agentleFS
LandonTomaineLandonTomaine/LT-Agents/skills/audit-docs/SKILL.md

audit-docs

Skill0 starsChanged 4 months agoMITView on GitHub

Lightweight documentation audit workflow for checking repo docs, indexes, and agent guidance for stale content, duplication, missing routes, unclear ownership, and mismatches with the current repository. Use when the user asks to review, tighten, de-duplicate, or improve documentation without doing a broad standards bootstrap.

17 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use diagnose and skill-creator.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    diagnose

    Use to systematically diagnose why scenarios fail — identifies root causes by analyzing agent traces, codebase, and behavioral patterns

    Also in 3 projects that use this

  • SentrySkill

    skill-creator

    Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read entrypoints first: README*, AGENTS.md, docs indexes, and skill indexes.

    line 19
  2. Distinctive:

    Search for changed concepts across the repo before calling a doc stale.

    line 25
  3. Distinctive:

    If the user asked for a review, report findings first with file paths.

    line 36
  4. Distinctive:

    If the user asked for fixes, make narrow edits to authoritative docs and indexes.

    line 37
  5. Distinctive:

    Prefer updating or deleting duplicate guidance over adding a new file.

    line 38
  6. Distinctive:

    Do not create broad docs, roadmaps, or repo-local skills without explicit approval.

    line 39
  7. Distinctive:

    Run the repo's documented doc validation.

    line 42
  8. Very specific:

    If no meaningful issue exists, say no change needed and do not invent cosmetic findings.

    line 56
  9. Distinctive:

    Do not call a doc stale without checking repo evidence.

    line 61

“Common” is measured: kept by at least 6 in 10 of the 16 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

Audit Docs

Primary lens: Review.

Goal

Review docs as a navigable system. Find drift, duplication, missing routes, and unclear maintenance rules. Prefer focused fixes over new documentation layers.

Workflow

  1. Scope the audit.
    • Identify the docs or repo area to review.
    • Check git status --short --branch.
    • Read entrypoints first: README*, AGENTS.md, docs indexes, and skill indexes.
  2. Build an evidence map.
    • List authoritative docs.
    • List route/index docs.
    • Note docs that appear historical, duplicated, stale, or incomplete.
    • Search for changed concepts across the repo before calling a doc stale.
  3. Audit for maintainability.
    • Can a new human find the right next doc?
    • Can an agent find the right rule without loading unrelated material?
    • Are install, validation, commit, push, and publishing expectations clear when relevant?
    • Are repeated command sequences better as scripts than prose?
    • Are skill package routes current?
    • Are maintenance triggers documented?
  4. Recommend or edit.
    • If the user asked for a review, report findings first with file paths.
    • If the user asked for fixes, make narrow edits to authoritative docs and indexes.
    • Prefer updating or deleting duplicate guidance over adding a new file.
    • Do not create broad docs, roadmaps, or repo-local skills without explicit approval.
  5. Validate.
    • Run the repo's documented doc validation.
    • At minimum, run git status --short and rg --files.
    • For changed links or routes, verify referenced files exist.

Output

Order findings by impact:

  • stale or wrong guidance
  • missing route or missing authoritative doc
  • duplication or conflicting docs
  • unclear ownership or maintenance trigger
  • overlarge or misplaced agent-only guidance

If no meaningful issue exists, say no change needed and do not invent cosmetic findings.

Do Not

  • Do not create broad docs, roadmaps, or repo-local skills without explicit approval.
  • Do not call a doc stale without checking repo evidence.

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.