MCP HubMCP Hub
返回技能列表

[{"TODO":"lowercase-hyphen-case-name"}]

jezweb
更新于 Today
85 次查看
33
4
33
在 GitHub 上查看
wordai

关于

This skill provides a template for creating new Claude Skills, with placeholders for descriptions, use cases, and technical specifications. It should be used when developers need to structure and document custom skills for Claude Code with clear implementation guidelines. The template includes sections for setup instructions, dependencies, and configuration examples.

快速安装

Claude Code

推荐
主要方式
npx skills add jezweb/claude-skills
插件命令备选方式
/plugin add https://github.com/jezweb/claude-skills
Git 克隆备选方式
git clone https://github.com/jezweb/claude-skills.git ~/.claude/skills/[{"TODO":"lowercase-hyphen-case-name"}]

在 Claude Code 中复制并粘贴此命令以安装该技能

技能文档

[TODO: Skill Display Name]

Status: [TODO: Production Ready / Beta / Experimental] Last Updated: [TODO: YYYY-MM-DD] Dependencies: [TODO: List prerequisite skills or tools, or write "None"] Latest Versions: [TODO: package@version, package2@version]


Quick Start ([TODO: X] Minutes)

1. [TODO: First Major Step]

[TODO: Provide clear, actionable instructions]

# [TODO: Example command]

Why this matters:

  • [TODO: Explain the reasoning]
  • [TODO: Key benefits]

2. [TODO: Second Major Step]

[TODO: Continue with step-by-step instructions]

// [TODO: Code example with comments]

CRITICAL:

  • [TODO: Important notes that prevent common mistakes]

3. [TODO: Third Major Step]

[TODO: Keep going until setup is complete]


The [TODO: Number]-Step Setup Process

Step 1: [TODO: First Step Name]

[TODO: Detailed instructions]

[TODO: Code examples, configurations, etc.]

Key Points:

  • [TODO: Important details]
  • [TODO: What to avoid]

Step 2: [TODO: Second Step Name]

[TODO: Continue with detailed steps]


Critical Rules

Always Do

✅ [TODO: Best practice #1] ✅ [TODO: Best practice #2] ✅ [TODO: Best practice #3]

Never Do

❌ [TODO: Anti-pattern #1] ❌ [TODO: Anti-pattern #2] ❌ [TODO: Anti-pattern #3]


Known Issues Prevention

This skill prevents [TODO: number] documented issues:

Issue #1: [TODO: Issue Name]

Error: [TODO: Exact error message or description] Source: [TODO: GitHub issue link, Stack Overflow link, or official docs] Why It Happens: [TODO: Root cause] Prevention: [TODO: How this skill fixes it]

Issue #2: [TODO: Issue Name]

[TODO: Repeat pattern for each issue]


Configuration Files Reference

[TODO: config-file.ext] (Full Example)

[TODO: Complete, working configuration file]

Why these settings:

  • [TODO: Explain key configuration decisions]

Common Patterns

Pattern 1: [TODO: Pattern Name]

// [TODO: Code example]

When to use: [TODO: Specific scenarios]

Pattern 2: [TODO: Pattern Name]

[TODO: More examples]


Using Bundled Resources

[TODO: Only include this section if you have scripts/, references/, or assets/]

Scripts (scripts/)

[TODO: List and explain any executable scripts]

Example Usage:

./scripts/[TODO: script-name].sh

References (references/)

[TODO: List documentation files that Claude can load when needed]

  • references/[TODO: filename].md - [TODO: What it contains]

When Claude should load these: [TODO: Specific scenarios]

Assets (assets/)

[TODO: List template files, images, etc. that get used in output]

  • assets/[TODO: filename] - [TODO: What it's for]

Advanced Topics

[TODO: Advanced Topic 1]

[TODO: Deep dive into complex scenarios]

[TODO: Advanced Topic 2]

[TODO: Additional advanced content]


