example path: ___\nPrerequisites and non-secret configuration: ___\nExecution command/runner: ___\nExpected output basis: ___\nObserved output and exit: not run"},{"heading":"Reader review","body":"Reader questions: ___\nBroken links or missing steps: ___\nClaims still unverified: ___\nLicence and attribution notes: ___\nPublication destination/owner: ___"}]},"resources":[{"kind":"skills","id":"anthropics-doc-coauthoring","purpose":"Structure iterative documentation drafting.","name":"Anthropic Documentation Coauthoring","href":"/skills/anthropics-doc-coauthoring/","compatibility":["Claude Code","Claude.ai"],"limitation":"Reader-model agreement is a spot check, not factual verification or a human usability study; the author still needs to verify facts and links.","reviewedAt":"2026-09-21","revision":"34040c9c568585f6929bedeaad110ad08f079624","definitionSha256":null,"sourceUrl":"https://github.com/anthropics/skills/tree/34040c9c568585f6929bedeaad110ad08f079624/skills/doc-coauthoring","permissions":["Read supplied documents and authorized connected content","Create or edit the working document","Send the draft to a separate reader session if that review path is chosen"],"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.","license":null},{"kind":"agents","id":"github-se-technical-writer","purpose":"Organise technical documentation for its audience.","name":"Se: Tech Writer","href":"/agents/github-se-technical-writer/","compatibility":["GitHub Copilot custom agents in VS Code"],"limitation":"The frontmatter permits file editing and web retrieval but does not name an execution tool; testing or compiling examples needs a separate runner.","reviewedAt":"2026-09-21","revision":"ad4c196b933c5ca7f82a5ba78969ddcd2603ba80","definitionSha256":"e2b7fe3959fee4701084022bdfb6bae9c24b2890d44305f17d779d0055ec9506","sourceUrl":"https://raw.githubusercontent.com/github/awesome-copilot/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/se-technical-writer.agent.md","permissions":["Requested: codebase, edit/editFiles, search, web/fetch.","Instructed to create/edit documentation content and fetch official docs. File writes are requested, not sandboxed."],"cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","license":{"name":"MIT","url":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/LICENSE"}},{"kind":"mcp-servers","id":"context7","purpose":"Look up relevant library reference material.","name":"Context7 MCP","href":"/mcp-servers/context7/","compatibility":["Remote HTTP MCP clients with the authentication configuration described in their client guide.","Node.js for the documented setup CLI/local adapter path."],"limitation":"Documentation projects are community-contributed; the publisher does not guarantee their accuracy, completeness or security.","reviewedAt":"2026-09-21","revision":"eb27b949fbc95b630bc51eb9e31736ff5895057b","definitionSha256":null,"sourceUrl":"https://context7.com","permissions":["Sends library names, identifiers and query text to Context7.","The documented MCP tools retrieve documentation; they do not edit the project."],"cost":"Hosted access is subject to Context7 account and usage limits; check current service terms for the intended workload.","license":{"name":"MIT","url":"https://github.com/upstash/context7/blob/eb27b949fbc95b630bc51eb9e31736ff5895057b/LICENSE"}}]},{"id":"investigate-an-incident","title":"Investigate an application incident","category":"operate","summary":"Keep observations, hypotheses and proposed fixes separate while collecting scoped evidence.","outcome":"An incident hypothesis supported by concrete evidence, followed by a scoped verification plan.","inputs":["An incident window and affected environment.","Redacted event identifiers, logs and recent change context.","A concrete symptom and a usable reproduction environment for the debugging agent; record the gap if either is unavailable."],"parallel":[{"title":"Event evidence","detail":"Inspect the permitted event set and list observed symptoms."},{"title":"Change evidence","detail":"Inspect relevant deployments and code changes without receiving a preferred explanation."}],"steps":["Confirm the environment, time window and permission scope. Redact sensitive fields before sending evidence to a model.","Collect event and change evidence separately, then compare hypotheses against both. Record contradictions and missing information.","Test a minimal fix in a suitable environment with visible test output and preserved exit status. Do not use a helper that suppresses failures as verification. Treat deployment and incident-state changes as separate authorised actions."],"boundaries":["Choose a host for each stage and verify its tool mapping. Pass evidence explicitly between stages; the listed resources do not automatically configure or invoke one another.","Configure Sentry access and the definition’s tool mapping separately. Record adapter and self-hosted feature limits before treating an event set as complete.","Do not resolve issues, change alerts, edit production or publish incident data during the evidence-gathering pass."],"deliverables":["Timestamped incident timeline","Competing-hypothesis ledger","Minimal reproduction or stated gap","Recovery verification plan"],"checks":["Every event uses a recorded time zone and the affected environment is unambiguous.","Observed events are separated from inferred causes.","The proposed fix explains the original symptom and contradictory evidence is retained.","Recovery checks preserve command exit status; deployment and incident closure remain separate decisions."],"template":{"title":"Incident evidence log","sections":[{"heading":"Scope","body":"Incident window and time zone: ___\nEnvironment/service: ___\nCustomer-visible symptom: ___\nPermitted event sources: ___\nSensitive fields removed: ___"},{"heading":"Timeline","body":"| Timestamp | Observed event | Evidence reference | Related deployment |\n| --- | --- | --- | --- |\n| ___ | ___ | ___ | ___ |"},{"heading":"Hypotheses","body":"Hypothesis: ___\nSupporting evidence: ___\nContradictory evidence: ___\nDiscriminating test: ___\nReproduction unavailable because: ___"},{"heading":"Recovery","body":"Proposed minimal change: ___\nValidation command and preserved exit: ___\nRecovery signal and observation window: ___\nRollback trigger/owner: ___\nCurrent state: investigation only"}]},"resources":[{"kind":"skills","id":"obra-systematic-debugging","purpose":"Investigate root cause before changing code.","name":"Superpowers Systematic Debugging","href":"/skills/obra-systematic-debugging/","compatibility":["Superpowers-supported coding agents","The optional polluter helper assumes Bash and npm"],"limitation":"The bundled polluter helper assumes npm tests, hides their output and swallows their failing exit statuses.","reviewedAt":"2026-09-21","revision":"5bf4e78011075bcfc0dc295f0724994cd123ee71","definitionSha256":null,"sourceUrl":"https://github.com/obra/superpowers/tree/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/systematic-debugging","permissions":["Read source, logs and recent changes","Add temporary diagnostic instrumentation","Execute project tests and inspect filesystem side effects"],"cost":"The MIT-licensed process uses the configured agent and local or external test resources.","license":{"name":"MIT","url":"https://github.com/obra/superpowers/blob/5bf4e78011075bcfc0dc295f0724994cd123ee71/LICENSE"}},{"kind":"agents","id":"github-debug-mode","purpose":"Structure a hypothesis-driven debugging pass.","name":"Systematic Debugging","href":"/agents/github-debug-mode/","compatibility":["GitHub Copilot custom agents in VS Code"],"limitation":"The procedure is a general debugging framework, so the caller must provide a concrete symptom and a usable reproduction environment.","reviewedAt":"2026-09-21","revision":"ad4c196b933c5ca7f82a5ba78969ddcd2603ba80","definitionSha256":"2ac23b322866f85b15918847b7989887df0f167aefdd815f7790214412b6ccdc","sourceUrl":"https://raw.githubusercontent.com/github/awesome-copilot/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/debug.agent.md","permissions":["The original grants repository edit and execution tools. Commands and test fixtures can change local or connected state.","Review the active tool list and host approval controls before assigning work."],"cost":"The definition is reusable under its stated licence. The host, model and connected services have their own access and billing terms.","license":{"name":"MIT","url":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/LICENSE"}},{"kind":"mcp-servers","id":"sentry","purpose":"Retrieve authorised application error evidence.","name":"Sentry MCP","href":"/mcp-servers/sentry/","compatibility":["An MCP client supporting stdio, Streamable HTTP.","A Sentry account with access to the target organization, or a configured self-hosted Sentry instance."],"limitation":"The stdio adapter is described as a work in progress; self-hosted feature availability differs.","reviewedAt":"2026-09-21","revision":"e61c1888c8f8bcca76b60229cad4eeb28226399d","definitionSha256":null,"sourceUrl":"https://github.com/getsentry/sentry-mcp","permissions":["Reads issue/event data accessible to the authenticated account.","Enabled skills and token scopes can permit project, team or event changes."],"cost":"Sentry account entitlements apply; a self-hosted adapter may also incur model-provider usage for AI search.","license":{"name":"FSL-1.1-Apache-2.0","url":"https://github.com/getsentry/sentry-mcp/blob/e61c1888c8f8bcca76b60229cad4eeb28226399d/LICENSE.md"}}]},{"id":"plan-an-interface","title":"Plan an interface from code and design","category":"build","summary":"Compare the implemented design system with design evidence and user tasks before drafting changes.","outcome":"A design brief with component rules, accessibility checks and an implementation checklist.","inputs":["Existing frontend source with the framework and project design tokens.","An authorised design file or exported frames, plus the user task and target devices."],"parallel":[{"title":"Design inventory","detail":"Extract component and token rules from frontend source; compare them with the supplied design evidence."},{"title":"Task-flow review","detail":"Inspect the user journey and accessibility requirements independently of the proposed visual solution."}],"steps":["Select the source revision and authorised design frames. Extract the existing system from code; pass exported design context between hosts where necessary.","Review design patterns and task flow separately, then reconcile them against the existing codebase and tokens.","Prepare an implementation brief. Verify the result in a real browser with keyboard, narrow-screen and dark-mode checks relevant to the project."],"boundaries":["Choose a host for each stage and verify its tool mapping. Pass evidence explicitly between stages; the listed resources do not automatically configure or invoke one another.","The extraction skill reads frontend source; Figma frames alone are not its documented input. The Copilot UX definition and Figma connection need separate host setup. This pairing is not a tested direct integration.","Respect design-file permissions and asset licences. Do not overwrite shared designs or claim browser accessibility was tested until it was."],"deliverables":["Code-derived token and component inventory","Task-flow brief","State and interaction specification","Browser acceptance checklist"],"checks":["Token values are traced to project files rather than copied from a sample palette.","Research observations are separated from proposed personas or usability hypotheses.","Loading, empty, error and success states have defined behaviour.","Keyboard, narrow-screen and relevant theme checks are observed before calling implementation complete."],"template":{"title":"Interface implementation brief","sections":[{"heading":"Task and evidence","body":"Person/task: ___\nExisting research or labelled hypothesis: ___\nSource revision: ___\nAuthorised design frames: ___\nTarget devices: ___"},{"heading":"Design inventory","body":"| Component or token | Source file/value | Design-frame counterpart | Mismatch |\n| --- | --- | --- | --- |\n| ___ | ___ | ___ | ___ |"},{"heading":"Interaction states","body":"Entry and completion criteria: ___\nLoading/empty/error/success: ___\nKeyboard order and focus return: ___\nAnnouncements and labels: ___"},{"heading":"Implementation acceptance","body":"Assigned files and owner: ___\nViewport/theme test matrix: ___\nBrowser evidence: not run\nUnresolved design decision: ___\nAsset rights and attribution: ___"}]},"resources":[{"kind":"skills","id":"google-labs-code-extract-design-md","purpose":"Extract a design description from existing frontend source.","name":"Google Stitch Design-System Extraction","href":"/skills/google-labs-code-extract-design-md/","compatibility":["Codex","Claude Code","Cursor","Gemini CLI"],"limitation":"Source extraction does not verify rendered appearance, accessibility or the effects of runtime themes. Descriptions of intent remain interpretation.","reviewedAt":"2026-09-21","revision":"0337446dadde6f8c94210444e2aa9d546126480f","definitionSha256":null,"sourceUrl":"https://github.com/google-labs-code/stitch-skills/tree/0337446dadde6f8c94210444e2aa9d546126480f/plugins/stitch-design/skills/extract-design-md","permissions":["Read style, component, theme and configuration files","Create a local design-system document","A separately selected integration can send that document to Stitch"],"cost":"Apache-licensed skill instructions; the consuming agent and any optional Stitch service access have their own terms.","license":{"name":"Apache-2.0","url":"https://github.com/google-labs-code/stitch-skills/blob/0337446dadde6f8c94210444e2aa9d546126480f/LICENSE"}},{"kind":"agents","id":"github-se-ux-designer","purpose":"Review task flow and interaction requirements.","name":"Jobs-to-be-Done UX Planner","href":"/agents/github-se-ux-designer/","compatibility":["GitHub Copilot custom agents in VS Code"],"limitation":"The agent drafts research artifacts; it does not conduct interviews, validate personas or create Figma designs.","reviewedAt":"2026-09-21","revision":"ad4c196b933c5ca7f82a5ba78969ddcd2603ba80","definitionSha256":"a7078735984cfec19643027b8e876435b3d73f43ab431f910186e16a11b0bdd2","sourceUrl":"https://raw.githubusercontent.com/github/awesome-copilot/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/se-ux-ui-designer.agent.md","permissions":["The tool list permits repository lookup, document editing and web fetches.","The role does not supply a Figma integration or a user-interview service."],"cost":"The definition is reusable under its stated licence. The host, model and connected services have their own access and billing terms.","license":{"name":"MIT","url":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/LICENSE"}},{"kind":"mcp-servers","id":"figma","purpose":"Retrieve the selected design context.","name":"Figma Remote MCP","href":"/mcp-servers/figma/","compatibility":["A client supporting the documented remote transport and authentication flow.","Configuration example is specifically VS Code mcp.json."],"limitation":"Only clients listed in Figma’s MCP Catalog may connect.","reviewedAt":"2026-09-21","revision":null,"definitionSha256":null,"sourceUrl":"https://developers.figma.com/docs/figma-mcp-server/remote-server-installation/","permissions":["Reads design context and can create/edit native Figma or FigJam content within file permissions."],"cost":"Figma plan and seat determine access and rate limits; consult the current access table.","license":null}]},{"id":"turn-a-decision-into-a-spec","title":"Turn an agreed change into a buildable specification","category":"build","summary":"Translate a settled discussion into repository-specific interfaces, acceptance cases and an implementation sequence.","outcome":"A local specification and architecture handoff with explicit unresolved decisions.","inputs":["The agreed discussion, requirements and exclusions.","A fixed repository revision, glossary and existing architecture decisions."],"parallel":[{"title":"Requirement synthesis","detail":"Map agreed statements to observable acceptance cases; do not silently settle open questions."