Agent skill · writing content · aiskillstore
documentation-audit
This skill should be used when verifying documentation claims against codebase reality. Triggers on "audit docs", "verify documentation", "check docs", "docs accurate", "documentation drift", "before release", "after refactor", "docs don't match". Uses two-pass extraction with pattern expansion for comprehensive detection.
Why this skill is useful
Provides a structured approach and specific patterns for verifying documentation claims against the codebase that the AI wouldn't generate on its own.
What it needs
About 2k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
<!-- ABOUTME: Documentation audit skill for verifying claims against codebase --> <!-- ABOUTME: Uses two-pass extraction with pattern expansion for comprehensive detection --> Documentation Audit Systematically verify claims in documentation against the actual codebase using a two-pass approach. Overview Core principle: Low recall is worse than false positives—missed claims stay invisible. Two-pass process: 1. Pass 1: Extract and verify claims directly from docs 2. Pass 2A: Expand patterns from false claims to find similar issues 3. Pass 2B: Compare codebase inventory vs documented items (gap detection) Quick Start 1. Identify target docs (user-facing only, skip plans/, audits/) 2. Note current git commit for report header 3. Run Pass 1 extraction using parallel agents (one per doc) 4. Analyze false claims for patterns 5. Run Pass 2 expansion searches 6. Generate docs/audits/AUDITREPORTYYYY-MM-DD.md Claim Types Type Example Verification ------ --------- -------------- fileref scripts/foo.py File exists? configdefault "defaults to 'AI Radio'" Check schema/code envvar STATIONNAME In .env.example + code? clicommand --normalize flag Script supports it? behavior "runs every 2 minutes" Check timers/code Verification confidence: Tier 1 (auto): fileref, configdefault, envvar, clicommand Tier 2 (semi-auto): symbolref, versionreq Tier 3 (human review): behavior, constraint Pass 2 Pattern Expansion After Pass 1, analyze false claims and search for similar patterns: Common patterns to always check: Dead scripts: scripts/.py references Timer intervals: every \d+ (seconds? minutes?) Service names: ai-radio-.service, .timer Config vars: RADIO environment variables CLI flags: --flag patterns in bash blocks Output Format Generate docs/audits/AUDITREPORTYYYY-MM-DD.md: Detailed References For execution checklist and anti-patterns: checklist.md For claim extraction patterns: extraction-patterns.md
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/documentation-audit