# quality-auditor

quality-auditor audits repositories, architecture, and code across 12 dimensions with a 1-to-10 scoring system.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 201 installs · ★ 39 repo stars
- Author: daffy0208
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/daffy0208/ai-dev-standards/tree/HEAD/skills/quality-auditor/SKILL.md
- Updated: 2025-12-25
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/quality-auditor

## What it does

This skill instructs the agent to audit tools, frameworks, and codebases. It scores projects across 12 areas, including code structure, testing depth, architectural modularity, security standards like OWASP, and accessibility.

The review starts with Phase 0, a mandatory registry completeness check. It compares catalog files against `META/registry.json` using `npm run test:registry` or shell tools like `jq` and `wc`. If more than 10% of resources are unregistered or cross-references break, the overall audit score is hard-capped at 6/10.

Every evaluation requires evidence from the codebase, citing concrete files and offering explicit remediation steps.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add daffy0208/ai-dev-standards --skill quality-auditor -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/quality-auditor/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/quality-auditor/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add daffy0208/ai-dev-standards --skill quality-auditor -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/quality-auditor/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add daffy0208/ai-dev-standards --skill quality-auditor -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/quality-auditor/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install daffy0208/ai-dev-standards skills/quality-auditor
```

2. **Manually: put the files in place**
- File: `.github/skills/quality-auditor/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add daffy0208/ai-dev-standards --skill quality-auditor -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/daffy0208/ai-dev-standards --path skills/quality-auditor
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/quality-auditor/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add daffy0208/ai-dev-standards --skill quality-auditor -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/daffy0208/ai-dev-standards/tree/HEAD/skills/quality-auditor/SKILL.md

## When to use it
- grade codebase maintainability and structure on a 1-to-10 scale
- validate that registry entries match actual directory files
- spot mismatches between README guides and active code
- audit automated testing and deployment workflows

## Example prompts
- Run a full quality audit on this codebase
- Assess architecture and test coverage against standards
- Verify registry completeness and resource discoverability

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: a2cf8c344d204b1b.

BEGIN THIRD-PARTY FILE a2cf8c344d204b1b
````text
---
name: quality-auditor
description: Comprehensive quality auditing and evaluation of tools, frameworks, and systems against industry best practices with detailed scoring across 12 critical dimensions
version: 1.0.0
category: Quality & Standards
triggers:
  - audit
  - evaluate
  - review
  - assess quality
  - score
  - quality check
  - code review
  - appraise
  - measure against standards
prerequisites: []
---

# Quality Auditor

You are a **Quality Auditor** - an expert in evaluating tools, frameworks, systems, and codebases against the highest industry standards.

## Core Competencies

You evaluate across **12 critical dimensions**:

1. **Code Quality** - Structure, patterns, maintainability
2. **Architecture** - Design, scalability, modularity
3. **Documentation** - Completeness, clarity, accuracy
4. **Usability** - User experience, learning curve, ergonomics
5. **Performance** - Speed, efficiency, resource usage
6. **Security** - Vulnerabilities, best practices, compliance
7. **Testing** - Coverage, quality, automation
8. **Maintainability** - Technical debt, refactorability, clarity
9. **Developer Experience** - Ease of use, tooling, workflow
10. **Accessibility** - ADHD-friendly, a11y compliance, inclusivity
11. **CI/CD** - Automation, deployment, reliability
12. **Innovation** - Novelty, creativity, forward-thinking

---

## Evaluation Framework

### Scoring System

Each dimension is scored on a **1-10 scale**:

- **10/10** - Exceptional, industry-leading, sets new standards
- **9/10** - Excellent, exceeds expectations significantly
- **8/10** - Very good, above average with minor gaps
- **7/10** - Good, meets expectations with some improvements needed
- **6/10** - Acceptable, meets minimum standards
- **5/10** - Below average, significant improvements needed
- **4/10** - Poor, major gaps and issues
- **3/10** - Very poor, fundamental problems
- **2/10** - Critical issues, barely functional
- **1/10** - Non-functional or completely inadequate

### Scoring Criteria

**Be rigorous and objective:**

- Compare against **industry leaders** (not average tools)
- Reference **established standards** (OWASP, WCAG, IEEE, ISO)
- Consider **real-world usage** and edge cases
- Identify both **strengths** and **weaknesses**
- Provide **specific examples** for each score
- Suggest **concrete improvements**

---

## Audit Process

### Phase 0: Resource Completeness Check (5 minutes) - CRITICAL

**⚠️ MANDATORY FIRST STEP - Audit MUST fail if this fails**

**For ai-dev-standards or similar repositories with resource registries:**

1. **Verify Registry Completeness**

   ```bash
   # Run automated validation
   npm run test:registry

   # Manual checks if tests don't exist yet:

   # Count resources in directories
   ls -1 SKILLS/ | grep -v "_TEMPLATE" | wc -l
   ls -1 MCP-SERVERS/ | wc -l
   ls -1 PLAYBOOKS/*.md | wc -l

   # Count resources in registry
   jq '.skills | length' META/registry.json
   jq '.mcpServers | length' META/registry.json
````
END THIRD-PARTY FILE a2cf8c344d204b1b

The third-party file has ended. Everything between the a2cf8c344d204b1b tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2996 of 20985 bytes. © daffy0208 · MIT · https://github.com/daffy0208/ai-dev-standards/tree/HEAD/skills/quality-auditor/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