},{"title":"Architecture inventory","detail":"Inspect comparable code paths and identify interfaces, invariants and dependency seams."}],"steps":["Choose local Markdown tracking before invoking the specification skill. Inspect its setup companion and any proposed repository-guidance changes.","Give the architect the fixed source and agreed requirements. Ask for concrete file/interface changes, then reconcile that blueprint with the independently extracted requirements.","Write the specification with test seams and migration effects. Resolve contradictions with the decision owner; publish an issue only when that destination and action are authorised."],"boundaries":["The to-spec skill synthesises an existing discussion; it does not replace requirements discovery. Its configured tracker can publish issues and labels.","The architect proposes a design without executing it. Older model/tool names need host adaptation, and a readiness label is not implementation evidence."],"deliverables":["Requirement-to-case map","Local specification","File/interface blueprint","Open-decision log"],"checks":["Every requirement has an observable acceptance case.","Each proposed interface cites an existing convention or records why it must change.","Unresolved requirements remain visible rather than guessed.","Tracker publication and repository configuration changes are explicitly scoped."],"template":{"title":"Specification handoff","sections":[{"heading":"Decision context","body":"Agreed task: ___\nSource revision: ___\nDecision records: ___\nExplicit non-goals: ___"},{"heading":"Acceptance map","body":"| Requirement | Observable case | Source decision | Open question |\n| --- | --- | --- | --- |\n| ___ | ___ | ___ | ___ |"},{"heading":"Architecture","body":"Files/interfaces affected: ___\nInvariants to preserve: ___\nDependency seams: ___\nImplementation order: ___"},{"heading":"Handoff","body":"Local specification path: ___\nBlocking decisions/owners: ___\nTracker destination, if authorised: ___\nChanges to setup/configuration: ___"}]},"resources":[{"kind":"skills","id":"mattpocock-to-spec","purpose":"Synthesise the agreed discussion using project terminology and explicit scope.","name":"Conversation to Specification","href":"/skills/mattpocock-to-spec/","compatibility":["Claude Code","Codex"],"limitation":"This is synthesis after discussion, not a discovery interview or a check that every stakeholder requirement is present.","reviewedAt":"2026-09-22","revision":"c55ee46073ed923f86ce59a5eb3b6d895095d1b7","definitionSha256":null,"sourceUrl":"https://github.com/mattpocock/skills/blob/c55ee46073ed923f86ce59a5eb3b6d895095d1b7/skills/engineering/to-spec/SKILL.md","permissions":["Read the current conversation, repository context and architecture decisions","Write a local specification or create an issue using configured tracker credentials","The separately invoked setup companion updates repository instruction/configuration files"],"cost":"MIT-licensed instructions; agent usage and any issue-tracker account terms are separate.","license":{"name":"MIT","url":"https://github.com/mattpocock/skills/blob/c55ee46073ed923f86ce59a5eb3b6d895095d1b7/LICENSE"}},{"kind":"agents","id":"anthropic-code-architect","purpose":"Map the agreed change to concrete repository interfaces and an implementation sequence.","name":"Code Architect","href":"/agents/anthropic-code-architect/","compatibility":["Claude Code (frontmatter adjustment required)"],"limitation":"The prompt asks for one decisive design; use another review process when competing designs or unresolved requirements need comparison.","reviewedAt":"2026-09-21","revision":"c447c3207a425bc4e2a0d068435f64b0477ae981","definitionSha256":"c50fb08d59a4bbd19660860626a049e44cf1a2b0c1cf782e6c7a99ba7e71b0c3","sourceUrl":"https://raw.githubusercontent.com/anthropics/claude-plugins-official/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/feature-dev/agents/code-architect.md","permissions":["Declared tools include repository search/read, WebFetch/WebSearch, task tracking, KillShell and BashOutput.","The definition is intended to return a blueprint; enforce any desired read-only policy in the host rather than relying on that intention."],"cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","license":{"name":"Apache-2.0","url":"https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/feature-dev/LICENSE"}}]},{"id":"modernise-with-characterisation-tests","title":"Modernise legacy code with characterisation tests","category":"build","summary":"Capture observed legacy behaviour before changing implementation, then distinguish preserved behaviour from intentional changes.","outcome":"A runnable characterisation suite and a dual-run comparison for an explicitly bounded module.","inputs":["Readable legacy sources and a caller-defined modernized/ output directory.","A target stack supported by the profile, representative fixtures and an agreed behaviour contract."],"parallel":[{"title":"Legacy observer","detail":"Record externally visible behaviour and unresolved edge cases without modifying legacy code."},{"title":"Test designer","detail":"Derive assertions from the contract and fixtures, identifying deliberate behaviour changes separately."}],"steps":["Use an isolated checkout and enforce write scope in the host. Record the legacy/ and modernized/ layout and establish the real test command.","Write a failing behaviour test before implementation. Verify that its failure is the intended assertion, not a broken runtime or fixture.","Build the smallest change, compare old and new outputs on the same inputs, then refactor while retaining passing checks. Leave unspecified target behaviour pending instead of inventing it."],"boundaries":["The test-engineer profile is for legacy modernisation and assumes the supplied directory layout and supported test framework. It grants edit and Bash tools; directory rules alone do not enforce containment.","Do not discard someone else’s implementation to satisfy test-first instructions. Preserve existing work, agree intentional behaviour changes and isolate any live-database harness."],"deliverables":["Legacy behaviour catalogue","Characterisation fixtures and tests","Dual-run comparison","Intentional-change and pending-case ledger"],"checks":["Each red test fails for the intended behavioural reason.","Legacy files remain unchanged unless a separate change was agreed.","Old/new comparisons use the same fixtures and record mismatches.","Compile/test exit statuses and unresolved pending cases are retained."],"template":{"title":"Modernisation test ledger","sections":[{"heading":"Scope","body":"Legacy path/revision: ___\nModernized output path: ___\nFramework/test command: ___\nHost write restrictions: ___"},{"heading":"Behaviour","body":"| Input fixture | Legacy observation | Target expectation | Preserve or change |\n| --- | --- | --- | --- |\n| ___ | not run | ___ | ___ |"},{"heading":"Red and green","body":"Assertion intended to fail: ___\nObserved failing output/exit: not run\nMinimal implementation revision: ___\nObserved passing output/exit: not run"},{"heading":"Dual-run handoff","body":"Comparison evidence: ___\nUnspecified or pending cases: ___\nAuthorised live dependencies, if any: ___\nRemaining migration risk: ___"}]},"resources":[{"kind":"skills","id":"obra-test-driven-development","purpose":"Establish an observed failing assertion before changing behaviour.","name":"Superpowers Test-Driven Development","href":"/skills/obra-test-driven-development/","compatibility":["Superpowers-supported coding agents","Project-specific test runners"],"limitation":"The workflow is deliberately prescriptive: it tells an agent to discard implementation written before tests and seek permission for exceptions.","reviewedAt":"2026-09-21","revision":"5bf4e78011075bcfc0dc295f0724994cd123ee71","definitionSha256":null,"sourceUrl":"https://github.com/obra/superpowers/tree/5bf4e78011075bcfc0dc295f0724994cd123ee71/skills/test-driven-development","permissions":["Read and edit implementation and tests","Run project test commands, including the broader suite","Potentially discard premature implementation under the skill instructions"],"cost":"The skill is MIT-licensed; agent calls, local test resources and external test services remain separate.","license":{"name":"MIT","url":"https://github.com/obra/superpowers/blob/5bf4e78011075bcfc0dc295f0724994cd123ee71/LICENSE"}},{"kind":"agents","id":"anthropic-test-engineer","purpose":"Draft characterisation tests and dual-run checks for the specified legacy/modernized layout.","name":"Test Engineer","href":"/agents/anthropic-test-engineer/","compatibility":["Claude Code subagents"],"limitation":"Frontmatter grants Write, Edit, and unrestricted Bash; the modernized/-only and never-edit-legacy/ rules are prompt text, not a sandbox.","reviewedAt":"2026-09-21","revision":"c447c3207a425bc4e2a0d068435f64b0477ae981","definitionSha256":"2bb01314295aef845536e1677ef28a6dbfecb9375d95b8c1489b7c82dc8481c1","sourceUrl":"https://raw.githubusercontent.com/anthropics/claude-plugins-official/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/code-modernization/agents/test-engineer.md","permissions":["Requested (frontmatter): Read, Write, Edit, Glob, Grep, Bash.","Instructed only: write tests under the given modernized/ directory; never write elsewhere; never edit legacy/; never inline credentials—use fake same-shape values or env vars. Those limits are not enforced by the tools list."],"cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","license":{"name":"Apache-2.0","url":"https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/code-modernization/LICENSE"}}]},{"id":"refactor-a-component-contract","title":"Refactor a React component contract","category":"build","summary":"Replace coupled mode flags only where explicit composition preserves behaviour and simplifies a real variation point.","outcome":"A scoped component API proposal with invariant checks and a consumer migration map.","inputs":["Component, provider and consumer source at one revision.","Installed React version and behaviour tests for the supported component variants."],"parallel":[{"title":"Variant inventory","detail":"List legal and illegal combinations of current props and the consumers that rely on them."},{"title":"Invariant review","detail":"Inspect constructors, mutators and state ownership independently of the preferred refactor."