do-skills-auditlisted
Install: claude install-skill tomcounsell/ai
# Skills Audit
Validates all `.claude/skills/*/SKILL.md` files against canonical template standards and Anthropic's latest published best practices.
## What this skill does
1. Runs 12 deterministic validation rules (frontmatter, structure, classification, content)
2. Fetches latest Anthropic skill docs and compares against our standards (by default)
3. Produces a structured PASS/WARN/FAIL report per skill
4. Optionally auto-fixes trivial issues
## Quick start
```bash
python .claude/skills-global/do-skills-audit/scripts/audit_skills.py $ARGUMENTS
```
**If `$ARGUMENTS` was not substituted** (the command shows a literal `$ARGUMENTS`): Look at the user's original message — they invoked this as `/do-skills-audit <flags>`. Extract whatever follows `/do-skills-audit` and pass it to the script. If no flags were provided, run the script with no arguments (default behavior).
## Arguments
| Flag | Description |
|------|-------------|
| `--fix` | Auto-fix trivial issues (missing name, trailing whitespace) |
| `--json` | Output JSON only |
| `--skill <name>` | Audit a single skill |
| `--no-sync` | Skip best practices sync (fast, offline) |
| `--apply` | Apply best practices updates to template/validator |
| `--update-skills` | Update existing skills to match new best practices |
| `--force-refresh` | Bypass doc cache and re-fetch |
## Validation Rules
**Structural (FAIL):** line count ≤500, frontmatter exists, name valid, broken sub-file links
**Quality (WARN):** description tr