- Installs
- 94
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/nickcrew/claude-cortex --skill quality-audit- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads quality-audit automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Quality Audit Skill
Systematic framework for evaluating skill quality across four dimensions: Clarity, Completeness, Accuracy, and Usefulness.
When to Use This Skill
- Reviewing a new skill before adding to the registry
- Auditing existing skills for quality improvements
- Creating quality rubrics for skill validation
- Standardizing skill quality across the library
- Preparing skills for production use
Core Principles
The Four Quality Dimensions
| Dimension | Weight | Focus |
|---|---|---|
| Clarity | 25% | Structure, readability, progressive disclosure |
| Completeness | 25% | Coverage, examples, edge cases, anti-patterns |
| Accuracy | 30% | Correctness, best practices, security |
| Usefulness | 20% | Real-world applicability, production-readiness |
Scoring Scale (1-5)
| Score | Label | Meaning |
|---|---|---|
| 1 | Unacceptable | Fundamentally broken, dangerous, or unusable |
| 2 | Needs Work | Major issues requiring significant revision |
| 3 | Acceptable | Meets minimum standards, functional |
| 4 | Good | High quality, minor improvements possible |
| 5 | Excellent | Exemplary, production-ready, best-in-class |
Passing Criteria
- Minimum: 3.0 weighted average (acceptable)
- Target: 4.0 weighted average (good)
- Exceptional: 4.5+ weighted average (excellent)
- Blocking: Accuracy must be ≥3.0 (no dangerous advice)
Audit Workflow
Phase 1: Structure Check
checklist:
structure:
- [ ] Has valid YAML frontmatter
- [ ] Contains required metadata (name, description)
- [ ] Follows progressive disclosure (Tier 1 → 2 → 3)
- [ ] Sections are logically ordered
- [ ] Token estimate is reasonable (<5000 for core)
Phase 2: Content Evaluation
checklist:
content:
- [ ] "When to Use" section is clear
- [ ] Core principles are well-defined
- [ ] Code examples are complete and runnable
- [ ] Anti-patterns are documented
- [ ] Troubleshooting guidance exists
Phase 3: Dimension Scoring
For each dimension, evaluate against specific criteria:
Clarity Criteria:
- Well-organized sections with logical flow
- Concise explanations without jargon overload
- Code examples are readable and well-commented
- Progressive disclosure from simple to complex
Completeness Criteria:
- Covers core concepts thoroughly
- Includes edge cases and error handling
- Provides both do's and don'ts
- Has working examples for main use cases
Accuracy Criteria:
- Code examples compile/run without errors
- Follows current best practices (not deprecated)
- Security considerations are correct
- Performance claims are verifiable
Usefulness Criteria:
- Examples solve real-world problems
- Can be applied immediately
- Scales to production use cases
- Includes troubleshooting guidance
Phase 4: Report Generation
## Audit Report: {skill_name}
**Date**: {date}
**Auditor**: {auditor}
**Status**: {PASS|FAIL|NEEDS_REVIEW}
### Scores
| Dimension | Score | Weight | Weighted |
|-----------|-------|--------|----------|
| Clarity | {x}/5 | 25% | {x*0.25} |
| Completeness | {x}/5 | 25% | {x*0.25} |
| Accuracy | {x}/5 | 30% | {x*0.30} |
| Usefulness | {x}/5 | 20% | {x*0.20} |
| **Total** | | | **{sum}/5** |
### Issues Found
- [CRITICAL] {issue description}
- [MAJOR] {issue description}
- [MINOR] {issue description}
### Recommendations
1. {actionable recommendation}
2. {actionable recommendation}
Implementation Patterns
Pattern 1: Quick Audit (5-minute review)
Use for rapid assessment of skill quality:
# Run automated structure checks
cortex skills audit <skill-name> --quick
# Output: Pass/Fail with basic metrics
Quick Audit Checks:
- YAML frontmatter valid?
- Required sections present?
- Code blocks have language tags?