}],"steps":["Record current variants, defaults and public consumers before selecting a composition pattern. Check whether the project version supports the suggested React APIs.","Propose explicit variants and a provider-owned state interface where they remove an actual ambiguity. Ask the type reviewer to challenge invalid states and migration costs.","Migrate a bounded consumer set, rerun interaction tests and compare the public contract. Retain the simpler API when the new indirection has no clear purpose."],"boundaries":["Composition guidance includes version-specific React APIs. Do not upgrade the framework merely to copy an example.","The type reviewer’s numeric rubric is subjective; use concrete invariants and compiler/test evidence. Its inherited tools need host restrictions for a review-only pass."],"deliverables":["Variant and consumer inventory","Proposed API/state contract","Consumer migration diff","Behaviour-preservation receipt"],"checks":["Supported variants and defaults have explicit cases.","Invalid combinations are rejected or documented rather than silently reinterpreted.","Provider scope and state ownership are checked at each consumer.","The chosen React APIs match the installed version."],"template":{"title":"Component contract worksheet","sections":[{"heading":"Current API","body":"Component/revision: ___\nReact version: ___\nConsumers: ___\nCoupled flags and defaults: ___"},{"heading":"Variant map","body":"| Current combination | Intended variant | Required invariant | Existing test |\n| --- | --- | --- | --- |\n| ___ | ___ | ___ | ___ |"},{"heading":"Proposed contract","body":"Public composition: ___\nState/actions/metadata ownership: ___\nInvalid state prevented: ___\nAdded complexity and reason: ___"},{"heading":"Migration proof","body":"Consumers changed: ___\nInteraction/typecheck command and result: not run\nBreaking changes: ___\nDeferred consumers: ___"}]},"resources":[{"kind":"skills","id":"vercel-labs-composition-patterns","purpose":"Design explicit component variants and state-provider contracts.","name":"Vercel React Composition Patterns","href":"/skills/vercel-labs-composition-patterns/","compatibility":["Agent Skills-compatible agents","React; newer API guidance requires a matching React version"],"limitation":"Context and compound components can add indirection to a simple component; apply the pattern where variation warrants it.","reviewedAt":"2026-09-21","revision":"063bee94c3f4df8453406c830b0a7df0f2860278","definitionSha256":null,"sourceUrl":"https://github.com/vercel-labs/agent-skills/tree/063bee94c3f4df8453406c830b0a7df0f2860278/skills/composition-patterns","permissions":["Read and refactor component APIs and state providers","Run application tests after changes"],"cost":"MIT is declared upstream; this is an instruction package without an additional hosted service.","license":{"name":"MIT (declared in upstream README)","url":"https://github.com/vercel-labs/agent-skills/blob/063bee94c3f4df8453406c830b0a7df0f2860278/README.md#license"}},{"kind":"agents","id":"anthropic-type-design-analyzer","purpose":"Challenge which invalid states the proposed types actually prevent.","name":"Type Design Analyzer","href":"/agents/anthropic-type-design-analyzer/","compatibility":["Claude Code subagents"],"limitation":"Its numerical design rubric is subjective guidance, not a measured quality score or compiler result.","reviewedAt":"2026-09-21","revision":"c447c3207a425bc4e2a0d068435f64b0477ae981","definitionSha256":"c1cf67843d3c4fd27ddf6b24aa92521414b16c01610e7f7e87212c7b8681198d","sourceUrl":"https://raw.githubusercontent.com/anthropics/claude-plugins-official/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/pr-review-toolkit/agents/type-design-analyzer.md","permissions":["Frontmatter: no tools, inherit model. Body: evaluate and suggest; does not forbid applying suggestions.","Numeric ratings are instructions to the model, not enforced gates."],"cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","license":{"name":"Apache-2.0","url":"https://github.com/anthropics/claude-plugins-official/blob/c447c3207a425bc4e2a0d068435f64b0477ae981/plugins/pr-review-toolkit/LICENSE"}}]},{"id":"audit-an-accessible-user-journey","title":"Audit an accessible user journey","category":"test","summary":"Combine source findings with observed keyboard and form behaviour for one defined user journey.","outcome":"A reproducible accessibility issue list with evidence and a bounded retest matrix.","inputs":["A running authorised interface and the source revision.","The journey, target browser, viewport and input or assistive-technology setup."],"parallel":[{"title":"Source review","detail":"Check semantics, labels and interaction rules; save the exact externally fetched guideline version."},{"title":"Journey design","detail":"Define keyboard steps, expected focus movement and error recovery without sharing a browser session."}],"steps":["Use an isolated browser context and explicitly enable the browser tools missing from the runtime agent’s original allowlist. Select a journey with clear start and completion states.","Run keyboard navigation, visible-focus and form-error checks. Check appropriate modal focus behaviour without imposing a trap on every non-modal surface.","Pair observed failures with source locations, prioritise by blocked task and retest the repaired journey. Mark any screen-reader behaviour unverified unless it was actually observed."],"boundaries":["A browser server can submit forms and change remote state. Use test accounts and fixtures appropriate to the journey.","Static guideline checks, DOM inspection and an automated scan do not establish full accessibility conformance. The guideline file is mutable and must be captured for reproducibility."],"deliverables":["Journey and environment matrix","Guideline snapshot reference","Reproducible issue ledger","Retest evidence and untested scope"],"checks":["Focus order and return behaviour are observed, not inferred from source.","Each issue states the blocked task and exact reproduction.","Screen-reader claims name the actual tested technology.","The repaired journey is rerun at the required narrow viewport."],"template":{"title":"Accessibility journey worksheet","sections":[{"heading":"Environment","body":"Journey: ___\nURL/revision: ___\nBrowser/viewport: ___\nInput method/assistive technology: ___\nGuideline URL/hash/date: ___"},{"heading":"Interaction expectations","body":"Start state: ___\nKeyboard sequence: ___\nExpected focus/announcement: ___\nError recovery: ___"},{"heading":"Observed issues","body":"| Step | Expected | Observed | Evidence | Source location |\n| --- | --- | --- | --- | --- |\n| ___ | ___ | not run | ___ | ___ |"},{"heading":"Retest scope","body":"Fix revision: ___\nRetest result: not run\nUntested technology/states: ___\nTask impact and owner: ___"}]},"resources":[{"kind":"skills","id":"vercel-labs-web-design-guidelines","purpose":"Find source-specific interaction and semantics concerns.","name":"Vercel Web Interface Guidelines","href":"/skills/vercel-labs-web-design-guidelines/","compatibility":["Agents with web retrieval and repository read access","Web application source"],"limitation":"The skill fetches a mutable external rules file at runtime; pinning the skill alone does not freeze the guidance.","reviewedAt":"2026-09-21","revision":"063bee94c3f4df8453406c830b0a7df0f2860278","definitionSha256":null,"sourceUrl":"https://github.com/vercel-labs/agent-skills/tree/063bee94c3f4df8453406c830b0a7df0f2860278/skills/web-design-guidelines","permissions":["Fetch public guidelines","Read source files and report line-specific findings"],"cost":"MIT is declared for the skill repository; the workflow uses the configured agent and retrieval tooling.","license":{"name":"MIT (declared in upstream README)","url":"https://github.com/vercel-labs/agent-skills/blob/063bee94c3f4df8453406c830b0a7df0f2860278/README.md#license"}},{"kind":"agents","id":"github-accessibility-runtime-tester","purpose":"Structure keyboard, focus and error-recovery observations after tool adaptation.","name":"Accessibility Runtime Tester","href":"/agents/github-accessibility-runtime-tester/","compatibility":["GitHub Copilot custom agents in VS Code (tool adjustment required)"],"limitation":"The body expects browser automation but the original allowlist does not enable the preferred Chrome DevTools or Playwright MCP tools. Configure and allow those tools in a working copy first.","reviewedAt":"2026-09-21","revision":"ad4c196b933c5ca7f82a5ba78969ddcd2603ba80","definitionSha256":"53d57ab559cf81776e794a1858f14990f7e8ef953c439fbc1673efef5ebdb75a","sourceUrl":"https://raw.githubusercontent.com/github/awesome-copilot/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/accessibility-runtime-tester.agent.md","permissions":["The original permits read/search and terminal/test tools, but lacks the browser MCP tools requested by the body.","The no-edit default is an instruction; permitted terminal commands can still change files or application state."],"cost":"The definition is reusable under its stated licence. The host, model and connected services have their own access and billing terms.","license":{"name":"MIT","url":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/LICENSE"}},{"kind":"mcp-servers","id":"playwright","purpose":"Operate the dedicated browser context and capture the selected journey.","name":"Playwright MCP","href":"/mcp-servers/playwright/","compatibility":["Node.js and a supported browser on the host.","MCP clients supporting stdio; documented local HTTP mode is also available."],"limitation":"This server is not a security boundary; allowed/blocked origin options do not provide a reliable sandbox.","reviewedAt":"2026-09-21","revision":"f1257a5a67aff872f947fae274759f7d54853862","definitionSha256":null,"sourceUrl":"https://github.com/microsoft/playwright-mcp","permissions":["Reads rendered pages, browser console/network state and screenshots.","May execute page scripts, upload/download files and perform authenticated browser actions."],"cost":"The server source has no metered licence; browser compute, target services and the chosen assistant have separate costs.","license":{"name":"Apache-2.0","url":"https://github.com/microsoft/playwright-mcp/blob/f1257a5a67aff872f947fae274759f7d54853862/LICENSE"}}]},{"id":"review-a-security-sensitive-diff","title":"Review a security-sensitive diff","category":"test","summary":"Trace changed trust boundaries and removed protections, then corroborate findings with scoped static analysis.","outcome":"A security review tied to exploit prerequisites, source lines and explicit coverage limits.","inputs":["A fixed base/head diff and the relevant authentication or data-flow contract.","A clean review worktree, selected scanner rules and permission to inspect the source."],"parallel":[{"title":"Differential review","detail":"Trace callers, removed checks and baseline intent for the changed boundary."},{"title":"Scanner review","detail":"Run an approved rule set and preserve its configuration, output and failures independently."}],"steps":["Use an isolated worktree because baseline inspection may change the checkout. Define assets, attacker-controlled inputs and the paths included in the review.","Inspect the diff and callers before interpreting scan results. Select local or platform scan mode deliberately and document any source upload or account dependency.","Reproduce material findings with controlled fixtures where authorised, reconcile scanner false positives and report unexamined paths. Treat suggested patches as a separate reviewed change."],"boundaries":["The differential-review plugin has required companion files and agent handoffs; a single SKILL.md is incomplete. Its caller counts are heuristics, not a complete call graph.","Semgrep capabilities and data flows vary by mode and entitlement. A clean scan does not prove absence of vulnerabilities, and exploit checks must stay inside authorised fixtures."],"deliverables":["Trust-boundary scope","Baseline/head evidence map","Scanner receipt","Findings with exploit prerequisites and coverage limits"],"checks":["Removed checks are examined with their history and callers.","Scanner version, rules, mode and data-flow choices are recorded.","Each confirmed finding has a controlled witness or a clearly labelled reasoning limit.","No finding severity is presented as a measured probability."],"template":{"title":"Security diff worksheet","sections":[{"heading":"Boundary","body":"Base/head: ___\nAssets and attacker-controlled inputs: ___\nPaths included/excluded: ___\nReview worktree: ___"},{"heading":"Removed protection","body":"Changed guard and source line: ___\nOriginal rationale/history: ___\nReachable caller: ___\nExploit prerequisites: ___"},{"heading":"Scanner evidence","body":"Version/rules/mode: ___\nNetwork or platform access: ___\nCommand, exit and report: not run\nFalse-positive rationale: ___"},{"heading":"Finding disposition","body":"Witness and expected impact: ___\nConfirmed/unverified/dismissed: ___\nSuggested repair and regression case: ___\nCoverage gaps: ___"}]},"resources":[{"kind":"skills","id":"trailofbits-differential-review","purpose":"Trace security consequences against baseline protections and callers.","name":"Trail of Bits Differential Security Review","href":"/skills/trailofbits-differential-review/","compatibility":["Claude Code and documented Codex plugin compatibility","Git repositories with a meaningful baseline"],"limitation":"The methodology includes checking out the baseline and head; use a suitable worktree so the review does not disrupt uncommitted work.","reviewedAt":"2026-09-21","revision":"123037ec8aed26f0d86327cc39137ee5043e5deb","definitionSha256":null,"sourceUrl":"https://github.com/trailofbits/skills/tree/123037ec8aed26f0d86327cc39137ee5043e5deb/plugins/differential-review/skills/differential-review","permissions":["Read diffs, history, callers and tests","Run git commands that can change the checked-out revision","Write review reports and optionally run authorized validation"],"cost":"The package uses CC-BY-SA terms; agent review and any validation infrastructure are separate costs.","license":{"name":"CC-BY-SA-4.0","url":"https://github.com/trailofbits/skills/blob/123037ec8aed26f0d86327cc39137ee5043e5deb/LICENSE"}},{"kind":"mcp-servers","id":"semgrep-cli","purpose":"Run the selected scanner mode and return rule-specific evidence.","name":"Semgrep CLI MCP","href":"/mcp-servers/semgrep-cli/","compatibility":["VS Code","Kiro","stdio clients"],"limitation":"Scan output is evidence from a scanner, not a guarantee that generated code is secure.","reviewedAt":"2026-09-21","revision":"0516c0f23a3dceac5c8f5ff3fecd402af4450182","definitionSha256":null,"sourceUrl":"https://raw.githubusercontent.com/semgrep/semgrep/0516c0f23a3dceac5c8f5ff3fecd402af4450182/cli/src/semgrep/mcp/README.md","permissions":["Reads source files and invokes scanner tooling; source text/results are returned to the client.","Depending on mode, calls Semgrep services and authenticated findings APIs."],"cost":"Open-source CLI and commercial Semgrep services have different terms; account features and the AI client may add costs.","license":{"name":"LGPL-2.1 (CLI source; commercial services separate)","url":"https://raw.githubusercontent.com/semgrep/semgrep/0516c0f23a3dceac5c8f5ff3fecd402af4450182/LICENSE"}}]},{"id":"review-a-terraform-plan","title":"Review Terraform before applying","category":"operate","summary":"Inspect HCL, version constraints and planned resource changes before granting any apply authority.","outcome":"A plan review with destructive changes, sensitive outputs and recovery questions made explicit.","inputs":["Terraform source, lockfile, backend identity and a fixed revision.","A saved plan or authorised non-production planning environment and the intended change."],"parallel":[{"title":"Configuration review","detail":"Check naming, module boundaries, variable contracts and sensitive values without changing provider versions."},{"title":"Impact review","detail":"Inspect the saved plan against the intended resource changes and identify replacement or destruction."