Loading...
Loading...
Found 17 Skills
Audit project documentation quality across 8 categories (Hierarchy, SSOT, Compactness, Requirements, Actuality, Legacy, Stack Adaptation, Semantic Content). Delegates to ln-601 for deep semantic verification of project documents. Use when documentation needs quality review, after major doc updates, or as part of ln-100-documents-pipeline. Outputs Compliance Score X/10 per category + Findings + Recommended Actions.
Audit tasks in docs/todo/done/ to verify claimed implementations actually exist in the codebase. Use when reviewing completed tasks, validating work before release, or periodically auditing task accuracy. Moves unverified tasks back to pending/.
Run audits on documentation and project health. Routes to specialized audit sub-skills for tasks, definitions, rules, and codebase consistency. Use when reviewing project health, validating documentation, or checking for drift.
Coordinates 4 documentation audit workers (structure, semantic, fact-check, code comments). Delegates parallel audits, aggregates into docs/project/docs_audit.md.
Use when Hermes reviews Claude-authored writeups, public docs, skill changes, README/agent/issue-template changes, or upstream speed-match documentation before syncing or publishing.
Validate documentation files for completeness, accuracy, and consistency with the codebase. Use when user mentions "check documentation", "validate docs", "is the README up to date?", requests documentation review, says "docs are wrong" or "fix the docs", or is working on documentation improvements. Covers README files, API docs, CHANGELOG, and any markdown documentation.
Post-ship documentation update. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION.
Four slash commands for documentation lifecycle: /docs, /docs-init, /docs-update, /docs-claude. Create, maintain, and audit CLAUDE.md, README.md, and docs/ structure with smart templates. Use when: starting new projects, maintaining documentation, auditing docs for staleness, or ensuring CLAUDE.md matches project state.
Audit project documentation against the codebase and fix drift. Run before PRs or after major changes. Compares documented architecture, test counts, and file paths against actual state.
Docs as QA: audit doc coverage and freshness, validate runbooks, and maintain documentation quality gates for APIs, services, events, and operational workflows. Includes AI-assisted audits, observability patterns, and automated coverage tracking.
Use when writing, moving, reviewing, or auditing documentation in a repository — choosing hierarchy and detail, separating tutorials from references, checking tutorial progression, trimming doc slop, responding to a documentation-budget gate failure, or requests like "improve the docs", "audit the docs", "govern the docs", "standardize the documentation of a repository", "where should this be documented", or "this doc is too long".
Audit whether a repo's docs actually ANSWER the questions a reader has — by spawning fresh, cheap (Haiku) agents that cold-read ONLY the docs and measuring how fast they reach the answer, whether they hit dead-ends, whether they fall back to source code, and whether they cite docs that contradict each other. Use after a doc reorg, when docs "feel scattered," or when the same confusion keeps recurring. Surfaces findability gaps (a corpus can be COMPLETE — every doc indexed — yet not FINDABLE) plus a prioritized fix list. Works on any repo's docs, not just this one.