audit

Analyze repositories for quality and risk issues, then output a prioritized markdown punch list.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/Z5Jonathan-maker/ai-coding-os --skill audit-z5jonathan-maker
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: audit
Source: https://github.com/Z5Jonathan-maker/ai-coding-os/tree/main/claude/skills/audit
Command: npx skills add https://github.com/Z5Jonathan-maker/ai-coding-os --skill audit-z5jonathan-maker

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires npm audit, jq, ts-prune, depcheck, detect-secrets.

What problem does it solve?

Audit-heavy teams need a reliable way to identify what is actually broken or risky in a codebase—spanning performance, accessibility, SEO, security, dependency hygiene, dead code, framework drift, documentation compliance, and CI/deploy readiness.

Core Features & Use Cases

  • Production-grade audit & scoring: Runs Lighthouse-style performance/accessibility/SEO checks and dependency security review, flagging categories that fall below thresholds.
  • Deep hygiene triage: Detects outdated deps, framework/version drift, unused/dead code, bundle bloat, potential secrets exposure, and missing or outdated documentation artifacts.
  • Taste & spec compliance: Compares DESIGN.md token usage vs actual code and checks for expected project-shape conventions, then outputs a single prioritized punch list for what to fix next.

Quick Start

Run /audit in an existing project to generate a prioritized markdown punch list with critical items first.

Frequently Asked Questions about audit

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run a comprehensive codebase audit for security, performance, and dead code?

To run a comprehensive codebase audit, execute a single command to analyze security, performance, accessibility, SEO, dependency hygiene, and dead code. The audit synthesizes these checks into a prioritized markdown punch list for immediate repository rehabilitation.

What is the best way to detect framework drift and outdated dependencies in an existing project?

Detecting framework drift and outdated dependencies involves analyzing your project against expected conventions and running stack dependency audits. This process flags version mismatches and stale packages, adding them to a prioritized rehab list.

How does secret scanning and dependency hygiene work during pre-deploy validation?

Pre-deploy validation uses tools like detect-secrets and npm audit to scan for exposed credentials and vulnerable packages. It checks dependency hygiene by identifying outdated libraries and potential security risks before release.

Can I check DESIGN.md token usage compliance against actual frontend code automatically?

You can check DESIGN.md token compliance by comparing documented design tokens against actual code usage. This spec compliance audit identifies drift between intended design architecture and implemented frontend components.

What limitations exist when running dead code detection on a large repository?

Dead code detection relies on static analysis tools like ts-prune and depcheck, which may miss dynamically imported modules or complex runtime references. It works best on structured codebases with expected CI conventions.

Do I need jq and npm audit installed to generate a repository rehab punch list?

Yes, generating a repository rehab punch list requires jq and npm audit installed to parse JSON outputs and analyze dependency vulnerabilities. These dependencies enable the structured analysis of security and hygiene metrics.