}],"steps":["Pin the Terraform and provider versions and confirm backend/workspace identity. Use public Registry documentation lookup without HCP/TFE credentials unless account access is actually needed.","Review formatting and validation output, then obtain a saved plan through the authorised project process. Inspect refresh/external-data effects and protect plan files that contain secrets.","Reconcile plan actions with requirements, backups and rollback feasibility. Hand over an explicit apply decision; do not execute state manipulation or destruction copied from a generic recovery example."],"boundaries":["Terraform MCP includes workspace and run mutations when credentials and tools permit them. Registry lookup is not a read-only guarantee for the full server.","The agent grants editing and terminal tools; approval language does not enforce permissions. Plans can contact providers, and backend/refresh behaviour is version-sensitive."],"deliverables":["Version/backend record","Validation and plan receipts","Resource-impact table","Apply decision and recovery note"],"checks":["The plan belongs to the intended revision, workspace and lockfile.","Every replacement or deletion has an explicit rationale.","Secret-bearing plan/state content is excluded from shared evidence.","Recovery feasibility is checked per resource before apply is considered."],"template":{"title":"Terraform change review","sections":[{"heading":"Identity","body":"Revision: ___\nTerraform/provider versions: ___\nLockfile hash: ___\nBackend/workspace/account: ___"},{"heading":"Plan evidence","body":"Plan command/process: ___\nPlan timestamp/hash: ___\nValidation output: ___\nRefresh or external-data effects: ___"},{"heading":"Impact","body":"| Resource | Planned action | Requirement | Destructive/replacement risk | Recovery |\n| --- | --- | --- | --- | --- |\n| ___ | ___ | ___ | ___ | ___ |"},{"heading":"Decision","body":"Unexplained actions: ___\nBackup/restore evidence: ___\nApprover and maintenance window: ___\nApply status: not authorised by this worksheet"}]},"resources":[{"kind":"skills","id":"hashicorp-terraform-style-guide","purpose":"Review HCL structure without turning sample versions into upgrade instructions.","name":"Terraform style guide","href":"/skills/hashicorp-terraform-style-guide/","compatibility":["Agent Skills-compatible hosts"],"limitation":"The resource snippets omit project-specific required values and are not deployment-ready. Suggested versions and latest-provider guidance do not authorize an upgrade.","reviewedAt":"2026-10-07","revision":"f706481af9b8fedb66de909f6243ad29601afa0c","definitionSha256":null,"sourceUrl":"https://github.com/hashicorp/agent-skills/tree/f706481af9b8fedb66de909f6243ad29601afa0c/plugins/terraform/skills/terraform-style-guide","permissions":["Writes and formats Terraform files and invokes validation; any later plan or apply uses the host account and provider permissions.","The host enforces permissions; installing instructions does not itself create a sandbox."],"cost":"Source is available under the stated licence. Model usage, compute and connected services can incur charges.","license":{"name":"MPL-2.0","url":"https://github.com/hashicorp/agent-skills/blob/f706481af9b8fedb66de909f6243ad29601afa0c/LICENSE"}},{"kind":"agents","id":"github-terraform-iac-reviewer","purpose":"Organise plan impact, validation evidence and recovery questions.","name":"Terraform Iac Reviewer","href":"/agents/github-terraform-iac-reviewer/","compatibility":["GitHub Copilot custom agents in VS Code"],"limitation":"Terminal and editing access can change infrastructure. Approval before apply is an instruction, not an enforced host permission boundary.","reviewedAt":"2026-09-21","revision":"ad4c196b933c5ca7f82a5ba78969ddcd2603ba80","definitionSha256":"6cdff3504bdf06504c3658a5d5a0127c918a99afbe9a4e46acc6cb7062940846","sourceUrl":"https://raw.githubusercontent.com/github/awesome-copilot/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/terraform-iac-reviewer.agent.md","permissions":["Requested: codebase, edit/editFiles, terminalCommand, search, githubRepo.","Instructed to review and create Terraform, run fmt/validate/scan/plan/apply. Apply-after-approval is not a technical lock. Not a sandbox."],"cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","license":{"name":"MIT","url":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/LICENSE"}},{"kind":"mcp-servers","id":"terraform","purpose":"Optionally retrieve Registry documentation for exact provider/module versions.","name":"Terraform MCP Server","href":"/mcp-servers/terraform/","compatibility":["An MCP client supporting stdio, Streamable HTTP.","Docker; HCP Terraform or Terraform Enterprise access only for account operations."],"limitation":"HCP/TFE workspace tools include creation, updates and deletion; registry lookup does not imply a read-only server.","reviewedAt":"2026-09-21","revision":"e2481878ee40560a91f07c38c09a478ede9fb87a","definitionSha256":null,"sourceUrl":"https://github.com/hashicorp/terraform-mcp-server","permissions":["Reads public registry documentation.","Credentialed tools can change workspaces, variables, tags and runs."],"cost":"Registry lookup and local hosting are distinct from HCP/TFE account and run costs.","license":{"name":"MPL-2.0","url":"https://github.com/hashicorp/terraform-mcp-server/blob/e2481878ee40560a91f07c38c09a478ede9fb87a/LICENSE"}}]},{"id":"triage-a-kubernetes-workload","title":"Triage a Kubernetes workload","category":"operate","summary":"Inspect workload events, logs and rollout state in a confirmed namespace before proposing a cluster change.","outcome":"A namespace-scoped diagnosis with evidence, remediation options and an explicit operational boundary.","inputs":["Cluster/context and namespace identifiers with a restricted kubeconfig or service account.","The affected workload, incident window and recent deployment or manifest change."],"parallel":[{"title":"Workload evidence","detail":"Inspect selected events, pod status and logs without editing the cluster."},{"title":"Manifest review","detail":"Compare probes, resource requests and deployment settings against the intended workload behaviour."}],"steps":["Confirm the actual context and namespace. Configure the MCP server with read_only = true in TOML and use RBAC limited to the required inspection; do not assume its default is read-only.","Collect timestamped workload evidence and correlate it with the manifest revision. Keep secrets and unrelated namespace data out of the model context.","Draft a minimal remediation and an observation window. Validate it in an authorised test environment before separately deciding any rollout, scale or rollback action."],"boundaries":["The SRE profile has edit and terminal capabilities; its prose does not prevent kubectl or Helm mutations. Keep inspection permissions restricted in the host and cluster.","The server exposes management tools by default. Network listeners need their own binding/authentication controls, and log queries can reveal sensitive values."],"deliverables":["Context and RBAC record","Workload event timeline","Manifest-linked diagnosis","Remediation and rollback proposal"],"checks":["Context, account and namespace are verified before every operational session.","Read-only server configuration and RBAC are both recorded.","The diagnosis cites actual events/logs and preserves contrary evidence.","No rollout success is claimed without an observed readiness and error-rate window."],"template":{"title":"Kubernetes triage sheet","sections":[{"heading":"Access scope","body":"Context/cluster: ___\nNamespace/workload: ___\nIdentity and RBAC: ___\nRead-only TOML path/hash: ___"},{"heading":"Observation","body":"Window/time zone: ___\nPod/event/log evidence: ___\nCurrent rollout revision: ___\nSensitive data removed: ___"},{"heading":"Diagnosis","body":"Manifest setting involved: ___\nSupporting and contradictory observations: ___\nMissing evidence: ___\nProposed minimal change: ___"},{"heading":"Operational handoff","body":"Test environment and result: not run\nReadiness/error checks: ___\nRollback condition/owner: ___\nCluster changes executed: not recorded\nThis inspection does not authorise cluster changes."}]},"resources":[{"kind":"agents","id":"github-platform-sre-kubernetes","purpose":"Review manifests, rollout conditions and operational recovery options.","name":"Platform SRE for Kubernetes","href":"/agents/github-platform-sre-kubernetes/","compatibility":["GitHub Copilot custom-agent format; inspect tool/model fields for the installed client"],"limitation":"Tool identifiers are host-specific and need adaptation. Replica counts, probes and deployment policies are examples; no cluster action or workload validation occurred here.","reviewedAt":"2026-10-07","revision":"3a685010a7afdc0dbd4c83b7fbda6c316aa516e5","definitionSha256":"ce7da8d73aaf59051481e32a7eca520fa536856f560aa3c6cdcdb3d14b5f5b0e","sourceUrl":"https://raw.githubusercontent.com/github/awesome-copilot/3a685010a7afdc0dbd4c83b7fbda6c316aa516e5/agents/platform-sre-kubernetes.agent.md","permissions":["Declared tools: codebase, edit/editFiles, terminalCommand, search, githubRepo.","Declared edit/terminal tools can change manifests and run kubectl or Helm commands that mutate a cluster.","The host enforces permissions; installing instructions does not itself create a sandbox."],"cost":"Source is available under the stated licence. Model usage, compute and connected services can incur charges.","license":{"name":"MIT","url":"https://github.com/github/awesome-copilot/blob/3a685010a7afdc0dbd4c83b7fbda6c316aa516e5/LICENSE"}},{"kind":"mcp-servers","id":"kubernetes","purpose":"Retrieve scoped cluster resources and logs under explicit read-only configuration and RBAC.","name":"Kubernetes MCP Server","href":"/mcp-servers/kubernetes/","compatibility":["An MCP client supporting stdio or Streamable HTTP.","Node.js for the launcher and Kubernetes/OpenShift access through kubeconfig or in-cluster configuration."],"limitation":"The configuration defaults read_only to false; enabled tools can create, update or delete resources.","reviewedAt":"2026-09-21","revision":"6fd66fb432d393ad662714e7baad5bdce5369870","definitionSha256":null,"sourceUrl":"https://github.com/containers/kubernetes-mcp-server","permissions":["Reads cluster resources and logs; enabled operations can mutate or delete resources and use administrative tools."],"cost":"Cluster hosting and any resources created through enabled tools determine cost.","license":{"name":"Apache-2.0","url":"https://github.com/containers/kubernetes-mcp-server/blob/6fd66fb432d393ad662714e7baad5bdce5369870/LICENSE"}}]},{"id":"verify-a-release-and-rollback","title":"Verify a release and its rollback path","category":"operate","summary":"Keep package identity, public availability and observed installation behaviour as separate release checks.","outcome":"A release evidence bundle with exact artifact hashes, meaningful public responses and a tested or explicitly untested rollback path.","inputs":["The exact revision/version, packaged artifacts and expected public surfaces.","An isolated consumer environment plus the approved activation and rollback procedure."],"parallel":[{"title":"Artifact verifier","detail":"Hash the immutable package and check its extracted files and clean-consumer behaviour."},{"title":"Public observer","detail":"After activation, inspect actual public content and compare it with the expected release identity."}],"steps":["Freeze the artifact before testing. Install or extract that exact package in an isolated consumer and record the actual command, output and exit status.","After authorised activation, collect timestamped response bodies with meaningful identity markers; reject soft-404 or stale-version content even when status is 200.","Run the offline receipt checker with evidence files contained beside its input. Separate independently observed runtime evidence from a supplied attestation, and state whether rollback was exercised or only planned."],"boundaries":["The offline checker validates supplied files and declared runtime evidence; it does not contact the site or establish that an installation happened.","Verification is not deployment authority. Public queries, installation scripts and rollback operations each need the permission appropriate to their actual effects."],"deliverables":["Immutable artifact manifest","Clean-consumer receipt","Public semantic-response bundle","Rollback readiness record"],"checks":["Tested and published artifacts have the same recorded hashes.","Public content identifies the expected release rather than merely returning 200.","Runtime evidence says who observed it and when.","Rollback status distinguishes an executed check from a written procedure."],"template":{"title":"Release verification packet","sections":[{"heading":"Artifact","body":"Revision/version: ___\nArchive path and SHA-256: ___\nExpected entry points: ___\nFrozen at: ___"},{"heading":"Consumer","body":"Clean environment/runtime: ___\nExact install/run command: ___\nExit and saved output: not run\nObserver: ___"},{"heading":"Public proof","body":"| URL | Checked at | Status | Required identity marker | Body path/hash |\n| --- | --- | --- | --- | --- |\n| ___ | ___ | not fetched | ___ | ___ |"},{"heading":"Release disposition","body":"Local identity: not checked\nPublic identity: not checked\nRuntime: not checked\nRollback target/procedure: ___\nRollback actually exercised: ___\nUnresolved release blockers: ___"}]},"resources":[{"kind":"skills","id":"undominated-release-proof","purpose":"Check artifact hashes and semantic public-response receipts within a bounded evidence folder.","name":"Undominated · Resource release proof","href":"/skills/undominated-release-proof/","compatibility":["Agent Skills compatible hosts","Python 3.10+"],"limitation":"Deterministic local checks over supplied evidence; not a guarantee of source truth or production suitability.","reviewedAt":"2026-10-07","revision":"a67bd9b86fca7455ed208403d9ea6f9fe847cd99","definitionSha256":"676ce9e0977fc1a0dc259c10fb19d44211c5ac6c9229d72d58655a6af9d8895c","sourceUrl":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-release-proof/SKILL.md","permissions":["read:user-selected-local-file"],"cost":"MIT source at no charge. Your agent host or model provider may charge for use; the included offline checks require no paid API.","license":{"name":"MIT","url":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-release-proof/LICENSE"}},{"kind":"agents","id":"undominated-release-verifier","purpose":"Independently inspect clean installation and observed public availability.","name":"Undominated · Resource release verifier","href":"/agents/undominated-release-verifier/","compatibility":["Portable Markdown role instructions"],"limitation":"Portable profile; manually load or adapt to a native agent format. No automatic subagent registration or permission grants.","reviewedAt":"2026-10-07","revision":"a67bd9b86fca7455ed208403d9ea6f9fe847cd99","definitionSha256":"09bf7c3f9b55ffdb674e4c2c525017ad21b0d441e830d4a4c829a39d63e2c0cf","sourceUrl":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/agents/undominated-release-verifier/AGENT.md","permissions":["read:assigned-sources","write:assigned-workspace"],"cost":"MIT source at no charge. Your agent host or model provider may charge for use.","license":{"name":"MIT","url":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/agents/undominated-release-verifier/LICENSE"}}]},{"id":"test-and-document-a-dbt-model","title":"Test and document a dbt model change","category":"data","summary":"Specify input rows and expected outputs, then keep the model’s grain and column documentation aligned with the change.","outcome":"A reviewed SQL-model test, updated documentation and an isolated warehouse execution receipt.","inputs":["A dbt SQL model, relevant refs/sources and a fixed project revision.","Supported dbt/adapter versions and an isolated development schema with prepared parent relations."],"parallel":[{"title":"Fixture design","detail":"Derive expected rows from the business rule, including nulls, duplicates and boundary values."