- No TODO/FIXME markers?
- Token count reasonable?
Pattern 2: Full Audit (15-30 minute review)
Comprehensive evaluation with human review:
# Generate full audit report
cortex skills audit <skill-name> --full
# Interactive mode for scoring
cortex skills audit <skill-name> --interactive
Full Audit Process:
- Run automated checks
- Read through content manually
- Test code examples
- Score each dimension
- Document issues and recommendations
- Generate report
Pattern 3: Comparative Audit
Compare skill against reference implementation:
# Compare against template-skill-enhanced
cortex skills audit <skill-name> --compare template-skill-enhanced
Pattern 4: Batch Audit
Audit multiple skills for registry health:
# Audit all skills in a category
cortex skills audit --category security
# Audit skills below threshold
cortex skills audit --below-score 3.5
CLI Commands
# Basic audit
cortex skills audit <skill-name>
# Options
--quick Quick structural check only
--full Full audit with all dimensions
--interactive Interactive scoring mode
--output FILE Write report to file
--format FORMAT Output format (markdown|json|yaml)
--compare SKILL Compare against reference skill
--fix Auto-fix simple issues (formatting)
Creating Custom Rubrics
Skills can define custom rubrics in validation/rubric.yaml:
# validation/rubric.yaml
version: "1.0.0"
skill_name: my-skill
dimensions:
clarity:
weight: 25
criteria:
- "API examples use realistic data"
- "Error handling is shown for each operation"
completeness:
weight: 25
criteria:
- "Covers all HTTP methods"
- "Includes pagination patterns"
accuracy:
weight: 30
criteria:
- "Follows REST conventions"
- "Security headers documented"
usefulness:
weight: 20
criteria:
- "Examples work with common frameworks"
passing_criteria:
minimum_score: 3.5 # Higher bar for this skill
required_dimensions:
- accuracy
- completeness
Best Practices
Do
- Be specific - "Line 45: SQL query vulnerable to injection" not "has security issues"
- Be actionable - Include how to fix each issue
- Be fair - Use the same standards consistently
- Document evidence - Quote specific content for each score
- Prioritize - Critical issues first, suggestions last
Don't
- Score based on personal style preferences
- Mark deprecated patterns without suggesting alternatives
- Fail skills for missing optional sections
- Ignore security issues regardless of other scores
- Rush through audits for complex skills
Anti-Patterns
The Rubber Stamp
Problem: Approving skills without thorough review Why it's bad: Low-quality skills erode trust in the library Fix: Use the full audit checklist, test code examples
The Perfectionist Block
Problem: Failing skills for minor issues Why it's bad: Prevents useful skills from being available Fix: Distinguish between blocking issues and suggestions
Score Inflation
Problem: Giving high scores without justification Why it's bad: Makes scores meaningless Fix: Document specific evidence for each score
Integration with CI/CD
# .github/workflows/skill-quality.yml
name: Skill Quality Gate
on:
pull_request:
paths:
- 'skills/**'
jobs:
audit:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Install cortex
run: pip install cortex
- name: Audit changed skills
run: |
for skill in $(git diff --name-only HEAD~1 | grep 'skills/' | cut -d'/' -f2 | uniq); do
cortex skills audit "$skill" --quick --fail-under 3.0
done
Troubleshooting
"Audit fails but skill looks fine"
- Check YAML frontmatter syntax
- Verify all required sections exist
- Ensure code blocks have language tags
- Check for hidden characters (copy/paste issues)
"Scores seem inconsistent"
- Review the scoring guide for each dimension
- Calibrate by auditing template-skill-enhanced first
- Use --interactive mode for clearer criteria
External Resources
- Skill Template Reference
- Rubric Schema
- Skill Creator Guide
Changelog
1.0.0 (2026-01-05)
- Initial release
- Four-dimension scoring framework
- CLI integration
- CI/CD workflow example
FAQ
What does the quality-audit skill do?
