agentleFS
aradmanamnaoonaradmanamnaoon/vibe-coding-skills/skills/documentation/documentation-accuracy-auditor/SKILL.md

documentation-accuracy-auditor

Skill0 starsChanged 18 days agoMITView on GitHub

Verify README, setup, examples, commands, API docs, screenshots/claims, and paths against the current repository. Use after implementation or before release.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    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
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Read applicable repository instructions before edits.

    line 20
  2. Very specific:

    Check referenced files/anchors/paths exist and internal links resolve.

    line 33
  3. Distinctive:

    Run quick-start and representative commands in a clean/local environment when feasible.

    line 34
  4. Distinctive:

    Verify screenshots or benchmark/status claims have corresponding current evidence.

    line 36
  5. Distinctive:

    Check installation instructions do not expose secrets or rely on undeclared global state.

    line 37
  6. Distinctive:

    Run link/doc validation and record external links that could not be checked.

    line 38
  7. Distinctive:

    Do not fabricate badges, benchmark results, screenshots, download counts, or compatibility claims.

    line 46
  8. Distinctive:

    All local links/paths and runnable commands in the reviewed scope are verified.

    line 50
  9. Distinctive:

    If an external link/service cannot be reached, leave the link only when authoritative and mark runtime validation separately rather than …

    line 63

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Purpose

Prevent documentation from describing a project that no longer exists.

When to activate

Code/config/CLI behavior changed or documentation is being prepared for publication.

When not to activate

Internal refactor has no externally documented behavior and all generated docs are unaffected.

Preconditions

  • Read applicable repository instructions before edits.
  • Preserve unrelated working-tree changes and establish a baseline when the workflow can modify code.
  • Identify which tools and environments are actually available; do not claim unavailable checks ran.

Required inputs

  • Documentation files
  • Current CLI/API/config
  • Build/test environment

Workflow

  1. Extract executable claims from docs: commands, filenames, flags, endpoints, versions, outputs, supported environments, badges, and feature status.
  2. Check referenced files/anchors/paths exist and internal links resolve.
  3. Run quick-start and representative commands in a clean/local environment when feasible.
  4. Compare API/CLI examples to current parser/schema/types and update stale output/options.
  5. Verify screenshots or benchmark/status claims have corresponding current evidence; remove stale/unsupported claims.
  6. Check installation instructions do not expose secrets or rely on undeclared global state.
  7. Run link/doc validation and record external links that could not be checked.

Relevant tools

Repository search, CLI --help, link checker when available, clean environment.

Safety restrictions

Do not fabricate badges, benchmark results, screenshots, download counts, or compatibility claims.

Validation

  • All local links/paths and runnable commands in the reviewed scope are verified.
  • Feature/status claims match validation evidence.
  • Known environment prerequisites and limitations are explicit.

Expected output

  • Documentation claim audit
  • Commands actually run
  • Broken/stale items fixed
  • Unverified external references

Failure handling

If an external link/service cannot be reached, leave the link only when authoritative and mark runtime validation separately rather than inventing accessibility.

Completion criteria

The skill is complete only when every applicable validation item above has observed evidence or is explicitly marked not executed with the concrete blocker. Do not replace missing evidence with confidence language.

Research mapping

This skill was selected from research problems: P051. See research/vibe-coding-problems.md and research/problem-evidence.csv in the Vibe Coding Skills repository.

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.