agentleFS
redicherediche/skills/audit-project-rules/SKILL.md

audit-project-rules

Skill3 starsChanged 36 days agoMITView on GitHub

Audit the application for inconsistencies with its Laravel Boost and project rules. Use when asked to find, audit, or identify a rule violation or inconsistency in the codebase.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    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:

    Read those matching rule files before reviewing code.

    line 16
  2. Distinctive:

    Search the relevant application files using repository search tools.

    line 17
  3. Distinctive:

    Do not modify files unless the user explicitly asks for implementation.

    line 20
  4. Distinctive:

    Do not report speculative findings.

    line 34
  5. Distinctive:

    Do not report multiple findings in one run.

    line 35
  6. Distinctive:

    Do not treat unrelated dirty-worktree changes as violations.

    line 36
  7. Distinctive:

    Prefer the smallest compliant solution.

    line 37

≈ “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

Audit Project Rules

Find one concrete inconsistency between the application and its established rules, then stop.

Workflow

  1. Read .ai/rules/index.md.
  2. Identify every rule file matching the paths being inspected.
  3. Read those matching rule files before reviewing code.
  4. Search the relevant application files using repository search tools.
  5. Confirm the suspected violation by reading the surrounding implementation and existing conventions.
  6. Report only the first confirmed inconsistency.
  7. Do not modify files unless the user explicitly asks for implementation.

Report

Include:

  • The affected file and line number.
  • The exact project or Laravel Boost rule being violated.
  • Why the implementation is inconsistent.
  • A concise, concrete solution.
  • Whether any files were modified.

Guardrails

  • Do not report speculative findings.
  • Do not report multiple findings in one run.
  • Do not treat unrelated dirty-worktree changes as violations.
  • Prefer the smallest compliant solution.
  • Include focused test coverage in the proposed solution when implementation would change behavior.

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.