},{"title":"Documentation audit","detail":"Inspect the manifest and model SQL for grain and declared-column meaning without inventing descriptions."}],"steps":["Choose the target schema explicitly and inspect which CLI or Platform tools are enabled. Mocked dbt unit inputs still require warehouse execution.","Create input fixtures and expected rows; handle ephemeral dependencies using the documented fixture format. Execute only in the disposable development scope and preserve output and exit status.","Update model and column descriptions from the SQL and domain evidence. Re-parse and inspect all modified and untracked YAML files, not only a path-scoped diff."],"boundaries":["Do not run --empty against relations that must be retained; dbt build/run and enabled MCP tools can replace warehouse objects or trigger jobs.","Documentation coverage counts declared manifest columns with nonempty descriptions, not every physical column or semantic correctness. Platform features have separate credentials and entitlements."],"deliverables":["Business-rule fixtures","Unit-test YAML and expected rows","Model/column documentation diff","Development execution receipt"],"checks":["The target schema is isolated from retained production relations.","Expected rows are derived independently of the implementation.","All new and modified YAML files are included in review.","Documentation states the model grain and preserves unresolved column meanings."],"template":{"title":"dbt model change packet","sections":[{"heading":"Scope","body":"Model/revision: ___\nGrain/business rule: ___\ndbt and adapter versions: ___\nDisposable target schema: ___"},{"heading":"Fixtures","body":"| Case | Input rows/reference | Expected rows/reference | Rule exercised |\n| --- | --- | --- | --- |\n| ___ | ___ | ___ | ___ |"},{"heading":"Execution","body":"Parent relations prepared: ___\nSelected command and tool scope: ___\nObserved exit/output: not run\nObjects created or replaced: ___"},{"heading":"Documentation","body":"Manifest path/hash: ___\nDescriptions changed: ___\nUnknown column meanings: ___\nUntracked/new YAML checked: ___\nDomain-owner review: ___"}]},"resources":[{"kind":"skills","id":"dbt-labs-adding-dbt-unit-test","purpose":"Write explicit SQL-model input fixtures and expected rows.","name":"Adding a dbt unit test","href":"/skills/dbt-labs-adding-dbt-unit-test/","compatibility":["Agent Skills-compatible hosts","dbt"],"limitation":"Mocked inputs do not make dbt tests offline. SQL models only; not a validator of production data, Python models or final incremental-table state. Never run --empty against data that must be retained.","reviewedAt":"2026-10-07","revision":"168a2b0b92da59be88866257140907c206ff0e44","definitionSha256":null,"sourceUrl":"https://github.com/dbt-labs/dbt-agent-skills/tree/168a2b0b92da59be88866257140907c206ff0e44/skills/dbt/skills/adding-dbt-unit-test","permissions":["Writes YAML/SQL/CSV fixtures and runs warehouse-connected dbt commands; --empty and build/run can replace relations.","The host enforces permissions; installing instructions does not itself create a sandbox."],"cost":"Source is available under the stated licence. Model usage, compute and connected services can incur charges.","license":{"name":"Apache-2.0","url":"https://github.com/dbt-labs/dbt-agent-skills/blob/168a2b0b92da59be88866257140907c206ff0e44/LICENSE"}},{"kind":"skills","id":"dbt-labs-maintaining-dbt-documentation","purpose":"Audit declared descriptions and draft source-backed model/column documentation.","name":"dbt Documentation Maintenance","href":"/skills/dbt-labs-maintaining-dbt-documentation/","compatibility":["Agent Skills-compatible coding agents","Claude Code"],"limitation":"The audit measures nonempty descriptions, not their correctness or every physical warehouse column; imported model nodes can also appear in a manifest.","reviewedAt":"2026-09-21","revision":"a8607fc02a679e81a2b0fe7fcb32a7568802e16a","definitionSha256":null,"sourceUrl":"https://github.com/dbt-labs/dbt-agent-skills/tree/a8607fc02a679e81a2b0fe7fcb32a7568802e16a/skills/dbt/skills/maintaining-dbt-documentation","permissions":["Read model SQL, YAML, macros and generated manifest JSON","Write documentation and run dbt parse","Optional authorized warehouse reads to inspect columns not declared in the manifest"],"cost":"Apache-licensed instructions and helper; agent calls and any optional dbt platform or warehouse compute are separate.","license":{"name":"Apache-2.0","url":"https://github.com/dbt-labs/dbt-agent-skills/blob/a8607fc02a679e81a2b0fe7fcb32a7568802e16a/LICENSE"}},{"kind":"mcp-servers","id":"dbt","purpose":"Optionally inspect lineage or invoke an explicitly permitted development command.","name":"dbt MCP Server","href":"/mcp-servers/dbt/","compatibility":["An MCP client supporting stdio.","A supported Python environment and dbt project/runtime or Platform account."],"limitation":"CLI and administrative tools can change warehouse objects or trigger/cancel jobs.","reviewedAt":"2026-09-21","revision":"e0b8c67f9a661c5414977301cd1b05ea7b2e6fc9","definitionSha256":null,"sourceUrl":"https://github.com/dbt-labs/dbt-mcp","permissions":["Reads model definitions, lineage and metrics; enabled CLI/API tools can build models, execute queries and manage job runs."],"cost":"dbt Platform entitlements, warehouse queries and local execution determine cost.","license":{"name":"Apache-2.0","url":"https://github.com/dbt-labs/dbt-mcp/blob/e0b8c67f9a661c5414977301cd1b05ea7b2e6fc9/LICENSE"}}]},{"id":"evaluate-retrieval-grounding","title":"Evaluate retrieval grounding and abstention","category":"data","summary":"Use a labelled question set to inspect retrieval evidence, answer grounding and behaviour when the corpus cannot answer.","outcome":"A reproducible retrieval evaluation with documented misses, unsupported answers and leakage checks.","inputs":["Versioned corpus, an existing populated collection, chunking/embedding configuration and retrieval code.","Held-out questions with authorised expected evidence and an existing evaluation runner."],"parallel":[{"title":"Pipeline inspection","detail":"Review filtering, chunking, reranking and prompt assembly for leakage or dropped evidence."},{"title":"Case adjudication","detail":"Label relevant source passages and unanswerable questions independently of retrieved outputs."}],"steps":["Freeze the corpus and configuration. For optional Qdrant inspection require an existing collection, set QDRANT_READ_ONLY=true, scope credentials and record embedding-model requirements. Check that startup will not provision a missing collection.","Run the same question set through the authorised evaluation harness. Preserve retrieved IDs, expected passages and unsupported answers; do not treat a changed top result as proof of a better reranker.","Inspect misses and abstention failures by case. Propose a bounded retrieval change and rerun the held-out cases without tuning their labels to the result."],"boundaries":["Qdrant MCP retrieves semantic memories; it is not a complete RAG evaluation harness. Read-only mode removes the storage tool, but does not by itself establish zero backend writes during setup. Use an existing collection and credentials that deny provisioning; FastEmbed can download models and use local compute.","The reviewer supplies no dataset or evaluation dependencies. Its read-only Bash instruction is not a sandbox, and model calls or corpus uploads require separate authorisation."],"deliverables":["Corpus/configuration manifest","Question and relevance set","Per-case retrieval/answer evidence","Failure analysis and next experiment"],"checks":["Evaluation labels were set independently of the tested output.","Unanswerable cases and missing-source cases are included.","Retrieved source IDs trace to the frozen corpus, and inspection uses an existing collection without provisioning permissions.","Any aggregate measure names its case denominator and excluded cases."],"template":{"title":"Retrieval evaluation worksheet","sections":[{"heading":"Frozen system","body":"Corpus version/hash: ___\nChunker/embedding/reranker configuration: ___\nExisting collection identity: ___\nRead-only setting and denied provisioning permissions: ___\nRunner version: ___"},{"heading":"Case labels","body":"| Question ID | Expected passage IDs | Answerable? | Label source |\n| --- | --- | --- | --- |\n| ___ | ___ | unknown | ___ |"},{"heading":"Observed output","body":"Retrieved IDs/ranks: ___\nAnswer and cited passages: ___\nUnsupported statements: ___\nAbstention behaviour: not run"},{"heading":"Experiment","body":"Failure categories: ___\nCase denominator/exclusions: ___\nSingle proposed change: ___\nHeld-out rerun evidence: not run\nData-sharing limits: ___"}]},"resources":[{"kind":"agents","id":"ecc-rag-pipeline-reviewer","purpose":"Challenge grounding, pruning, fallback and evaluation-policy evidence.","name":"Rag Pipeline Reviewer","href":"/agents/ecc-rag-pipeline-reviewer/","compatibility":["Claude Code subagents"],"limitation":"The read-only Bash rule is an instruction; the host must enforce the intended access boundary.","reviewedAt":"2026-09-21","revision":"2b6e839771e53096d8451a213d40dc64ec8acac0","definitionSha256":"793432a0c4e44aa4c640cb85ec24b47062ed044782852b0ba67323d860154fec","sourceUrl":"https://raw.githubusercontent.com/affaan-m/everything-claude-code/2b6e839771e53096d8451a213d40dc64ec8acac0/agents/rag-pipeline-reviewer.md","permissions":["Requested: Read, Grep, Glob, Bash. Instructed: Bash read-only, no new packages, no secret dumps. Not enforced by an OS sandbox. Reviewer title still only inspects if the host honors the tool list."],"cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","license":{"name":"MIT","url":"https://github.com/affaan-m/everything-claude-code/blob/2b6e839771e53096d8451a213d40dc64ec8acac0/LICENSE"}},{"kind":"mcp-servers","id":"qdrant","purpose":"Optionally inspect a scoped collection’s retrieved matches without enabling storage.","name":"Qdrant MCP Server","href":"/mcp-servers/qdrant/","compatibility":["An MCP client supporting stdio, SSE, Streamable HTTP.","uv/Python, a Qdrant endpoint or local data path, and storage for the embedding model."],"limitation":"Storage is enabled by default; QDRANT_READ_ONLY must be set for retrieval-only use.","reviewedAt":"2026-09-21","revision":"c56ae5adf62bb78d852bf7bbcbc5d7b75e2bbe41","definitionSha256":null,"sourceUrl":"https://github.com/qdrant/mcp-server-qdrant","permissions":["Reads vector matches; the enabled store tool writes text embeddings and metadata to Qdrant."],"cost":"Qdrant hosting and local embedding compute determine cost.","license":{"name":"Apache-2.0","url":"https://github.com/qdrant/mcp-server-qdrant/blob/c56ae5adf62bb78d852bf7bbcbc5d7b75e2bbe41/LICENSE"}}]},{"id":"verify-feature-telemetry","title":"Verify telemetry for a new feature","category":"data","summary":"Start from operational questions, then check whether emitted logs, metrics and traces can actually answer them.","outcome":"An instrumentation contract and staging evidence for successful, failed and missing-telemetry paths.","inputs":["Feature source and concrete diagnostic questions.","An authorised staging service, telemetry backend and a privacy/retention policy."],"parallel":[{"title":"Question mapping","detail":"Map each operational question to a signal, owner and interpretation."},{"title":"Data-flow review","detail":"Inspect field allowlists, cardinality, request identity and sampling before adding instrumentation."