active/docs-audit-v2/SKILL.md
Audit documentation rewrites with JSON-first, block-scoped, line-level coverage mappings. Use for moved-section checklists, preservation proofs, migration maps, or line-by-line coverage reviews of Markdown/MDX docs.
npx skillsauth add kevinslin/skills docs-audit-v2Install this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill to prove that a documentation rewrite preserved, moved, paraphrased, generated, or intentionally removed source content. It is for docs coverage audits, not repository code-quality audits.
For general codebase quality audits, use the regular audit skill instead.
mappings.length
is non-zero. Do not render a final viewer/report for a preservation review
until mappings have been authored and merged with map.mapping[] row per material source line.Load only the reference needed for the current step:
./references/workflow.md: command sequence, artifacts, validation loop, and
handoff checklist../references/schema.md: JSON schema, stable IDs, enums, destination entry
shapes, validation findings, and invariants../references/refactor-integration.md: contract for docs refactor skills
that author mappings while rewriting docs../references/viewer.md: Markdown report and HTML viewer rendering contract.The first-version CLI commands are:
scaffoldadd-destreindex-destmaphydratevalidaterenderThe canonical artifact is JSON. Markdown reports and HTML viewers are render outputs and must not be parsed back into JSON as source of truth.
scaffold, add-dest, and reindex-dest never create semantic mappings;
they only inventory source and destination docs.map.mapping[]
row.justification as the canonical explanation field. Do not invent
notes or detailed_reason aliases.covered line.Reference bundled files relative to this SKILL.md directory:
./references/..../assets/audit-viewer.html./scripts/...Do not use machine-local absolute paths in skill instructions or generated audit docs.
development
Resolve explicit shortcut triggers and usage. Always read this file at the start of a thread or when user mentions `trigger`.
testing
Improve skills from observed agent friction in sessions, PRs, or audits.
development
Generate incremental Slack digests for channels, topics, and categories.
testing
Audit an OpenClaw maturity-scorecard surface into an evidence-backed component score report. Use when given a surface from an OpenClaw maturity-scorecard.md and asked to score coverage, quality, readiness, or generate a detailed surface report plus per-component subreports.