Claude
Skills
Sign in
Back

skill-reviewer-and-enhancer

Included with Lifetime
$97 forever

This skill should be used when reviewing, auditing, or improving existing Claude Code skills to ensure they follow Anthropic best practices, have proper structure, use current domain-specific patterns, and include all necessary resources. It analyzes skill quality, identifies gaps, suggests improvements, and can automatically enhance skills with updated best practices. Trigger terms include review skill, audit skill, improve skill, enhance skill, update skill, check skill quality, skill best practices, fix skill, optimize skill, validate skill structure.

AI Agentsscriptsassets

What this skill does


# Skill Reviewer and Enhancer

Review, audit, and enhance existing Claude Code skills to ensure they follow Anthropic best practices and current domain-specific patterns.

## Overview

To improve skill quality and ensure adherence to official standards, this skill performs comprehensive analysis of existing skills, identifies structural issues, verifies domain-specific best practices, and automatically applies improvements.

## When to Use This Skill

Apply this skill when:
- Reviewing an existing skill for quality and compliance
- Auditing skills before deployment to production
- Updating skills to follow latest Anthropic guidelines
- Ensuring skills use current framework/library patterns
- Identifying missing resources or incomplete implementations
- Enhancing skill descriptions for better discoverability
- Fixing structural or formatting issues
- Modernizing outdated skill instructions

## Step 1: Locate and Read the Skill

To begin the review process:

1. Ask user for the skill path or name if not provided
2. Verify the skill directory exists
3. Read the SKILL.md file completely
4. Note the skill's category and purpose

```bash
# Find skill
ls skills/[category]/[skill-name]/SKILL.md

# Read skill
Read: skills/[category]/[skill-name]/SKILL.md
```

## Step 2: Analyze Skill Structure

To verify proper skill structure, check for:

### Frontmatter Validation

**Required Fields:**
- `name`: Must be present, hyphen-case, no angle brackets
- `description`: Must be present, third-person voice, includes trigger terms, under 1024 characters

**Optional Fields:**
- `allowed-tools`: Present for read-only/analysis skills

**Validation Script:**
```bash
python scripts/analyze_skill_structure.py --skill skills/[category]/[skill-name]
```

### Name Convention Check

Verify name follows hyphen-case:
- [OK] Correct: `skill-reviewer-and-enhancer`, `nextjs-fullstack-scaffold`
- [WRONG] Incorrect: `SkillReviewer`, `skill_reviewer`, `skillReviewer`

Check for invalid patterns:
- Starts or ends with hyphen
- Contains consecutive hyphens (`--`)
- Contains uppercase letters
- Contains underscores or other special characters

### Description Quality Check

Verify description:
- **Voice**: Uses third-person ("This skill should be used when...")
- **Content**: Explains WHAT it does and WHEN to use it
- **Trigger Terms**: Includes specific keywords users would search for
- **Length**: Under 1024 characters
- **Format**: No angle brackets, proper grammar

## Step 3: Review Instruction Style

To verify proper instruction format, scan the SKILL.md body for:

### Imperative Form Check

Instructions should use imperative/infinitive form:
- [OK] Correct: "To create a form, use the generator script"
- [OK] Correct: "Generate schemas using the Zod validator"
- [WRONG] Incorrect: "You should create forms using the generator"
- [WRONG] Incorrect: "You can generate schemas with Zod"

Use Grep to find second-person usage:
```bash
Grep: pattern="\\b[Yy]ou\\b" path="skills/[category]/[skill-name]/SKILL.md" output_mode="content"
```

Flag any instances for correction.

### Section Structure Check

Verify logical organization:
- Overview/Introduction
- When to Use (optional but recommended)
- Prerequisites (if applicable)
- Step-by-step implementation
- Resource references (scripts, references, assets)
- Best practices
- Troubleshooting (optional)

## Step 4: Verify Domain-Specific Best Practices

To ensure the skill follows current best practices for its domain, consult the appropriate reference:

### Development Skills
For Next.js, React, TypeScript, database skills, check:
- Uses latest framework versions (Next.js 15/16, React 19)
- Follows Server Components patterns
- Uses App Router (not Pages Router)
- Implements proper TypeScript types
- Uses modern tooling (Vite, Vitest, ESM)

Consult `references/nextjs-best-practices.md` for detailed checks.

