Triage, plan, and implement a fix or feature for a GitHub issue end-to-end

Create or reuse a git worktree for a pull request or branch so reviews and work happen in isolation

Enforces dlt import conventions and ordering. Use when writing or modifying Python imports in dlt/ or tests/.

Enforces dlt docstring conventions. Use when writing or modifying docstrings, classes, or function signatures in Python files.

Use when writing, modifying, or debugging tests for an LLMObs plugin in dd-trace-js. Triggers: "write LLMObs tests", "test an LLMObs plugin", "assertLlmObsSpanEvent", "useLlmObs", "getEvents", any MOCK_* matcher ("MOCK_STRING" / "MOCK_NOT_NULLISH" / "MOCK_NUMBER" / "MOCK_OBJECT"), "VCR cassette", "vcr proxy", "127.0.0.1:9126", "record a cassette", "test:llmobs:plugins".

Use when adding, debugging, fixing, or modifying instrumentation and plugins for third-party libraries in dd-trace-js. Triggers: "add a new integration", "instrument a library", any *Plugin base class (Tracing/Database/Cache/ Client/Server/Consumer/Producer/Composite), "addHook", "shimmer.wrap", "orchestrion", "bindStart"/"bindFinish", "diagnostic channel", "runStores", "subscriber cardinality", "channel.publish gate", "read upstream source", "reference plugin".

Turn Figma designs into CDS React (cds-web) or React Native (cds-mobile) code. Use when the user shares a Figma design URL (e.g. `figma.com/design/...?node-id=...`) or asks to "implement this design" or "build this from Figma" in a frontend project that is using Coinbase Design System (CDS). Do not use for general CDS UI work with no Figma reference (use `cds-code`), or for design critique without an implementation request.

Provides a workflow for building and reviewing high-quality React and React Native UI with the Coinbase Design System (CDS). Use this skill to create UI or make visual changes to existing UI with CDS components, tokens, style props, icons, and illustrations. Use it for explicit CDS-adherence audits and reviews, not non-visual logic, data, analytics, navigation, tests, generated code, or refactoring. Examples: "build this screen", "fix spacing on this component", "replace this UI with CDS components", "perform a CDS audit on our changes", "check our codebase for CDS adherence", "does this feature use CDS well?"

Deprecates a CDS component, hook, or other exported symbol with consistent JSDoc, version tags, and docsite metadata across every public export path (web, mobile, common, visualization), not only the original package. Use whenever the user asks to deprecate a CDS component or API, mark something as deprecated, add @deprecated / @deprecationExpectedRemoval, or update deprecation warnings in apps/docs metadata under components or hooks (webMetadata.json / mobileMetadata.json / metadata.json). Also use when replacing a component or hook and sunsetting the old one. Always finish by running `yarn nx run <project>:lint` on modified packages so `internal/deprecated-jsdoc-has-removal-version` passes.

Read-only GitHub triage for issues AND PRs. 1 item = 1 background task (category: quick). Analyzes all open items and writes evidence-backed reports to /tmp/{datetime}/. Every claim requires a GitHub permalink as proof. NEVER takes any action on GitHub - no comments, no merges, no closes, no labels. Reports only. Triggers: 'triage', 'triage issues', 'triage PRs', 'github triage'.

Creates and updates GitHub pull requests for cloudflare-docs changes. Load when asked to open, create, submit, update, or edit a PR, or write a PR title or description. Covers title conventions, branch naming, PR body structure, and the documentation checklist template.

Produce a gradeable rubric file from an issue, PRD, or free-form goal — sharpened to the standard required by Anthropic's Managed Agents user.define_outcome event. Sidecar artifact (issues/NNN-*.rubric.md or rubrics/SLUG.md); does not modify source files. Use when the user wants to define "what done looks like" for grader-checkable success criteria. Triggers: /write-a-rubric, "write a rubric", "outcome rubric", "define-outcome", "managed-agent outcome", "make this gradeable".

Interview the user and produce issues/prd.md from a client brief, feature idea, or rough request. Step 1 of the build pipeline (write-a-prd → prd-to-issues → work-issues). Use when no PRD exists yet and one is needed. NOT for breaking an existing PRD into tasks (use prd-to-issues), and NOT for tracker-coupled output (this writes local markdown only). Triggers: /write-a-prd, "write a PRD", "draft a spec", "turn this brief into a PRD".

Autonomously work one task from an issues/ queue end-to-end — explore, implement (TDD when applicable), run feedback loops, commit, update the issue file. Step 3 of the build pipeline (write-a-prd → prd-to-issues → work-issues). Heavyweight (commits code, modifies the issue queue). Use only when explicitly asked: /work-issues, "work the issue queue", "run an AFK iteration", "do one issue end-to-end", OR when another orchestrator skill (e.g. /feature) needs to dispatch an AFK iteration programmatically. Headless loop runner: bin/loop.sh.

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

Read an existing PRD (typically issues/prd.md, written by write-a-prd) and break it into vertical-slice tracer-bullet issues at issues/NNN-short-title.md, tagged HITL (needs human) or AFK (autonomous). Step 2 of the build pipeline (write-a-prd → prd-to-issues → work-issues). Use when a PRD exists and needs to become work tickets. NOT for writing the PRD itself (use write-a-prd). Triggers: /prd-to-issues, "break this PRD into issues", "turn this spec into tickets".

Generate or update ARCHITECTURE.md — a living map of a project's structure, dependencies, and high-coupling zones. Polyglot-adaptive. Heavyweight (writes ARCHITECTURE.md, dispatches parallel agents). Use only when explicitly asked: /map, "generate ARCHITECTURE.md", "map this codebase", OR when another orchestrator skill (e.g. /feature step_refresh_map) needs to dispatch it programmatically.

Rank functions by CRAP score (complexity × lack of real test coverage) on the current branch, then propose either a refactor or missing tests for the worst offender. Use when the user runs /crap or asks to find risky, complex, poorly-tested code.

Three parallel reviewer agents find contradictions, config gaps, and coverage holes across a project's docs, config, and tests — then fix what you approve. Heavyweight (dispatches parallel agents, can modify files). Supports env-var automation hooks (ADVERSARIAL_REVIEW_TARGETS, ADVERSARIAL_REVIEW_REPORT_ONLY) so an orchestrator can dispatch a programmatic validator pass without keyboard. Use only when explicitly asked: /adversarial-review, "adversarial review", "find gaps in my docs/config", OR when another skill (e.g. /feature) needs to dispatch a validator pass programmatically.

Use WordPress Studio for local WordPress development, preferring MCP and falling back to the Studio CLI when needed.