doc-audit
Cross-check a PRD/design doc against the real codebase and emit a review report. Enumerates every factual claim the doc makes about the code, verifies each one against actual files with file:line citations, and writes a verdict table to docs/reviews/. Read-only with respect to source: it audits, it does not fix. Use when asked to "audit <doc>", "check <PRD> against the code", "verify the claims in <plan>", or "doc-audit <path>".
- License 许可
- MIT
- 最近更新
- 2026-11-01
- Stars
- ★ 2
- Forks
- 1
01 前言 Front Matter
- name
- doc-audit
- triggers
- [ "doc audit", "audit the PRD", "check the doc against the code", "verify the claims in" ]
- description
- Cross-check a PRD/design doc against the real codebase and emit a review report. Enumerates every factual claim the doc makes about the code, verifies each one against actual files with file:line citations, and writes a verdict table to docs/reviews/. Read-only with respect to source: it audits, it does not fix. Use when asked to "audit <doc>", "check <PRD> against the code", "verify the claims in <plan>", or "doc-audit <path>".
- allowed-tools
- [ "Read", "Grep", "Glob", "Bash", "Write", "Agent" ]
03 SKILL.md 正文
Doc Audit
Given $ARGUMENTS (a doc path):
- Read the doc fully. Enumerate every factual claim about the codebase.
- Verify each claim with Read/Grep against actual files. Cite
file:linefor each. - Do NOT edit source code. Do NOT commit or push.
- Write the report to
docs/reviews/using the next free zero-padded index (lsthe dir first to avoid collisions). - Report a table: claim | verdict (confirmed/wrong/unverifiable) | evidence path.
04 同仓库更多 Skills
react-doctor
Use when finishing a feature, fixing a bug, before committing React code, or when the user types `/doctor`, asks to scan, triage, or clean up React diagnostics. Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full local-triage workflow that fetches the canonical playbook.
review-remediate
Use for the review-then-fix-everything loop on a package or diff — deliver a grounded review report immediately (no scoping questions, no plan-approval), then remediate every finding as tracked numbered items, gating each batch on typecheck/lint/test/build plus an independent Codex pass until clean. Trigger on "review and fix <package>", "remediate the review", "review-fix-verify", or when the user wants a deep review followed by autonomous remediation. Distinct from gstack `review` (pre-landing PR review) and `code-review` (diff only) — this reviews from scratch AND fixes to green.
review-fixes
Close out an EXISTING code-review findings report — one subagent per finding, each with a regression test — then regenerate EN/zh/ja/ko docs, run all gates, and verify no stale or unexported symbols remain. Trigger on "/review-fixes", "fix all N review findings", "close the review findings", or when the user hands over a findings report to remediate. Distinct from review-remediate, which produces the review itself first — this skill starts from a report that already exists.
release-prep
Pre-release verification + go/no-go checklist for publishing @anvilkit packages. Detects the release surface (main workspace fixed-group vs components submodule), runs changeset status and the check:all release gates, enforces this repo's publish gotchas (version.ts drift, ui peer ranges, never-publish canvas-templates, bundle/api-snapshot), then hands the exact publish command to the user. Use when asked to "prep a release", "check release readiness", "/release-prep", or before cutting a version. Does NOT commit or publish.
react-doctor
Use when finishing a feature, fixing a bug, before committing React code, or when the user types `/doctor`, asks to scan, triage, or clean up React diagnostics. Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full local-triage workflow that fetches the canonical playbook.
pre-refactor
暂无简介