agentleFS
ApurvBazariApurvBazari/claude-plugins/.claude/skills/doc-audit/SKILL.md

doc-audit

Skill3 starsChanged 48 days agoMITView on GitHub

Audit and surgically fix the marketplace's documentation so every shipped command is discoverable — checks each plugin README's Skills section against SKILL.md frontmatter, the root README's plugin list and command index, manifest/description sync, and docs-site parity. Use when docs may have drifted from the code, after adding or renaming a skill or plugin, or before a release.

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

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never run the fix pass outside a git working tree where changes can be reviewed/reverted.

    line 17
  2. Distinctive:

    Run the audit and read the full report:

    line 21
  3. Very specific:

    Read references/completeness-contract.md for the exact rules and scaffold shape.

    line 36
  4. Distinctive:

    Surgical rule: never rewrite an existing hand-written entry.

    line 46
  5. Distinctive:

    Leave existing hand-written documentation intact — add, don't rewrite.

    line 72

“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

/doc-audit — Documentation Completeness Auditor & Fixer

Audit the marketplace's docs against machine truth (SKILL.md frontmatter + manifests), then surgically fix the mechanical gaps and flag the rest. Read-only detection lives in audit-docs.sh; the edits below are applied by you, the model, only on the fix pass.

Guard

This skill edits files (READMEs). It is user-invoked only. On a real run it will modify plugin READMEs and the root README in the working tree — the user reviews via git diff. Never run the fix pass outside a git working tree where changes can be reviewed/reverted.

Step 1: Detect

Run the audit and read the full report:

bash .claude/skills/doc-audit/scripts/audit-docs.sh --format pretty

(Optionally --root <dir> to audit a different checkout, e.g. a worktree.)

Step 2: Present the report

Summarise the findings grouped by severity (ERROR / WARN / INFO) and by layer. Include the coverage table (command → documented?) so the user sees included-vs-omitted without asking.

Step 3: Surgical fix pass (auto-fixable findings only)

Read references/completeness-contract.md for the exact rules and scaffold shape. Then, for each auto-fixable finding, make the smallest edit that resolves it:

  • MISSING_SKILLS_SECTION → add a ## Skills section scaffolded from frontmatter.
  • CMD_NOT_IN_README → insert one entry (scaffold shape) in canonical order.
  • MARKER_MISSING → add *(destructive — user-invoked only)* to that entry's header only.
  • PLUGIN_NOT_IN_ROOT → add the plugin to the root "at a glance" table and command index.
  • ROOT_COUNT_STALE → correct the plugin-count word/number.
  • ROOT_NO_CMD_INDEX → add a central command index listing every plugin's user commands. If a command section already exists, extend it in place — never add a second index (the fix is idempotent: re-running must produce no further change).

Surgical rule: never rewrite an existing hand-written entry. Only add what is missing or correct a marker/count. Preserve tables, prose, and ordering already present.

Step 4: Flag the rest (no edits)

Report flag-only findings verbatim for the user to handle: PHANTOM_CMD, VERSION_MISMATCH, DESC_MISMATCH, PLUGIN_JSON_MISSING, SITE_PAGE_MISSING. For that finding, the instruction is "run /walkthrough:document <plugin>". Site content drift is checked by /release-docs and its "Docs Obligations" gate, not here.

Step 5: Re-verify

Re-run the audit and confirm ERROR count is 0 and the only remaining items are the flag-only findings you reported:

bash .claude/skills/doc-audit/scripts/audit-docs.sh --format pretty

Then tell the user to review git diff before committing.

Key Rules

  • Detection is deterministic and read-only; all edits are yours, applied surgically.
  • Truth = SKILL.md frontmatter + manifests. Never invent a command not backed by a SKILL.md.
  • Auto-fix only the codes listed in Step 3; everything else is flag-only.
  • Leave existing hand-written documentation intact — add, don't rewrite.

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.