Meta-skill for auditing and validating skill quality. Use when reviewing skills for consistency, completeness, accuracy, and adherence to standards. Provides structured rubrics, scoring frameworks, and actionable recommendations.
How do I install quality-audit?
Run npx skills add https://github.com/nickcrew/claude-cortex --skill quality-audit in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/quality-audit/ (personal) or .claude/skills/quality-audit/ (project).
Which AI agents can use quality-audit?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is quality-audit safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains quality-audit?
It is published by nickcrew in nickcrew/claude-cortex. It has 94 recorded installs.
More from nickcrew/claude-cortex
react-performance-optimization
nickcrew/claude-cortex
React performance optimization patterns using memoization, code splitting, and efficient rendering strategies. Use when optimizing slow React applications, reducing bundle size, or improving user experience with large datasets.
owasp-top-10
nickcrew/claude-cortex
OWASP Top 10 security vulnerabilities with detection and remediation patterns. Use when conducting security audits, implementing secure coding practices, or reviewing code for common security vulnerabilities.
ui-design-aesthetics
nickcrew/claude-cortex
Generates high-quality, non-generic UI designs with a focus on performance, progressive disclosure, and distinctive aesthetics.
threat-modeling-techniques
nickcrew/claude-cortex
Open the skill to read its SKILL.md instructions.
token-efficiency
nickcrew/claude-cortex
Compressed communication using symbols and abbreviations. Use when context is limited or brevity is needed.
helm-chart-patterns
nickcrew/claude-cortex
Helm chart development patterns for packaging and deploying Kubernetes applications. Use when creating reusable Helm charts, managing multi-environment deployments, or building application catalogs for Kubernetes.
Popular security skills
azure-compliance
microsoft/azure-skills
Run Azure compliance and security audits with azqr plus Key Vault expiration checks. Covers best-practice assessment, resource review, policy/compliance validation, and security posture checks. WHEN: compliance scan, security audit, BEFORE running azqr (compliance cli tool), Azure best practices, Key Vault expiration check, expired certificates, expiring secrets, orphaned resources, compliance assessment.
minimal-run-and-audit
lllllllama/rigorpilot-skills
Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized reprooutputs/ files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end-to-end orchestration by itself.
seo-audit
coreyhaines31/marketingskills
When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking," "Google update hit me," "page speed," "core web vitals," "crawl errors," "indexing issues," "stuck on page 2," "striking distance keywords," "title tag rewrite," "low CTR," "local SEO," "Google Business Profile," or "map pack." Use this even if the user just says something vague like "my SEO is bad" or "help with SEO" — start with an audit. For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema. For AI search optimization, see ai-seo.
firebase-security-rules-auditor
firebase/agent-skills
Audits Firebase (Firestore, Cloud Storage) security rules for vulnerabilities, privilege escalation, role bypasses, create vs update inconsistencies, resource exhaustion, type safety, size limits, and hasOnly ownership checks. Use when auditing/reviewing rules, running red-team rule assessments, or scoring against auditor checklists. Don't use for Firebase CLI (login, deploy), Auth, Crashlytics, Remote Config, or database queries.
audit
pbakaus/impeccable
Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.
competitors
coreyhaines31/marketingskills
When the user wants to create competitor comparison or alternative pages for SEO and buyer-facing use. Also use when the user mentions 'alternative page,' 'vs page,' 'competitor comparison,' 'comparison page,' '[Product] vs [Product],' '[Product] alternative,' 'competitive landing pages,' 'how do we compare to X,' 'competitor teardown,' 'audit our competitor pages,' 'are our comparison pages out of date,' or 'competitive asset audit.' Use this for any content that positions your product against competitors. Covers four formats: singular alternative, plural alternatives, you vs competitor, and competitor vs competitor. For auditing existing claims (not researching competitors from scratch, which is competitor-profiling; not technical SEO on these pages, which is seo-audit), use the asset audit here. For internal battle cards and sales-specific competitor docs, see sales-enablement.