Skip to content
Skills Library
AI & agents · Review & audit

audit

/audit

Use this skill when auditing a directory of skills, agents, or prompts (SKILL.md, AGENTS.md, CLAUDE.md) for deterministic offline static findings, critical then major then minor. Not for runtime telemetry comparison or unrelated code review.

Licence
MIT
Last repository change
10.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
4
Scripts
3
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 10.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What to check before installing
  • 3 scripts in this package. Review them before installing, as Claude may execute them.

Scripts: lib/checks.js, scripts/audit-staged.mjs, scripts/audit.mjs

What it does and when to use it

Use this skill when auditing a directory of skills, agents, or prompts (SKILL.md, AGENTS.md, CLAUDE.md) for deterministic offline static findings, critical then major then minor. Not for runtime telemetry comparison or unrelated code review.

Original author description

Use this skill when auditing a directory of skills, agents, or prompts (SKILL.md, AGENTS.md, CLAUDE.md) for deterministic offline static findings, critical then major then minor. Not for runtime telemetry comparison or unrelated code review.

How it works

  1. Steps
  2. Notes
Original SKILL.md headings · 36 lines, 235 words
SKILL.md preview
---
name: audit
description: Use this skill when auditing a directory of skills, agents, or prompts (SKILL.md, AGENTS.md, CLAUDE.md) for deterministic offline static findings, critical then major then minor. Not for runtime telemetry comparison or unrelated code review.
allowed-tools: Read, Glob, Grep, Bash
---

# Audit

Run the same static checks the upstream Left the Chat page and its pre-commit hook use,
at full local depth, against a directory the user names.

## Steps

1. Ask which directory to audit if not given. Default to the current directory.
2. Run: `node "${CLAUDE_PLUGIN_ROOT}/skills/audit/scripts/audit.mjs" <directory>`
3. Print the output as-is: findings grouped critical, then major, then minor.
4. If this is the first time this skill has run in this repo, offer to enable a
   pre-commit hook that calls `"${CLAUDE_PLUGIN_ROOT}/skills/audit/scripts/audit-staged.mjs"`
   against files staged in the target repo. Disabled by default. Ask before enabling it;
   never enable it unasked. A minimal hook body:

   ```bash
   #!/usr/bin/env bash
   node "${CLAUDE_PLUGIN_ROOT}/skills/audit/scripts/audit-staged.mjs" || exit 1
   ```

   Write it to `.git/hooks/pre-commit` (or a hooks directory pointed at by
   `git config core.hooksPath`) in the target repo, and mark it executable.

## Notes

- This is the static half only. Declared-versus-actual findings (a tool granted but
  never called, a skill that never fires) need runtime telemetry, which this CLI
  does not have.
- Read-only against the audited files. This skill never edits, moves, or deletes a file
  in the target repo, other than the hook file it is explicitly asked to write in step 4.
- [`examples/find-ai-events.md`](../../examples/find-ai-events.md) (with
  [`examples/find-ai-events-fixed.md`](../../examples/find-ai-events-fixed.md) alongside it
  as the corrected version) is a task prompt written to trip every `PROMPT-*` check - useful
  for seeing the full report shape without writing a prompt from scratch.
Files in this package (4)
  • SKILL.md 2 KB
  • lib/checks.js 23 KB
  • scripts/audit-staged.mjs 2 KB
  • scripts/audit.mjs 3 KB

Versions

RepositoryScoreLicence
This page · youngleadersdottech/young-leaders-tech-marketplace100MIT
marcel-bich/marcel-bich-claude-marketplace100MIT
jeremylongshore/tons-of-skills-marketplace100MIT
friendlyinternet/nuxt-crouton100MIT
userKael/rastro100MIT
Archont561/qgis-agent-harness100MIT
lilly-logic-labs/lll-skills100MIT
Come-In-Labs/agent-skills100MIT
minanyang/10x-agent100MIT

Database snapshot: 13.11.2026 · package version 8cda939d9529 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 90writing-for-agents
    Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
  • 90writing-for-agents
    Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
  • 90writing-for-agents
    Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
  • 90writing-for-agents
    Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
  • 85writing-for-agents
    Use when authoring or restructuring an agent-consumed document, a SKILL.md or skill directory, an AGENTS.md, CLAUDE.md, or rules file, writing skills, or deciding a skill split-or-monolith disclosure question. Not for prose style: use unslop.
  • 100skills-eval
    Evaluate Claude skill quality through auditing. Use when reviewing or auditing skills.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.