}],"steps":["Define bounded labels and redact sensitive fields. Validate untrusted request identifiers and distinguish request correlation from the event that initiated a shared job.","Generate controlled staging success and failure cases, then query the expected signals. If Grafana is used, disable writes and separately restrict datasource queries; a write-disabled server does not constrain SQL grants.","Check missing signals, sampling effects and alert routing. Record actual observations and overhead measurements if taken; leave SLO thresholds and unmeasured impact as explicit decisions."],"boundaries":["Instrumentation changes can export private data and trigger notifications. Use approved staging destinations and separately authorise any alert test.","Grafana authentication, datasource permissions and query costs are separate controls. A dashboard’s existence does not establish that its data is correct or complete."],"deliverables":["Question-to-signal map","Field/label privacy contract","Staging telemetry receipts","Alert and missing-signal checklist"],"checks":["Every signal answers a named operational question.","Metric labels have an explicit bounded value policy.","Success, failure and missing-signal paths are observed.","Alert tests use an approved destination and retain their actual outcome."],"template":{"title":"Feature telemetry contract","sections":[{"heading":"Questions","body":"Feature/revision: ___\nOperational question: ___\nSignal and owner: ___\nInterpretation limits: ___"},{"heading":"Data policy","body":"Allowed fields: ___\nRedacted fields: ___\nBounded metric labels: ___\nCorrelation/initiator identity: ___\nSampling/retention: ___"},{"heading":"Staging proof","body":"| Scenario | Expected signal | Observed evidence | Missing data |\n| --- | --- | --- | --- |\n| ___ | ___ | not run | ___ |"},{"heading":"Operations","body":"Datasource grants/tool restrictions: ___\nAlert test destination/authorisation: ___\nObserved overhead, if measured: ___\nThreshold decision and source: ___"}]},"resources":[{"kind":"skills","id":"addyosmani-observability-and-instrumentation","purpose":"Design signals around operational questions and test their failure paths.","name":"Observability and instrumentation","href":"/skills/addyosmani-observability-and-instrumentation/","compatibility":["Agent Skills-compatible hosts"],"limitation":"Sample thresholds and the prescribed alerting policy are starting points, not universal SLOs. Validate untrusted request IDs and measure overhead, sampling and privacy in the real system.","reviewedAt":"2026-10-07","revision":"1401c8b8030e023baeebb31781a6653fe8e93026","definitionSha256":null,"sourceUrl":"https://github.com/addyosmani/agent-skills/tree/1401c8b8030e023baeebb31781a6653fe8e93026/skills/observability-and-instrumentation","permissions":["Edits application logging/metrics/tracing and alert configuration; verification emits telemetry, sends test traffic and may trigger notification channels.","The host enforces permissions; installing instructions does not itself create a sandbox."],"cost":"Source is available under the stated licence. Model usage, compute and connected services can incur charges.","license":{"name":"MIT","url":"https://github.com/addyosmani/agent-skills/blob/1401c8b8030e023baeebb31781a6653fe8e93026/LICENSE"}},{"kind":"mcp-servers","id":"grafana","purpose":"Optionally inspect the relevant dashboard and datasource evidence with restricted tools.","name":"Grafana MCP Server","href":"/mcp-servers/grafana/","compatibility":["An MCP client supporting stdio, SSE, Streamable HTTP.","uv and access to a supported Grafana instance."],"limitation":"Write tools are enabled unless disabled; raw SQL permissions also depend on the underlying datasource.","reviewedAt":"2026-09-21","revision":"20b20b3aec8ebc56162ffac233ac9de9e46f5684","definitionSha256":null,"sourceUrl":"https://github.com/grafana/mcp-grafana","permissions":["Reads dashboards, telemetry and datasource query results.","Enabled tools can change Grafana state; SQL datasource queries may mutate data if allowed downstream."],"cost":"Grafana and connected datasource plans or hosting/query usage apply.","license":{"name":"Apache-2.0","url":"https://github.com/grafana/mcp-grafana/blob/20b20b3aec8ebc56162ffac233ac9de9e46f5684/LICENSE"}}]},{"id":"audit-a-benchmark-comparison","title":"Audit a benchmark comparison","category":"decide","summary":"Check model identity, matched coverage and sample selection before interpreting a correlation or ranking disagreement.","outcome":"A reproducible cohort audit with missingness, descriptive correlations and limits on the comparison.","inputs":["Two permitted benchmark snapshots with dates, licences and exact model identifiers.","A stated target population and documented inclusion/exclusion rules."],"parallel":[{"title":"Identity and coverage","detail":"Reconstruct exact model joins and keep missing scores in the population ledger."},{"title":"Claim challenge","detail":"Review selection bias and the proposed wording without seeing a preferred conclusion."}],"steps":["Freeze snapshots and rights evidence. Define the population before inspecting the result, and reject fuzzy identity joins that lack supporting evidence.","Prepare the checker’s explicit rows with null for missing scores. Compute matched coverage and descriptive correlations; investigate constant columns or too few matched rows instead of forcing a number.","Compare justified cohort variants and report the denominator and missingness with every conclusion. Request evaluator-specific evidence for interval or significance claims."],"boundaries":["A restricted or frontier-only cohort does not represent all models. Correlation does not demonstrate task interchangeability or causation.","Overlapping individual intervals do not prove equivalence. The checker produces no significance test and does not verify dataset rights or score provenance."],"deliverables":["Snapshot and rights ledger","Exact identity crosswalk","Coverage/correlation receipt","Qualified comparison note"],"checks":["Each join has a documented exact identity basis.","Missing models remain in the stated coverage denominator.","Correlation is labelled with the matched sample and selection rule.","No interval overlap or descriptive correlation is recast as equivalence or causation."],"template":{"title":"Benchmark comparison worksheet","sections":[{"heading":"Population","body":"Claim under review: ___\nTarget population: ___\nSelection rule: ___\nSnapshot URLs/dates/hashes/licences: ___"},{"heading":"Identity and missingness","body":"| Exact model ID | Source A identity/score | Source B identity/score | Join evidence or missing reason |\n| --- | --- | --- | --- |\n| ___ | unknown | unknown | ___ |"},{"heading":"Computation","body":"Input JSON path/hash: ___\nMatched/total/missing counts: not computed\nChecker output/exit: not run\nSensitivity cohort and result: ___"},{"heading":"Interpretation","body":"What the observed cohort supports: ___\nWhat it cannot support: ___\nInterval-comparison evidence, if any: ___\nReview decision: ___"}]},"resources":[{"kind":"skills","id":"undominated-benchmark-audit","purpose":"Compute bounded matched-cohort coverage and correlations from supplied rows.","name":"Undominated · Benchmark cohort audit","href":"/skills/undominated-benchmark-audit/","compatibility":["Agent Skills compatible hosts","Python 3.10+"],"limitation":"Deterministic local checks over supplied evidence; not a guarantee of source truth or production suitability.","reviewedAt":"2026-10-07","revision":"a67bd9b86fca7455ed208403d9ea6f9fe847cd99","definitionSha256":"783038e101eadb11f1c6b94fa20fc9fd3158b4a503e739b8b72d7c976c4193d4","sourceUrl":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-benchmark-audit/SKILL.md","permissions":["read:user-selected-local-file"],"cost":"MIT source at no charge. Your agent host or model provider may charge for use; the included offline checks require no paid API.","license":{"name":"MIT","url":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-benchmark-audit/LICENSE"}},{"kind":"agents","id":"undominated-evidence-reviewer","purpose":"Independently challenge joins, denominators and the conclusion’s scope.","name":"Undominated · Evidence reviewer","href":"/agents/undominated-evidence-reviewer/","compatibility":["Portable Markdown role instructions"],"limitation":"Portable profile; manually load or adapt to a native agent format. No automatic subagent registration or permission grants.","reviewedAt":"2026-10-07","revision":"a67bd9b86fca7455ed208403d9ea6f9fe847cd99","definitionSha256":"e1ba060c4e782b46b90e73ba1f04a927b7881d7f2d7adae53db55370963dcad3","sourceUrl":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/agents/undominated-evidence-reviewer/AGENT.md","permissions":["read:assigned-sources","write:assigned-workspace"],"cost":"MIT source at no charge. Your agent host or model provider may charge for use.","license":{"name":"MIT","url":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/agents/undominated-evidence-reviewer/LICENSE"}}]},{"id":"compare-provider-quotes","title":"Compare provider quotes for one workload","category":"decide","summary":"Preserve model identity, serving precision, service tier and every pricing rung before comparing distinct sellers.","outcome":"A source-backed quote comparison with excluded offers and unsupported billing components made visible.","inputs":["Dated first-party quotes for the same exact model, currency, precision and service tier.","Uncached input and billed output token counts, plus a documented seller-owner map."],"parallel":[{"title":"Quote extraction","detail":"Capture complete rate ladders and billing footnotes without deriving numbers from marketing prose."},{"title":"Identity and terms review","detail":"Check model/version, seller ownership, precision and service-tier comparability independently."}],"steps":["Save source URLs and dates for every rate. Use Undominated MCP only as an optional published-evidence starting point; confirm the chosen seller’s primary terms.","Build the full input-length ladder ending in an explicit unbounded rung and run the quote checker for the stated workload. Separate unsupported cache, reasoning, per-call and marginal-block billing instead of guessing them.","Use the seller-spread check only for a separately stated input or output rate after establishing like-for-like scope. Keep owner-level and row-level spreads separate and report unknown precision or mixed service tiers as exclusions."],"boundaries":["The quote calculator models an entire request at its selected input-length rung; it does not model every possible bill. A generic model reference price is not a complete set of seller quotes.","The spread checker trusts the supplied seller-owner map and does not establish precision equivalence. Neither a lower rate nor a script pass establishes endpoint reliability or migration suitability."],"deliverables":["Workload and identity sheet","Complete quote ladder table","Excluded-offer ledger","Comparison receipt with source dates"],"checks":["All compared quotes share exact model, precision, currency and service tier.","Every ladder retains all boundaries and an explicit final unbounded rung.","Unknown precision and unsupported billing components are not silently normalised.","Seller ownership is documented and one company’s service tiers are not counted as competitors."],"template":{"title":"Provider quote comparison","sections":[{"heading":"Workload","body":"Exact model/version: ___\nPrecision and service tier: ___\nCurrency: ___\nUncached input/billed output tokens: ___\nUnsupported billing components: ___"},{"heading":"Source ledger","body":"| Seller owner | Endpoint | Source/date | Currency and unit | Complete tier table path |\n| --- | --- | --- | --- | --- |\n| ___ | ___ | ___ | ___ | ___ |"},{"heading":"Comparability","body":"Excluded offer and reason: ___\nOwner-map evidence: ___\nContext/privacy/residency constraints: ___\nUnresolved precision or terms: ___"},{"heading":"Calculation","body":"Quote-check input/output/exit: not run\nSeparate spread rate and claimed multiple: ___\nOwner-level versus row-level result: not computed\nConclusion limited to this workload: ___"}]},"resources":[{"kind":"skills","id":"undominated-provider-quote-compare","purpose":"Recompute the narrow uncached-input/billed-output workload over complete supplied ladders.","name":"Undominated · Provider quote comparison","href":"/skills/undominated-provider-quote-compare/","compatibility":["Agent Skills compatible hosts","Python 3.10+"],"limitation":"Deterministic local checks over supplied evidence; not a guarantee of source truth or production suitability.","reviewedAt":"2026-10-07","revision":"a67bd9b86fca7455ed208403d9ea6f9fe847cd99","definitionSha256":"8efe1c64f23bf2addc81b82091620c952345124df4d97e56f15830cfad4763b1","sourceUrl":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-provider-quote-compare/SKILL.md","permissions":["read:user-selected-local-file"],"cost":"MIT source at no charge. Your agent host or model provider may charge for use; the included offline checks require no paid API.","license":{"name":"MIT","url":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-provider-quote-compare/LICENSE"}},{"kind":"skills","id":"undominated-seller-spread","purpose":"Check a separately scoped rate multiple across supplied distinct seller owners.","name":"Undominated · Seller-spread audit","href":"/skills/undominated-seller-spread/","compatibility":["Agent Skills compatible hosts","Python 3.10+"],"limitation":"Deterministic local checks over supplied rows and caller-assigned seller owners; not a guarantee of source truth or market coverage.","reviewedAt":"2026-10-07","revision":"a67bd9b86fca7455ed208403d9ea6f9fe847cd99","definitionSha256":"79cc9edd7098b9c3640a7d03b085920674bbf5f1b803f02dfb86c3b97e04cb76","sourceUrl":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-seller-spread/SKILL.md","permissions":["read:user-selected-local-file"],"cost":"MIT source at no charge. Your agent host or model provider may charge for use; the included offline checks require no paid API.","license":{"name":"MIT","url":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-seller-spread/LICENSE"}},{"kind":"agents","id":"undominated-pricing-source-reviewer","purpose":"Challenge currency, units, tier boundaries and quote provenance.","name":"Undominated · Pricing source reviewer","href":"/agents/undominated-pricing-source-reviewer/","compatibility":["Portable Markdown role instructions"],"limitation":"Portable profile; manually load or adapt to a native agent format. No automatic subagent registration or permission grants.","reviewedAt":"2026-10-07","revision":"a67bd9b86fca7455ed208403d9ea6f9fe847cd99","definitionSha256":"4ef1bd51d0cb94e006028fa3f8872641565e8f8e1df490976ed756bde220356b","sourceUrl":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/agents/undominated-pricing-source-reviewer/AGENT.md","permissions":["read:assigned-sources","write:assigned-workspace"],"cost":"MIT source at no charge. Your agent host or model provider may charge for use.","license":{"name":"MIT","url":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/agents/undominated-pricing-source-reviewer/LICENSE"}},{"kind":"mcp-servers","id":"undominated-mcp","purpose":"Optionally retrieve published evidence and its source links without running inference.","name":"Undominated · Model and resource evidence MCP","href":"/mcp-servers/undominated-mcp/","compatibility":["MCP stdio clients","Node.js 22.12+"],"limitation":"Requires network access to published Undominated JSON endpoints. It does not execute resource install commands or verify third-party runtime behaviour.","reviewedAt":"2026-10-07","revision":"a67bd9b86fca7455ed208403d9ea6f9fe847cd99","definitionSha256":"2dfef658c3521e8628a45c7b4813e58f412ea54a4e2ca8ed3b9cef15dfab2afb","sourceUrl":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/packages/undominated-mcp/README.md","permissions":["Network GET requests to Undominated.ai public data","No credentials, local project access or configuration changes"],"cost":"MIT source at no charge. Your agent host or model provider may charge for use.","license":{"name":"MIT","url":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/packages/undominated-mcp/LICENSE"}}]},{"id":"plan-a-model-migration","title":"Plan a model migration without dropping requirements","category":"decide","summary":"Derive requirements from application behaviour, then separate compatibility, measured task outcomes and rollout authority.","outcome":"A candidate decision with capability gaps, evaluation coverage and observable rollback triggers.","inputs":["Current model/endpoint identity and representative application requests.","Candidate specifications and a held-out case set with required modalities, context and output behaviour."],"parallel":[{"title":"Requirement extraction","detail":"Map actual calls and fixtures to hard requirements; do not assume every incumbent capability is required."