agentleFS
Sign inStart free
mrveissmrveiss/AutoBot-AI/.claude/skills/canonical-audit/SKILL.md

canonical-audit

Skill39 starsChanged 20 days agoApache-2.0View on GitHub

Run a full-codebase canonical-pattern audit and write a markdown report to .canonical-audit/. Use when the user asks for a canonical-style scan, a #7458 progress check, or a periodic audit between cron runs.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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
  1. Distinctive:

    Verify the runners exist:

    line 12
  2. Very specific:

    Run the audit via the Make target (also creates .canonical-audit/ if missing):

    line 17
  3. Distinctive:

    Read the most recent markdown reports:

    line 22
  4. Distinctive:

    If any rule has BLOCK-severity violations, also surface the top 5 offending files for that rule.

    line 28
  5. Distinctive:

    Do NOT auto-file GitHub issues.

    line 30

≈ “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

/canonical-audit

Runs the canonical-check Python and infra runners in --all mode and writes both markdown and JSON sidecars to .canonical-audit/ (gitignored). Then summarizes the report inline.

Steps

  1. Verify the runners exist:
    test -f tools/lint/canonical_check.py && test -f tools/lint/canonical_check_infra.py || echo "ERROR: canonical-check not installed"
  2. Run the audit via the Make target (also creates .canonical-audit/ if missing):
    make canonical-audit
  3. Read the most recent markdown reports:
    ls -1t .canonical-audit/*.md | head -3
    Open each and surface the Summary table to the user.
  4. If any rule has BLOCK-severity violations, also surface the top 5 offending files for that rule.
  5. Do NOT auto-file GitHub issues. Report findings inline. Filing is a separate user-driven step.

Notes

  • Frontend audit (canonical-check-fe) does not yet support --all mode (deferred to Wave 3). It is skipped here.
  • Reports go to .canonical-audit/ locally and to GitHub Actions artifacts on the weekly cron run. Neither is committed.

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.

Check your setup, free