← ClaudeAtlas

doc-accuracylisted

Multi-phase documentation verification treating code as source of truth. Single canonical entrypoint for documentation auditing; replaced the former doc-coverage and doc-sync skills (deleted 2026-05-09) and absorbs incoherence detection and comment analysis into one workflow. Use when auditing documentation accuracy, verifying code examples compile, checking behavioral claims, or running pre-release doc audits.
rjmurillo/ai-agents · ★ 33 · AI & Automation · score 79
Install: claude install-skill rjmurillo/ai-agents
# Documentation Accuracy Skill Verify documentation claims against actual code behavior. Code is truth; docs are the subject under test. ## Triggers | Trigger Phrase | Operation | |----------------|-----------| | `check documentation accuracy` | Full audit (Phases 1-6) | | `verify code examples` | Compilability check (Phases 1-3) | | `audit docs vs code` | Behavioral verification (Phases 1-4) | | `check doc consistency` | Cross-document consistency (Phases 1-2, 5) | | `run doc-accuracy` | Full audit (Phases 1-6) | --- ## When to Use Use this skill when: - Documentation may contain non-compilable code examples - Behavioral claims in docs may contradict implementation - Quantitative claims (performance, limits) appear in multiple files with different values - Preparing for a release and need a documentation accuracy audit - API reference may be missing public members Use direct code review instead when: - Investigating a single known documentation error - The inaccuracy is already identified and needs a fix --- ## Replaces | Skill | Reason | |-------|--------| | `incoherence` | 15.8% recall on critical issues; Haiku agents too shallow | | `doc-coverage` | 0% recall on actionable issues; checks presence, not correctness | | `doc-sync` | No scripts, purely manual LLM workflow | | `comment-analyzer` | Advisory only, single-file scope | --- ## Architecture ### Asymmetric Verification Code compiles and runs. Documentation describes what code does. When they disagree,