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

Scoring Scale (1-5)

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:

1. YAML frontmatter valid?
2. Required sections present?
3. Code blocks have language tags?
4. No TODO/FIXME markers?
5. 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:

1. Run automated checks
2. Read through content manually
3. Test code examples
4. Score each dimension
5. Document issues and recommendations
6. 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 dimen

...