skill-auditor
Audits and validates skill definitions for quality, completeness, and best practices. Use when reviewing existing skills for proper formatting, evaluating if skills should be split into sub-skills, or ensuring skills follow established conventions.
Best use case
skill-auditor is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. Audits and validates skill definitions for quality, completeness, and best practices. Use when reviewing existing skills for proper formatting, evaluating if skills should be split into sub-skills, or ensuring skills follow established conventions.
Audits and validates skill definitions for quality, completeness, and best practices. Use when reviewing existing skills for proper formatting, evaluating if skills should be split into sub-skills, or ensuring skills follow established conventions.
Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.
Practical example
Example input
Use the "skill-auditor" skill to help with this workflow task. Context: Audits and validates skill definitions for quality, completeness, and best practices. Use when reviewing existing skills for proper formatting, evaluating if skills should be split into sub-skills, or ensuring skills follow established conventions.
Example output
A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.
When to use this skill
- Use this skill when you want a reusable workflow rather than writing the same prompt again and again.
When not to use this skill
- Do not use this when you only need a one-off answer and do not need a reusable workflow.
- Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/skill-auditor/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How skill-auditor Compares
| Feature / Agent | skill-auditor | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Audits and validates skill definitions for quality, completeness, and best practices. Use when reviewing existing skills for proper formatting, evaluating if skills should be split into sub-skills, or ensuring skills follow established conventions.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Skill Auditor This skill audits other skills for quality, completeness, and adherence to best practices. It validates skill structure, evaluates content quality, and recommends improvements or decomposition into sub-skills. ## When to Use This skill should be triggered when: - Reviewing existing skills for quality issues - Checking if a skill follows proper formatting conventions - Evaluating whether a skill should be divided into sub-skills - Performing bulk audits across all project skills - Validating skills before packaging or distribution ## Workflow ### Step 1: Discover Skills List all skills in the `.claude/skills/` directory: ```bash ls -la .claude/skills/ ``` For each skill directory, verify it contains the required `SKILL.md` file. ### Step 2: Run Automated Validation Execute the audit script to check structural requirements: ```bash python .claude/skills/skill-auditor/scripts/audit_skills.py .claude/skills/ ``` The script validates: - YAML frontmatter presence and required fields - Description quality (length, specificity) - Word count limits (<5000 words recommended) - Unfinished placeholder detection - Empty directory warnings - Script executability ### Step 3: Manual Quality Review For each skill, evaluate against these criteria: **Frontmatter Quality:** - `name`: Uses hyphens, is descriptive - `description`: 50+ characters, specific about triggers, no placeholders **Content Structure:** - Clear "When to Use" section with specific triggers - Workflow with actionable steps - Bundled resources properly documented **Decomposition Analysis:** - Evaluate if skill handles >3 distinct concerns - Check if skill exceeds 5000 words - Identify reusable components that could be shared ### Step 4: Generate Audit Report Produce a structured report for each skill: ``` ## Skill: [name] ### Validation Results - Frontmatter: PASS/FAIL - Structure: PASS/FAIL - Word Count: X words (PASS/WARNING/FAIL) - Unfinished Placeholders: X found ### Quality Score: X/10 ### Recommendations 1. [Specific improvement] 2. [Another improvement] ### Decomposition Analysis - Should split: YES/NO - Reason: [explanation] - Suggested sub-skills: [list if applicable] ``` ### Step 5: Apply Fixes For automated fixes, use the audit script with `--fix` flag: ```bash python .claude/skills/skill-auditor/scripts/audit_skills.py .claude/skills/ --fix ``` For manual improvements, edit SKILL.md files directly following recommendations. ## Audit Criteria Reference See `references/audit-criteria.md` for detailed scoring rubrics and decomposition guidelines. ## Bundled Resources ### Scripts - `scripts/audit_skills.py` - Automated validation and reporting script ### References - `references/audit-criteria.md` - Detailed audit criteria and scoring rubrics
Related Skills
seo-content-auditor
Analyzes provided content for quality, E-E-A-T signals, and SEO best practices. Scores content and provides improvement recommendations based on established guidelines. Use PROACTIVELY for content review.