Dependencies

Required:

  • [TODO: package@version] - [TODO: What it's used for]
  • [TODO: package@version] - [TODO: What it's used for]

Optional:

  • [TODO: package@version] - [TODO: What it's used for]

Official Documentation

  • [TODO: Technology Name]: [TODO: Official docs URL]
  • [TODO: Related Tool]: [TODO: Official docs URL]
  • Context7 Library ID: [TODO: /org/project if applicable]

Package Versions (Verified [TODO: YYYY-MM-DD])

{
  "dependencies": {
    "[TODO: package]": "^[TODO: version]"
  },
  "devDependencies": {
    "[TODO: package]": "^[TODO: version]"
  }
}

Production Example

[TODO: Optional - provide evidence of production usage]

This skill is based on [TODO: project name]:

  • Live: [TODO: URL if applicable]
  • Build Time: [TODO: time]
  • Errors: 0 (all [TODO: number] known issues prevented)
  • Validation: ✅ [TODO: What was tested]

Troubleshooting

Problem: [TODO: Common issue]

Solution: [TODO: How to fix]

Problem: [TODO: Another issue]

Solution: [TODO: How to fix]


Complete Setup Checklist

Use this checklist to verify your setup:

  • [TODO: First verification step]
  • [TODO: Second verification step]
  • [TODO: Third verification step]
  • [TODO: All package versions correct]
  • [TODO: Dev server runs without errors]
  • [TODO: Production build succeeds]
  • [TODO: Deployed successfully (if applicable)]

Questions? Issues?

  1. Check [TODO: reference/common-issues.md] if you created one
  2. Verify all steps in the setup process
  3. Check official docs: [TODO: URL]
  4. Ensure [TODO: critical requirement] is configured

INSTRUCTIONS FOR USING THIS TEMPLATE

  1. Search for [TODO:** - Replace every [TODO: ...] with actual content
  2. Delete this section when done
  3. Remove sections that don't apply to your skill
  4. Add sections as needed for your specific use case
  5. Test everything before committing
  6. Verify against ONE_PAGE_CHECKLIST.md

Key Reminders:

  • Use third-person for description: "This skill provides..." not "This skill helps you..."
  • Write in imperative form: "To do X, run Y" not "You should run Y to do X"
  • Include actual error messages and GitHub issue links
  • Document all package versions with verification date
  • Test all code examples
  • Remove all [TODO:] markers before committing

Example Good Description:

description: |
  This skill provides comprehensive knowledge for building React applications with
  Vite and TypeScript. It should be used when scaffolding new Vite projects,
  configuring TypeScript settings, or encountering HMR issues.

  Keywords: vite, react, typescript, hmr, vite config, react setup

Example Bad Description:

description: "A skill for Vite and React"  # ❌ Too vague, no keywords

Ready to build? Fill in all [TODO:] markers and create an amazing skill!

GitHub 仓库

jezweb/claude-skills
路径: templates/skill-skeleton
aiautomationclaude-codeclaude-skillscloudflarereact

相关推荐技能

content-collections

Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。

查看技能

himalaya-email-manager

通信

这个Claude Skill通过Himalaya CLI工具提供IMAP邮箱管理功能,支持使用自然语言查询搜索、总结和删除邮件。它特别适合开发者快速获取每日邮件摘要和执行批量邮件操作,所有功能都通过Python脚本封装,简化了环境配置和命令执行流程。关键特性包括支持富文本表格输出、多文件夹分类处理,以及完整的Unicode字符和表情符号显示。

查看技能

sglang

SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。

查看技能

evaluating-llms-harness

测试

该Skill通过60+个学术基准测试(如MMLU、GSM8K等)评估大语言模型质量,适用于模型对比、学术研究及训练进度追踪。它支持HuggingFace、vLLM和API接口,被EleutherAI等行业领先机构广泛采用。开发者可通过简单命令行快速对模型进行多任务批量评估。

查看技能