agentleFS
florian101010florian101010/awesome-agentic-AI-coding-template/.agents/skills/doc-audit/SKILL.md

doc-audit

Skill4 starsChanged 12 days agoMITView on GitHub

8-phase documentation drift audit across all docs, agent instructions, and config files. Use when checking for documentation drift, stale paths/counts, or inconsistencies between code and docs.

12 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Principle: Use existing scripts instead of ad-hoc grep commands.

    line 10
  2. Distinctive:

    Every real file/directory must appear in all file maps.

    line 62
  3. Distinctive:

    All automated checks from Phase 2 cover config consistency.

    line 116
  4. Distinctive:

    Verify all files/directories in the repo are listed in the agent file maps (see Phase 0).

    line 124
  5. Distinctive:

    All agent instruction files must agree on:

    line 128
  6. Distinctive:

    If any doc fixes were made:

    line 149

“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Documentation Audit

Comprehensive audit to ensure zero documentation drift across ALL docs, agent instructions, and config files.

Principle: Use existing scripts instead of ad-hoc grep commands. Never create temporary audit scripts — all checks are covered by the repo's tooling and test suite.


Complete Documentation Inventory

Layer 1: Primary Docs

<!-- SETUP: Replace with your project's actual doc structure. -->
FileDrift-sensitive fields
docs/README.mdFile tree, asset paths, tech stack
docs/ARCHITECTURE.mdFile paths, component structure
docs/CHANGELOG.mdMissing entries for recent changes
[FILL: docs/CONFIG-REFERENCE.md][FILL: Schema tables, field descriptions]
docs/decisions/ADR accuracy vs. current implementation

Layer 2: Agent Instructions

FileDrift-sensitive fields
AGENTS.mdFile structure (paths), coding rules
CLAUDE.mdFile map (paths), key patterns
.github/copilot-instructions.mdKey files table (paths), always/never rules
.agent/rules/coding-standards.mdRules, path conventions
[FILL: Additional agent instruction files][FILL: Drift-sensitive fields]

Layer 3: Root-Level Files

FileDrift-sensitive fields
README.mdFile paths, quickstart instructions
[FILL: Add project-specific root-level files][FILL: Drift-sensitive fields]

Phase 0 — File Tree Completeness (Structural Drift)

Why this is Phase 0: Missing files in file maps is the #1 drift source. Check this first.

Compare the actual file tree against every file-map section in agent instruction files and docs:

  1. List actual files: ls src/, ls config/, ls docs/
  2. Cross-check against file maps in:
FileSection name
AGENTS.md## File Structure
CLAUDE.md## File Map
[FILL: docs/README.md][FILL: Section name for file tree]
  1. Every real file/directory must appear in all file maps. Flag any missing entries.

Phase 1 — Identify What Changed

git diff --stat
git log --oneline -10

Classify the change type:

  • Config change → schema, examples, stats references may be stale
  • UI/layout change → styling guide, layout constraints may be stale
  • New feature → user flow, architecture, changelog, roadmap may be stale
  • File added/removed/renamed → file trees, path references may be stale
  • Agent rule change → must propagate to ALL agent instruction files

Phase 2 — Run Automated Drift Checks

Do not use ad-hoc grep commands or create temporary scripts for checks that existing tooling already covers.

# Run all automated tests
npm test

# [FILL: Add any project-specific drift/stats scripts here]

Verify policy alignment:

  • Agent docs do not hardcode mutable totals as static source-of-truth values
  • If a snapshot number is documented, it is clearly labeled with snapshot context/date

Phase 3 — Verify Path Conventions

# Find references to potentially stale paths
grep -rn "[FILL: old-path-prefix]" docs/ .agent/ .claude/ .github/ AGENTS.md CLAUDE.md --include="*.md"

Current correct conventions:

  • [FILL: Path convention 1 — e.g. "No leading / or ./ in asset paths"]
  • [FILL: Path convention 2 — e.g. "Assets at assets/{name}.ext"]

Phase 4 — Verify Config ↔ Code Consistency

Use existing tooling — do not write ad-hoc scripts for these checks.

All automated checks from Phase 2 cover config consistency. If they all pass, this phase is done.


Phase 5 — Cross-Check Agent Files

5a. File map sync (structural)

Verify all files/directories in the repo are listed in the agent file maps (see Phase 0).

5b. Fact consistency

All agent instruction files must agree on:

FactMust match across
Coding rulesAGENTS.md, CLAUDE.md, copilot-instructions.md, coding-standards.md
Security requirementsAGENTS.md, CLAUDE.md, copilot-instructions.md, coding-standards.md
[FILL: Project-specific fact][FILL: Which files must agree]

Phase 6 — Workflow & Skill Consistency

  • .agent/workflows/doc-audit.md — This workflow is itself still accurate? (meta-audit)
  • .claude/skills/doc-audit/SKILL.md — Same as above?
  • .github/pull_request_template.md — Contains explicit docs/ADR/policy alignment gates?
  • [FILL: Any project-specific workflows to check]

Phase 7 — Update CHANGELOG

If any doc fixes were made:

### Fixed
- Documentation drift: updated [specific counts/paths/conventions] across [N] files

Change → Doc Impact Matrix

<!-- SETUP: Fill in the impact matrix for your project. -->
If you changed…Update these docs
File added/removed/renamedAGENTS.md (file structure), CLAUDE.md (file map), docs/ARCHITECTURE.md
Architecture decisiondocs/decisions/ (add new ADR file)
New feature / bug fixdocs/CHANGELOG.md
Coding rule changedAGENTS.md, CLAUDE.md, copilot-instructions.md, coding-standards.md
[FILL: Project-specific change][FILL: Affected docs]

Drift Severity

LevelDescriptionAction
🔴 CriticalWrong paths, wrong schema, contradictory policy rulesFix immediately
🟠 HighMissing files in agent file maps, outdated conventionsFix before next AI-assisted change
🟡 MediumMissing changelog entry, outdated roadmapFix in next doc pass
🟢 LowStylistic inconsistencyFix when convenient

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.