security-auditor
Expert security auditor specializing in DevSecOps, comprehensive cybersecurity, and compliance frameworks. Masters vulnerability assessment, threat modeling, secure authentication (OAuth2/OIDC), OWASP standards, cloud security, and security automation. Handles DevSecOps integration, compliance (GDPR/HIPAA/SOC2), and incident response. Use PROACTIVELY for security audits, DevSecOps, or compliance implementation.
dependency-auditor
Automated security auditing of project dependencies to identify known vulnerabilities.
accessibility-auditor
Reviews UI components for WCAG compliance, ARIA attributes, keyboard navigation, and screen reader support. Use when building frontend components or user requests accessibility improvements.
azure-quotas
Check/manage Azure quotas and usage across providers. For deployment planning, capacity validation, region selection. WHEN: "check quotas", "service limits", "current usage", "request quota increase", "quota exceeded", "validate capacity", "regional availability", "provisioning limits", "vCPU limit", "how many vCPUs available in my subscription".
raindrop-io
Manage Raindrop.io bookmarks with AI assistance. Save and organize bookmarks, search your collection, manage reading lists, and organize research materials. Use when working with bookmarks, web research, reading lists, or when user mentions Raindrop.io.
zlibrary-to-notebooklm
自动从 Z-Library 下载书籍并上传到 Google NotebookLM。支持 PDF/EPUB 格式，自动转换，一键创建知识库。
discover-skills
当你发现当前可用的技能都不够合适（或用户明确要求你寻找技能）时使用。本技能会基于任务目标和约束，给出一份精简的候选技能清单，帮助你选出最适配当前任务的技能。
web-performance-seo
Fix PageSpeed Insights/Lighthouse accessibility "!" errors caused by contrast audit failures (CSS filters, OKLCH/OKLAB, low opacity, gradient text, image backgrounds). Use for accessibility-driven SEO/performance debugging and remediation.
project-to-obsidian
将代码项目转换为 Obsidian 知识库。当用户提到 obsidian、项目文档、知识库、分析项目、转换项目 时激活。 【激活后必须执行】： 1. 先完整阅读本 SKILL.md 文件 2. 理解 AI 写入规则（默认到 00_Inbox/AI/、追加式、统一 Schema） 3. 执行 STEP 0: 使用 AskUserQuestion 询问用户确认 4. 用户确认后才开始 STEP 1 项目扫描 5. 严格按 STEP 0 → 1 → 2 → 3 → 4 顺序执行 【禁止行为】： - 禁止不读 SKILL.md 就开始分析项目 - 禁止跳过 STEP 0 用户确认 - 禁止直接在 30_Resources 创建（先到 00_Inbox/AI/） - 禁止自作主张决定输出位置
obsidian-helper
Obsidian 智能笔记助手。当用户提到 obsidian、日记、笔记、知识库、capture、review 时激活。 【激活后必须执行】： 1. 先完整阅读本 SKILL.md 文件 2. 理解 AI 写入三条硬规矩（00_Inbox/AI/、追加式、白名单字段） 3. 按 STEP 0 → STEP 1 → ... 顺序执行 4. 不要跳过任何步骤，不要自作主张 【禁止行为】： - 禁止不读 SKILL.md 就开始工作 - 禁止跳过用户确认步骤 - 禁止在非 00_Inbox/AI/ 位置创建新笔记（除非用户明确指定）
internationalizing-websites
Adds multi-language support to Next.js websites with proper SEO configuration including hreflang tags, localized sitemaps, and language-specific content. Use when adding new languages, setting up i18n, optimizing for international SEO, or when user mentions localization, translation, multi-language, or specific languages like Japanese, Korean, Chinese.