技能评审
skill-reviewer
by daymade
按官方最佳实践审查并优化 Claude Code Skill，支持自检、评审他人 Skill 仓库，以及 fork 后自动改进并提交 PR，适合发布前验收和开源贡献。
对照官方最佳实践快速体检并优化 Claude Code 技能，既能自查代审，也能自动提 PR，特别适合高效维护开源技能库。
安装
claude skill add --url github.com/daymade/claude-code-skills/tree/main/skill-reviewer文档
Skill Reviewer
Review and improve Claude Code skills against official best practices.
Setup (Auto-Install Dependencies)
Before using this skill, ensure skill-creator is installed for automated validation.
Auto-install sequence:
# 1. Check if skill-creator exists
SKILL_CREATOR=$(find ~/.claude/plugins/cache -name "skill-creator" -type d 2>/dev/null | head -1)
# 2. If not found, install it
if [ -z "$SKILL_CREATOR" ]; then
claude plugin marketplace add https://github.com/daymade/claude-code-skills
claude plugin install skill-creator@daymade-skills
SKILL_CREATOR=$(find ~/.claude/plugins/cache -name "skill-creator" -type d 2>/dev/null | head -1)
fi
echo "skill-creator location: $SKILL_CREATOR"
Three Modes
Mode 1: Self-Review
Check your own skill before publishing.
Automated validation (run after setup):
# Quick validation
python3 "$SKILL_CREATOR"/*/quick_validate.py <target-skill>
# Security scan
python3 "$SKILL_CREATOR"/*/security_scan.py <target-skill> --verbose
Manual evaluation: See references/evaluation_checklist.md.
Mode 2: External Review
Evaluate someone else's skill repository.
Review Workflow:
- [ ] Clone repository to /tmp/
- [ ] Read ALL documentation first
- [ ] Identify author's intent
- [ ] Run evaluation checklist
- [ ] Generate improvement report
Mode 3: Auto-PR
Fork, improve, and submit PR to external skill repository.
Auto-PR Workflow:
- [ ] Fork repository (gh repo fork)
- [ ] Create feature branch
- [ ] Apply additive improvements only
- [ ] Self-review: respect check passed?
- [ ] Create PR with detailed explanation
Evaluation Checklist (Quick)
| Category | Check | Status |
|---|---|---|
| Frontmatter | name present? | |
| description present? | ||
| description in third-person? | ||
| includes trigger conditions? | ||
| Instructions | imperative form? | |
| under 500 lines? | ||
| workflow pattern? | ||
| Resources | no hardcoded paths? | |
| scripts have error handling? |
Full checklist: references/evaluation_checklist.md
Core Principle: Additive Only
When improving external skills, NEVER:
- Delete existing files
- Remove functionality
- Change primary language
- Rename components
ALWAYS:
- Add new capabilities
- Preserve original content
- Explain every change
❌ "Removed metadata.json (non-standard)"
✅ "Added marketplace.json (metadata.json preserved)"
❌ "Rewrote README in English"
✅ "Added README.en.md (Chinese preserved as default)"
Common Issues & Fixes
Issue: Description Not Third-Person
# Before
description: Browse YouTube videos and summarize them.
# After
description: Browses YouTube videos and generates summaries. Use when...
Issue: Missing Trigger Conditions
# Before
description: Processes PDF files.
# After
description: Extracts text from PDFs. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.
Issue: No Workflow Pattern
Add checklist for complex tasks:
## Workflow
Copy this checklist:
\`\`\`
Task Progress:
- [ ] Step 1: ...
- [ ] Step 2: ...
\`\`\`
Issue: Missing Marketplace Support
mkdir -p .claude-plugin
# Create marketplace.json from template
See references/marketplace_template.json.
PR Guidelines
When submitting PRs to external repos:
Tone
❌ "Your skill doesn't follow best practices"
✅ "This PR aligns with best practices for better discoverability"
❌ "Fixed the incorrect description"
✅ "Improved description with trigger conditions"
Required Sections
- Summary - What this PR does
- What's NOT Changed - Show respect for original
- Rationale - Why each change helps
- Test Plan - How to verify
Template: references/pr_template.md
Self-Review Checklist
Before submitting any PR:
Respect Check:
- [ ] No files deleted?
- [ ] No functionality removed?
- [ ] Original language preserved?
- [ ] Author's design decisions respected?
- [ ] All changes are additive?
- [ ] PR explains the "why"?
References
references/evaluation_checklist.md- Full evaluation checklistreferences/pr_template.md- PR description templatereferences/marketplace_template.json- marketplace.json template- Best practices: https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices
相关 Skills
网页构建器
by anthropics
面向复杂 claude.ai HTML artifact 开发，快速初始化 React + Tailwind CSS + shadcn/ui 项目并打包为单文件 HTML，适合需要状态管理、路由或多组件交互的页面。
✎ 在 claude.ai 里做复杂网页 Artifact 很省心，多组件、状态和路由都能顺手搭起来，React、Tailwind 与 shadcn/ui 组合效率高、成品也更精致。
前端设计
by anthropics
面向组件、页面、海报和 Web 应用开发，按鲜明视觉方向生成可直接落地的前端代码与高质感 UI，适合做 landing page、Dashboard 或美化现有界面，避开千篇一律的 AI 审美。
✎ 想把页面做得既能上线又有设计感，就用前端设计：组件到整站都能产出，难得的是能避开千篇一律的 AI 味。
网页应用测试
by anthropics
用 Playwright 为本地 Web 应用编写自动化测试，支持启动开发服务器、校验前端交互、排查 UI 异常、抓取截图与浏览器日志，适合调试动态页面和回归验证。
✎ 借助 Playwright 一站式验证本地 Web 应用前端功能，调 UI 时还能同步查看日志和截图，定位问题更快。
相关 MCP 服务
GitHub
编辑精选by GitHub
GitHub 是 MCP 官方参考服务器，让 Claude 直接读写你的代码仓库和 Issues。
✎ 这个参考服务器解决了开发者想让 AI 安全访问 GitHub 数据的问题，适合需要自动化代码审查或 Issue 管理的团队。但注意它只是参考实现，生产环境得自己加固安全。
Context7 文档查询
编辑精选by Context7
Context7 是实时拉取最新文档和代码示例的智能助手，让你告别过时资料。
✎ 它能解决开发者查找文档时信息滞后的问题，特别适合快速上手新库或跟进更新。不过，依赖外部源可能导致偶尔的数据延迟，建议结合官方文档使用。
by tldraw
tldraw 是让 AI 助手直接在无限画布上绘图和协作的 MCP 服务器。
✎ 这解决了 AI 只能输出文本、无法视觉化协作的痛点——想象让 Claude 帮你画流程图或白板讨论。最适合需要快速原型设计或头脑风暴的开发者。不过，目前它只是个基础连接器，你得自己搭建画布应用才能发挥全部潜力。