Skip to content
Back to skills

Skill Audit

ASecurity

Use when "audit skill", "review skill quality", "check skill", "skill score", "skill checklist", "is this skill good", or evaluating skill against best practices. Do NOT use for KB audits (/audit) or code review (/review).

  • 18 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 18, 2026
ai-agentsgobashreact

Works with

  • claude code

Security analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned November 18, 2026

npx -y skills add fortunto2/solo-factory --skill skill-audit --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Skill Audit?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Skill Audit
[![Security: A β€” Skills Directory](https://www.skillsdirectory.com/api/skills/fortunto2-skill-audit/badge)](https://www.skillsdirectory.com/skills/fortunto2-skill-audit)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: solo-skill-audit
description: Use when "audit skill", "review skill quality", "check skill", "skill score", "skill checklist", "is this skill good", or evaluating skill against best practices. Do NOT use for KB audits (/audit) or code review (/review).
license: MIT
metadata:
  author: fortunto2
  version: "1.0.0"
  openclaw:
    emoji: "πŸ”"
allowed-tools: Read, Grep, Glob, Bash
argument-hint: "<skill-name or path>"
---

# /skill-audit

Audit a skill against the quality checklist based on Anthropic's internal best practices for Claude Code skills. Reads the skill's SKILL.md, references/, scripts/, and evaluates across 12 dimensions.

Source: https://x.com/trq212/status/2033949937936085378

## Checklist Reference

- Scoring rubric, 12 dimensions: `references/checklist.md`
- The levers the scores measure β€” invocation, information hierarchy, leading words, failure modes: `references/writing-skills.md`
- Term definitions used in findings: `references/skills-glossary.md`

## Steps

1. **Locate skill** from `$ARGUMENTS`:
   - If name: search `skills/{name}/SKILL.md` in current project, then `~/.claude/plugins/**/skills/{name}/SKILL.md`
   - If path: read directly
   - If empty: list available skills via Glob `**/skills/*/SKILL.md`, ask via AskUserQuestion

2. **Read skill contents** (parallel):
   - `SKILL.md` β€” main skill file
   - `references/*` β€” all reference files (if dir exists)
   - `scripts/*` β€” all scripts (if dir exists)
   - `assets/*` β€” all assets (if dir exists)
   - Count total lines of SKILL.md

3. **Read checklist** from `references/checklist.md`

4. **Evaluate each dimension** β€” for every checklist item, assess based on what you read:

   For each of the 12 dimensions:
   - State what you found (evidence)
   - Score 0, 1, or 2 (use rubric from checklist)
   - If score < 2: give one specific fix

5. **Determine category** β€” classify skill into one of 9 types from checklist. Flag if it straddles multiple.

6. **Failure-mode pass** β€” read `references/writing-skills.md`, then check the skill for each named failure mode. Quote the offending line for every hit; a hit with no quote is a guess:
   - **No-op** β€” a line the model already obeys by default. Test each sentence in isolation: does it change behaviour versus the default?
   - **Duplication** β€” one meaning stated in more than one place.
   - **Sediment** β€” stale lines describing behaviour, paths, or tools that no longer exist.
   - **Sprawl** β€” long even after no-ops and duplication are removed; cure is disclosure into `references/`, not deletion.
   - **Negation** β€” steering by prohibition where a positive target would work. `Don't use X` names X; `use Y` doesn't.
   - **Premature completion** β€” a step whose completion criterion can't distinguish done from not-done.
   - **Weak leading word** β€” a description or body leaning on generic words instead of a compact pretrained concept the user actually types.

7. **Output scorecard:**

   ```
   ## Skill Audit: {skill-name}

   **Score:** {N}/24 (Grade: {A/B/C/D/F})
   **Category:** {type}
   **SKILL.md:** {N} lines | **References:** {N} files | **Scripts:** {N} files

   | # | Dimension | Score | Notes |
   |---|-----------|-------|-------|
   | 1 | Category Fit | {0-2} | {one line} |
   | 2 | Description Quality | {0-2} | {one line} |
   | 3 | Progressive Disclosure | {0-2} | {one line} |
   | 4 | Gotchas | {0-2} | {one line} |
   | 5 | Don't State Obvious | {0-2} | {one line} |
   | 6 | Flexibility | {0-2} | {one line} |
   | 7 | Setup & Config | {0-2} | {one line} |
   | 8 | Memory & State | {0-2} | {one line} |
   | 9 | Scripts & Code | {0-2} | {one line} |
   | 10 | Allowed Tools | {0-2} | {one line} |
   | 11 | Argument Handling | {0-2} | {one line} |
   | 12 | Output & Artifacts | {0-2} | {one line} |

   ### Failure Modes
   {mode} β€” "{quoted line}" β†’ {fix}
   (or "none found")

   ### Top 3 Fixes (highest impact)
   1. {fix}
   2. {fix}
   3. {fix}
   ```

8. **Batch mode** β€” if `$ARGUMENTS` is "all" or "*":
   - Find all skills via Glob
   - Run audit on each
   - Output summary table sorted by score (worst first)
   - Identify common weaknesses across the set

## Gotchas

1. **N/A dimensions still score 2** β€” if a skill genuinely doesn't need config/state/scripts, don't penalize it. Score N/A as 2. Only score 0-1 when the skill SHOULD have it but doesn't.
2. **Gotchas β‰  Common Issues** β€” "Common Issues" is troubleshooting (reactive). Gotchas are preventive β€” things Claude would get WRONG by default. A skill with only "Common Issues" scores 1, not 2.
3. **Line count is a smell, not a rule** β€” 500-line SKILL.md with no references is suspicious. But 400 lines of dense, non-obvious content is fine. Check if content COULD be extracted, not just if it's long.
4. **Description under 300 chars** β€” long descriptions dilute the trigger signal. Claude scans ALL skill descriptions at session start. Shorter = sharper matching.

## Common Issues

### Can't find skill
**Cause:** Skill not in expected path or using different directory structure.
**Fix:** Use full path to SKILL.md as argument. Or run with "all" to discover available skills.

### Score seems unfair
**Cause:** Some dimensions don't apply to the skill type.
**Fix:** N/A dimensions score 2. Re-read the rubric β€” it accounts for genuinely stateless or config-free skills.

Files in this skill

  • SKILL.md5.3 KB
  • references/checklist.md7.2 KB
  • references/skills-glossary.md8.8 KB
  • references/writing-skills.md9.7 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents β†’

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.