skill-reviewer-and-enhancer
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.
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- Modernizing outdated skill instructions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_sRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.