},{"title":"Candidate evidence","detail":"Collect dated endpoint specifications and mark unsupported or unknown fields explicitly."}],"steps":["Define required input/output modalities, context/output budgets, tool use and structured output. Preserve unknown candidate capabilities as unknown.","Run the local preflight over exact required evaluation IDs and supplied outcomes. If paid evaluation is authorised, run the same held-out cases on current and candidate endpoints and record failures, latency and billed usage.","Review task evidence and operational terms together. Propose a bounded canary, rollback conditions and decision owner; keep a passed preflight separate from production rollout."],"boundaries":["Benchmark position does not prove tool-call, vision or application compatibility. Missing, duplicate or failed required evaluations block a preflight pass.","API calls, private input transfer and a canary can incur cost or affect people. The local checker runs none of those actions and does not verify vendor specifications."],"deliverables":["Requirement/capability matrix","Held-out evaluation ledger","Cost and operational comparison","Canary and rollback proposal"],"checks":["Requirements come from actual application contracts or fixtures.","Unknown capability remains distinct from supported and unsupported.","Every required evaluation ID has one observed result.","Rollout and rollback triggers use observable application signals."],"template":{"title":"Model migration decision","sections":[{"heading":"Workload contract","body":"Current endpoint: ___\nRequired modalities/context/output/tools: ___\nRequirement evidence: ___\nData residency/privacy conditions: ___"},{"heading":"Candidate","body":"Exact endpoint and source/date: ___\nSupported requirements: ___\nUnknown or missing requirements: ___\nPreflight input/output: ___"},{"heading":"Evaluations","body":"| Required case ID | Current result | Candidate result | Actual billed usage/evidence |\n| --- | --- | --- | --- |\n| ___ | not run | not run | unknown |"},{"heading":"Rollout decision","body":"Unresolved blockers: ___\nCanary scope and observation window: ___\nRollback trigger/owner: ___\nAuthorised API budget: ___\nDecision: pending"}]},"resources":[{"kind":"skills","id":"undominated-migration-preflight","purpose":"Check supplied candidate capabilities and required evaluation coverage.","name":"Undominated · Model migration preflight","href":"/skills/undominated-migration-preflight/","compatibility":["Agent Skills compatible hosts","Python 3.10+"],"limitation":"Deterministic local checks over supplied evidence; not a guarantee of source truth or production suitability.","reviewedAt":"2026-10-07","revision":"a67bd9b86fca7455ed208403d9ea6f9fe847cd99","definitionSha256":"177ddd4c2bf46a15f85fb25a74890fac1f3325a26d65fc0c5d897d2c2c11922d","sourceUrl":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-migration-preflight/SKILL.md","permissions":["read:user-selected-local-file"],"cost":"MIT source at no charge. Your agent host or model provider may charge for use; the included offline checks require no paid API.","license":{"name":"MIT","url":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-migration-preflight/LICENSE"}},{"kind":"agents","id":"undominated-migration-planner","purpose":"Turn evidence and gaps into a workload-specific canary and rollback plan.","name":"Undominated · Model migration planner","href":"/agents/undominated-migration-planner/","compatibility":["Portable Markdown role instructions"],"limitation":"Portable profile; manually load or adapt to a native agent format. No automatic subagent registration or permission grants.","reviewedAt":"2026-10-07","revision":"a67bd9b86fca7455ed208403d9ea6f9fe847cd99","definitionSha256":"6dac6f7fe68a825f2d074be8cbc32863dc69b5b459efceb25bbc4a27d2907bac","sourceUrl":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/agents/undominated-migration-planner/AGENT.md","permissions":["read:assigned-sources","write:assigned-workspace"],"cost":"MIT source at no charge. Your agent host or model provider may charge for use.","license":{"name":"MIT","url":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/agents/undominated-migration-planner/LICENSE"}}]},{"id":"check-a-plan-and-switching-payback","title":"Check plan costs and switching payback","category":"decide","summary":"Keep unverified subscription quotes outside a USD monthly total, then calculate payback from savings rather than the whole bill.","outcome":"A verified-plan subtotal and a separately scoped switching-cost calculation with unresolved inputs retained.","inputs":["Plan source snapshots with explicit currency, billing period and verified amounts or unverified quotes.","Documented switching cost and independently established savings per common period."],"parallel":[{"title":"Plan evidence","detail":"Separate explicit verified USD amounts from prose, other currencies and annual-billing ambiguities."},{"title":"Payback basis","detail":"Check the switching-cost scope, saving denominator and period alignment independently."}],"steps":["Verify monthly USD amounts from primary terms. Keep unverified plans as quoted text with null amounts; document which plan IDs enter the total.","Run the plan checker on that explicit subset. Establish savings per period independently; a subscription subtotal is not itself a saving.","Run the payback checker with aligned decimal-string inputs. Preserve an exact rational result when it repeats, and report zero savings as undefined payback rather than inventing a finite period."],"boundaries":["The plan checker does not convert currencies, verify current vendor availability or derive monthly amounts from billing prose. A subtotal is not a complete spending cap unless all relevant charges are covered.","Payback checks supplied arithmetic, not taxes, discounting, payment timing or source truth. The payback skill is available through its pinned Skills CLI command or complete source download; it is not included in undominated-check@0.4.0."],"deliverables":["Verified and unverified plan ledger","Included-plan subtotal receipt","Savings-basis note","Exact payback result and limitations"],"checks":["Unverified or non-USD quotes contribute no invented amount.","Included plan IDs and the total agree exactly.","Savings and switching cost share a documented currency and time basis.","Zero savings and repeating ratios retain their correct undefined or exact-rational treatment."],"template":{"title":"Plan and payback worksheet","sections":[{"heading":"Plan evidence","body":"| Plan ID | Source/date | Verified monthly USD amount or unknown | Recorded quote | Included? |\n| --- | --- | --- | --- | --- |\n| ___ | ___ | unknown | ___ | undecided |"},{"heading":"Subtotal","body":"Included IDs: ___\nTaxes/usage/add-ons outside scope: ___\nChecker input/output/exit: not run\nUnverified plans excluded: ___"},{"heading":"Savings basis","body":"Currency and common period: ___\nSwitching-cost evidence: ___\nCurrent/proposed cost evidence: ___\nSavings per period and derivation: unknown"},{"heading":"Payback","body":"Claimed periods, if any: ___\nExact numerator/denominator: not computed\nTerminating decimal, if available: ___\nChecker output/exit: not run\nTiming, risk and discounting exclusions: ___"}]},"resources":[{"kind":"skills","id":"undominated-plan-quote","purpose":"Check that the stated USD total contains only the explicitly verified included plan amounts.","name":"Undominated · Plan-quote hygiene","href":"/skills/undominated-plan-quote/","compatibility":["Agent Skills compatible hosts","Python 3.10+"],"limitation":"Deterministic local checks over a supplied plan table; not a guarantee that a vendor page still matches.","reviewedAt":"2026-10-07","revision":"a67bd9b86fca7455ed208403d9ea6f9fe847cd99","definitionSha256":"e85dd4d17ef2b943ec601a97f5cd5af596e85c330af376fdd7d0ab7b7257d638","sourceUrl":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-plan-quote/SKILL.md","permissions":["read:user-selected-local-file"],"cost":"MIT source at no charge. Your agent host or model provider may charge for use; the included offline checks require no paid API.","license":{"name":"MIT","url":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-plan-quote/LICENSE"}},{"kind":"skills","id":"undominated-payback-basis","purpose":"Check switching cost divided by savings per period with exact arithmetic.","name":"Undominated · Payback basis","href":"/skills/undominated-payback-basis/","compatibility":["Agent Skills compatible hosts","Python 3.10+"],"limitation":"Exact savings-based arithmetic only; repeating results remain rational pairs. Currency and period alignment, taxes, timing, discounting and source truth are not verified.","reviewedAt":"2026-10-07","revision":"a67bd9b86fca7455ed208403d9ea6f9fe847cd99","definitionSha256":"d87c3e9558121a94470217b1f4cedc87299f44130f9be3d2d84fb9c8eeb0d9ac","sourceUrl":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-payback-basis/SKILL.md","permissions":["read:user-selected-local-file"],"cost":"MIT source at no charge. Your agent host or model provider may charge for use; the included offline checks require no paid API.","license":{"name":"MIT","url":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-payback-basis/LICENSE"}}]},{"id":"edit-docs-without-losing-meaning","title":"Edit documentation without losing meaning","category":"publish","summary":"Improve readability and Markdown navigation while preserving qualifiers, defaults, warnings and technical meaning.","outcome":"A focused documentation diff with semantic checks, accessible structure and a list of changes needing editorial judgement.","inputs":["The assigned Markdown files and their technical sources.","The intended reader, house style and any images whose descriptions are in scope."],"parallel":[{"title":"Readability review","detail":"Propose shorter wording while preserving optionality, recommendation strength and warnings."},{"title":"Structure review","detail":"Inspect headings, links, lists and image-description needs without rewriting factual claims."}],"steps":["Limit editing to the assigned files and record meaning-sensitive passages. Review declared shell/GitHub tools before loading the profiles.","Reconcile wording and structure suggestions into a local diff. Do not invent examples, remove technical defaults or turn can into will; inspect images before accepting alt text.","Check links and rendered heading order, run an approved linter if needed and have a technical reviewer inspect semantic changes. Publish a pull request only when requested."],"boundaries":["The readability profile asks for pull-request submission and declares broad tools; downloading it does not authorise publication.","The Markdown accessibility profile covers selected practices, not full accessibility conformance. Its npx linter may download code; alt text and meaning changes need deliberate review."],"deliverables":["Assigned-file scope","Readability and structure diff","Meaning-preservation checklist","Rendered-link and heading receipt"],"checks":["Optionality, recommendations, defaults and warnings retain their original meaning.","Every new example is supplied and verified rather than invented.","Links and heading structure work in the rendered document.","Image descriptions are checked against the actual image."],"template":{"title":"Documentation edit review","sections":[{"heading":"Scope","body":"Assigned files/revision: ___\nAudience/style: ___\nTechnical reference: ___\nProtected qualifiers/defaults/warnings: ___"},{"heading":"Semantic diff","body":"| Original meaning | Proposed wording | Source check | Reviewer decision |\n| --- | --- | --- | --- |\n| ___ | ___ | ___ | pending |"},{"heading":"Accessibility and rendering","body":"Heading outline: ___\nDescriptive-link checks: ___\nImage inspected and proposed alt: ___\nLinter/version/output, if run: ___"},{"heading":"Publication handoff","body":"Unresolved meaning changes: ___\nRendered preview evidence: ___\nNew examples and their evidence: ___\nRequested publication destination/action: ___"}]},"resources":[{"kind":"agents","id":"github-docs-readability-editor","purpose":"Improve assigned prose while preserving technical qualifiers and avoiding invented examples.","name":"GitHub Docs readability editor","href":"/agents/github-docs-readability-editor/","compatibility":["A GitHub Copilot agent markdown file whose frontmatter names its tools"],"limitation":"The body restricts editing to assigned Markdown files, but this is an instruction rather than an enforced filesystem boundary. Frontmatter includes edit, search, web, github/* and