### Testing Skills
For testing-related skills, check:
- Uses modern test runners (Vitest, not Jest)
- Uses Testing Library patterns
- Implements accessibility testing
- Follows AAA pattern (Arrange, Act, Assert)
- Uses proper mocking strategies

Consult `references/testing-best-practices.md` for detailed checks.

### UI Component Skills
For UI and component skills, check:
- Uses shadcn/ui patterns correctly
- Implements accessibility (ARIA, semantic HTML)
- Follows Tailwind CSS conventions
- Uses proper composition patterns
- Implements dark mode support

Consult `references/ui-best-practices.md` for detailed checks.

### Database Skills
For database and ORM skills, check:
- Uses Prisma 5+ patterns
- Implements proper connection pooling
- Uses prepared statements/parameterized queries
- Implements RLS for Supabase
- Uses proper migration patterns

Consult `references/database-best-practices.md` for detailed checks.

### Security Skills
For security-related skills, check:
- Follows OWASP guidelines
- Implements proper authentication patterns
- Uses secure session management
- Implements CSRF protection
- Uses Content Security Policy
- Validates and sanitizes inputs

Consult `references/security-best-practices.md` for detailed checks.

## Step 5: Check Resource References

To verify bundled resources are properly referenced:

### Scripts Directory
Check if skill references scripts and whether they exist:
```bash
Grep: pattern="scripts/" path="skills/[category]/[skill-name]/SKILL.md" output_mode="content"
Glob: pattern="skills/[category]/[skill-name]/scripts/*"
```

Verify:
- Scripts mentioned in SKILL.md exist in scripts/ directory
- Scripts have proper documentation
- Scripts are executable (Python/Bash)
- Usage examples are provided

### References Directory
Check if skill references documentation:
```bash
Grep: pattern="references/" path="skills/[category]/[skill-name]/SKILL.md" output_mode="content"
Glob: pattern="skills/[category]/[skill-name]/references/*"
```

Verify:
- References mentioned exist
- Large documents (>5k words) use grep patterns for selective loading
- References are up-to-date with current practices

### Assets Directory
Check if skill references templates or output files:
```bash
Grep: pattern="assets/" path="skills/[category]/[skill-name]/SKILL.md" output_mode="content"
Glob: pattern="skills/[category]/[skill-name]/assets/*"
```

Verify:
- Assets mentioned exist
- Templates are properly formatted
- File names are descriptive

## Step 6: Generate Improvement Report

To create a comprehensive review report, use the template from `assets/review-report-template.md`:

```markdown
# Skill Review Report: [Skill Name]

**Skill Path:** skills/[category]/[skill-name]
**Review Date:** [Date]
**Reviewer:** Claude Code (skill-reviewer-and-enhancer)

## Overall Assessment

**Grade:** [A/B/C/D/F]
**Status:** [Production Ready / Needs Minor Fixes / Needs Major Revision]

## Structural Compliance

### Frontmatter
- [x] Name present and valid
- [x] Description present and well-formatted
- [ ] allowed-tools specified (if applicable)

### Naming Convention
- [x] Uses hyphen-case
- [ ] Issue: Contains uppercase/invalid characters

### Description Quality
- [x] Third-person voice
- [x] Includes trigger terms
- [x] Under 1024 characters
- [ ] Issue: Missing WHEN to use explanation

## Instruction Style

### Imperative Form
- [x] Uses verb-first instructions
- [ ] Issue: Found 5 instances of "you should" (lines: 45, 67, 89, 102, 134)

**Recommended Changes:**
```
Line 45: "You should use the script" → "Use the script"
Line 67: "You can generate forms" → "Generate forms" or "To generate forms"
```

## Domain-Specific Best Practices

### [Domain] Patterns
- [x] Uses current framework version
- [x] Follows recommended patterns
- [ ] Issue: References deprecated API (NextAuth v3, should use v5)
- [ ] Issue: Uses Pages Router patterns (should use App Router)

**Recommended Updates:**
[Specific suggestions for domain improvements]

## Resource Completeness

### Scripts
- [ ] Script `generate_form.py` mentioned but not found
- [x] Script `validate_s

Related in AI Agents