Skill Audit

Audits a codebase for quality, consistency, and broken patterns before release.

Tested · Works

Test report

Verdict
Tested · Works
Score
7.6/10
Tested
Jul 13, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Jul 18, 2026 · 0d79bb6

Tested full install (clean, SKILL.md-only, strict YAML frontmatter parses, no external file deps), a 6-prompt trigger battery, and an A/B output test auditing a deliberately-flawed SKILL.md with 7 planted defects. The skill arm caught all 7 planted flaws with no false positives; the no-skill base arm caught 6 (missing the unverifiable-referenced-files defect) and added one minor false positive. Skill is a generic phase/checklist audit methodology with no skill-specific knowledge, so its lift over a capable base model was real but marginal.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 4/5
  • Output vs. baseline 6/10
  • Docs & honesty 4/5

What Skill Audit does

Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review

How to install Skill Audit

git clone https://github.com/nyldn/claude-octopus
cd claude-octopus
mkdir -p ~/.claude/skills
cp -r .claude/skills/skill-audit ~/.claude/skills/skill-audit

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Skill Audit

  • /skill-audit Audits a codebase for quality, consistency, and broken patterns before release.

It also activates on plain-language prompts like these:

  • Audit this codebase before we ship it
  • Find broken patterns and consistency issues in this repo
  • Do a tech-debt review of this project

Frequently asked questions

Is the Skill Audit skill free?
Yes. The skill itself is free from nyldn/claude-octopus. SkillProof publishes the install command and an independent test verdict at no cost.
Does Skill Audit work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 13, 2026. Verdict: Tested · Works. Tested full install (clean, SKILL.md-only, strict YAML frontmatter parses, no external file deps), a 6-prompt trigger battery, and an A/B output test auditing a deliberately-flawed SKILL.md with 7 planted defects. The skill arm caught all 7 planted flaws with no false positives; the no-skill base arm caught 6 (missing the unverifiable-referenced-files defect) and added one minor false positive. Skill is a generic phase/checklist audit methodology with no skill-specific knowledge, so its lift over a capable base model was real but marginal.
What is the Skill Audit SkillProof Score?
7.6/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 6/10, docs & honesty 4/5.
How do I install Skill Audit?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Skill Audit with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.