execute.","reviewedAt":"2026-10-07","revision":"b3ca4b7986534061037979e480c9d363fc95a909","definitionSha256":"edd502b2b86566595bf8e48f6bdfa50968ce52ad4cb5fcddcd8355876aca6dcc","sourceUrl":"https://raw.githubusercontent.com/github/docs/b3ca4b7986534061037979e480c9d363fc95a909/.github/agents/readability-editor.md","permissions":["Read and edit the assigned Markdown files, as instructed by the body.","Declared tools also include search, web, github/* and execute; host permissions determine actual access.","The body requests pull-request submission after edits; this is an external publication action."],"cost":"MIT-licensed definition under the repository code grant. Host subscriptions, model usage and connected services have their own costs.","license":{"name":"MIT","url":"https://github.com/github/docs/blob/b3ca4b7986534061037979e480c9d363fc95a909/LICENSE-CODE"}},{"kind":"agents","id":"github-markdown-accessibility-assistant","purpose":"Review Markdown navigation and suggest image descriptions with human visual review.","name":"Markdown Accessibility Assistant","href":"/agents/github-markdown-accessibility-assistant/","compatibility":["GitHub Copilot custom agents in VS Code"],"limitation":"The scope is selected Markdown accessibility practices, not full web accessibility conformance.","reviewedAt":"2026-09-21","revision":"ad4c196b933c5ca7f82a5ba78969ddcd2603ba80","definitionSha256":"be7f29e3f00670901011fef24707f9188fbcbc540fb07c9612a8e487daa99a3e","sourceUrl":"https://raw.githubusercontent.com/github/awesome-copilot/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/agents/markdown-accessibility-assistant.agent.md","permissions":["Instructed: read, edit, search, execute; run npx markdownlint; directly edit links/headings/lists; only suggest alt text and plain language pending a human. No mechanism in-file enforces that wait."],"cost":"Definition can be reused under its stated licence. Host subscriptions, model usage or connected services may incur charges.","license":{"name":"MIT","url":"https://github.com/github/awesome-copilot/blob/ad4c196b933c5ca7f82a5ba78969ddcd2603ba80/LICENSE"}}]},{"id":"curate-a-resource-with-licence-evidence","title":"Curate a resource with licence evidence","category":"publish","summary":"Review one skill, agent or MCP server for source identity, useful scope, permissions and actual redistribution terms.","outcome":"A defensible catalogue decision with a pinned source, licence note and separately labelled runtime evidence.","inputs":["The upstream repository or service, exact resource path and a concrete use case.","The applicable licence, installation documentation and an isolated review workspace."],"parallel":[{"title":"Source and capability review","detail":"Read the full definition and relevant helpers; map stated capabilities to what the resource actually supplies."},{"title":"Rights and access review","detail":"Check the applicable code/content/service terms and requested permissions independently."}],"steps":["Pin the repository revision and save the exact source/licence evidence. Check for duplicate identities before adding another listing.","Inspect installation side effects, tool grants, credentials and paid prerequisites. Use isolated smoke checks only when authorised and separate source inspection from installation and real-task results.","Fill the resource-audit and licence-boundary inputs from inspected evidence. Publish or redistribute only within an established grant; keep unknown rights, failed checks and declined candidates visible."],"boundaries":["A public page or successful download is not a redistribution grant. Internal-use permission needs its own evidence and does not follow from a redistribution denial.","The local checkers validate supplied notes; they do not interpret a licence or certify security. Retrieved instructions are review material, not authority to execute them."],"deliverables":["Pinned source and hash manifest","Licence/attribution note","Permissions and prerequisite map","Selected/deferred/declined decision"],"checks":["The exact source path and revision are recorded and distinct from existing entries.","The licence applies to the files or content actually being redistributed.","Runtime, installation and source-review evidence are labelled separately.","Unresolved rights or missing material permissions are not converted into favourable claims."],"template":{"title":"Resource curation dossier","sections":[{"heading":"Identity and fit","body":"Kind/name/publisher: ___\nRepository/path/revision: ___\nSource hash: ___\nConcrete use case: ___\nPossible duplicate identity: ___"},{"heading":"Rights","body":"Applicable licence URL/date: ___\nExplicit redistribution grant/denial/not stated: ___\nShort supporting quote: ___\nInternal-use evidence, if claimed: ___\nAttribution to ship: ___"},{"heading":"Access and verification","body":"Requested tools/credentials: ___\nWrites/network/paid prerequisites: ___\nFiles/helpers inspected: ___\nInstallation result: not run\nReal-task result: not run"},{"heading":"Disposition","body":"Selected/deferred/declined: ___\nReason and unresolved evidence: ___\nSupported claims only: ___\nReviewer/date: ___"}]},"resources":[{"kind":"skills","id":"undominated-resource-audit","purpose":"Check that the review records source identity, rights, permissions and bounded evidence.","name":"Undominated · AI resource intake audit","href":"/skills/undominated-resource-audit/","compatibility":["Agent Skills compatible hosts","Python 3.10+"],"limitation":"Deterministic local checks over supplied evidence; not a guarantee of source truth or production suitability.","reviewedAt":"2026-10-07","revision":"a67bd9b86fca7455ed208403d9ea6f9fe847cd99","definitionSha256":"b65e37122452f4b1b9bde4ddfcd7248b0da48866c8c10fd9d220a87053bc471f","sourceUrl":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-resource-audit/SKILL.md","permissions":["read:user-selected-local-file"],"cost":"MIT source at no charge. Your agent host or model provider may charge for use; the included offline checks require no paid API.","license":{"name":"MIT","url":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-resource-audit/LICENSE"}},{"kind":"skills","id":"undominated-licence-boundary","purpose":"Check consistency of the recorded rights claim and its explicit evidence.","name":"Undominated · Licence-boundary audit","href":"/skills/undominated-licence-boundary/","compatibility":["Agent Skills compatible hosts","Python 3.10+"],"limitation":"Deterministic consistency check of a filled licence note; it does not interpret licence text or fetch the licence.","reviewedAt":"2026-10-07","revision":"a67bd9b86fca7455ed208403d9ea6f9fe847cd99","definitionSha256":"6e37ec5b50336a05aed00a1c3c844dcd9fa672d55939b7c01a9766a7d0a50b35","sourceUrl":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-licence-boundary/SKILL.md","permissions":["read:user-selected-local-file"],"cost":"MIT source at no charge. Your agent host or model provider may charge for use; the included offline checks require no paid API.","license":{"name":"MIT","url":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-licence-boundary/LICENSE"}},{"kind":"agents","id":"undominated-resource-curator","purpose":"Challenge resource fit, duplicate identity and untested scope before listing.","name":"Undominated · AI resource curator","href":"/agents/undominated-resource-curator/","compatibility":["Portable Markdown role instructions"],"limitation":"Portable profile; manually load or adapt to a native agent format. No automatic subagent registration or permission grants.","reviewedAt":"2026-10-07","revision":"a67bd9b86fca7455ed208403d9ea6f9fe847cd99","definitionSha256":"be30e2cb65efeb9e87cfbd992e916c19f354fde3269b5443f30dd60991c74919","sourceUrl":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/agents/undominated-resource-curator/AGENT.md","permissions":["read:assigned-sources","write:assigned-workspace"],"cost":"MIT source at no charge. Your agent host or model provider may charge for use.","license":{"name":"MIT","url":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/agents/undominated-resource-curator/LICENSE"}}]},{"id":"publish-a-traceable-ai-comparison","title":"Publish a traceable model comparison","category":"publish","summary":"Bind a numeric comparison to its source population, serving mode and capability requirements before writing the headline.","outcome":"A publication-ready claim packet whose wording matches the checked evidence and clearly states its limits.","inputs":["A draft claim, saved permitted source evidence and reproducible calculations.","Exact model/serving-mode identities and the requirements relevant to the comparison."],"parallel":[{"title":"Numeric audit","detail":"Reconstruct the numerator, denominator and calculation independently of the draft headline."},{"title":"Attribution and wording","detail":"Check whether each score belongs to the model or a named serving mode, then inspect ties and capability losses."}],"steps":["Freeze source files and record dates, identities and the allowed publication scope. Keep missing scores or rates as unknown.","Run the relevant local checks on explicit inputs: evidence structure/calculation, claimed score attribution and the supplied two-model comparison. Investigate disagreement instead of editing inputs to obtain a pass.","Write only the supported directional claim. Equal-price or equal-score improvements are not both better and cheaper; a dropped requirement is a trade-off. Attach evidence and retain any correction history before publication."],"boundaries":["These checkers validate supplied data and bounded consistency rules; they do not establish source truth, benchmark equivalence or permission to redistribute.","Serving-attribution is available through its pinned Skills CLI command or complete source download; it is not included in undominated-check@0.4.0. Do not imply every source skill is in that immutable package, and do not turn fixture success into a production endorsement."],"deliverables":["Claim-to-source ledger","Reproducible calculation receipt","Score attribution and requirement sheet","Qualified headline and correction note"],"checks":["Every numeric claim has a source/date and reproducible calculation.","The claimed population matches the actual denominator.","Serving-mode scores remain attributed to that mode.","The headline distinguishes strict improvements, tied axes and lost requirements."],"template":{"title":"Model-comparison publication packet","sections":[{"heading":"Claim and sources","body":"Draft sentence: ___\nSource URLs/dates/hashes: ___\nPublication rights/attribution: ___\nTarget population and exclusions: ___"},{"heading":"Numeric proof","body":"Numerator/denominator definitions: ___\nCalculation command/input: ___\nObserved output/exit: not run\nMissing values and treatment: ___"},{"heading":"Identity and requirements","body":"Model and serving-mode IDs: ___\nClaim subject and explicit claimed score: ___\nRequired capabilities: ___\nTie or requirement loss: ___"},{"heading":"Editorial disposition","body":"Checked wording: ___\nSupported scope and remaining uncertainty: ___\nChecker receipts: ___\nCorrection history, if any: ___\nPublication decision owner: ___"}]},"resources":[{"kind":"skills","id":"undominated-evidence-audit","purpose":"Check evidence references, denominator accounting and the supplied calculation.","name":"Undominated · Evidence audit","href":"/skills/undominated-evidence-audit/","compatibility":["Agent Skills compatible hosts","Python 3.10+"],"limitation":"Deterministic local checks over supplied evidence; not a guarantee of source truth or production suitability.","reviewedAt":"2026-10-07","revision":"a67bd9b86fca7455ed208403d9ea6f9fe847cd99","definitionSha256":"8251338610e2edf42ba1ac1e370ef028dddff6a3ba608f209d30a31fe253ff57","sourceUrl":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-evidence-audit/SKILL.md","permissions":["read:user-selected-local-file"],"cost":"MIT source at no charge. Your agent host or model provider may charge for use; the included offline checks require no paid API.","license":{"name":"MIT","url":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-evidence-audit/LICENSE"}},{"kind":"skills","id":"undominated-serving-attribution","purpose":"Compare an explicit claimed score with its named model or serving-mode subject.","name":"Undominated · Serving-mode attribution","href":"/skills/undominated-serving-attribution/","compatibility":["Agent Skills compatible hosts","Python 3.10+"],"limitation":"Checks explicit claimedScore and named-subject equality only. It does not verify benchmark provenance, source truth or shared measurement conditions.","reviewedAt":"2026-10-07","revision":"a67bd9b86fca7455ed208403d9ea6f9fe847cd99","definitionSha256":"a9a3aa54fb5c35300f666220b490b3fb128c4ab510ecfff3066adae78e87eb2d","sourceUrl":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-serving-attribution/SKILL.md","permissions":["read:user-selected-local-file"],"cost":"MIT source at no charge. Your agent host or model provider may charge for use; the included offline checks require no paid API.","license":{"name":"MIT","url":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-serving-attribution/LICENSE"}},{"kind":"skills","id":"undominated-dominance-wording","purpose":"Classify the supplied pair while preserving ties and recorded requirements.","name":"Undominated · Dominance wording audit","href":"/skills/undominated-dominance-wording/","compatibility":["Agent Skills compatible hosts","Python 3.10+"],"limitation":"Deterministic local checks over one supplied pair and the listed requirements; not a guarantee of source truth.","reviewedAt":"2026-10-07","revision":"a67bd9b86fca7455ed208403d9ea6f9fe847cd99","definitionSha256":"b820f582cae01029d9f72b0f4c6acdb2846be053774806e05bef03da29c4f0ed","sourceUrl":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-dominance-wording/SKILL.md","permissions":["read:user-selected-local-file"],"cost":"MIT source at no charge. Your agent host or model provider may charge for use; the included offline checks require no paid API.","license":{"name":"MIT","url":"https://github.com/Lenvanderhof/Undominated.ai/blob/a67bd9b86fca7455ed208403d9ea6f9fe847cd99/skills/undominated-dominance-wording/LICENSE"}}]}]}