your-skill-name
Skill1 starsChanged 38 days agoMITView on GitHub
Use when <用户会怎么说 / 什么场景>。产出 <交付物形态>。<可选：也用于 <第二个场景>。>不用于：<明确排除的场景，避免抢别的 skill 的活>。
49 other projects use a version of this.
Adopted by
Most recently taken up by
- findscripter/everything-skillstheir own version, first seen Nov 2, 2026
- artherahq/skillstheir own version, first seen Oct 31, 2026
- artheras/skillstheir own version, first seen Oct 31, 2026
- grafana/skillstheir own version, first seen Oct 27, 2026
- osamabinjannat/remote-hiring-skillstheir own version, first seen Oct 25, 2026
- Galvarcus/claude-skillstheir own version, first seen Oct 25, 2026
Other versions49 projects use a version of this.
Word for word · 2
- 123ccw/anime-collection-book★ 1100% same
- 123ccw/fanbook★ 1100% same
Edited · 0
None found.
Wrote their own version · 47
- Fullive-AI/Anima★ 1ksame name
- Affitor/affiliate-skills★ 757same name
- grafana/skills★ 302same name
- openocta/openocta_skills★ 166same name
- trustwallet/tw-agent-skills★ 111same name
- frankxai/claude-skills-library★ 47same name
- inbharatai/claude-skills★ 33same name
- lionelsimai/claude-skills-collection★ 26same name
- findscripter/everything-skills★ 8same name
- TheArchitectit/awesome-cline-skills★ 8same name
37 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
Files
<Skill 名>
一句话：给谁、解决什么、产出什么。别写功能清单，写"没有它会怎样"。
先读哪份文档（按需，别一次全读）
| 你现在要做的事 | 读这个 |
| <第一次要写的输入文件> | references/<字段说明>.md + assets/<模板>.json |
| <跑命令 / 构建> | references/build.md |
| <遇到报错> | references/pipeline.md（完整踩坑清单） |
| <交付前把关> | references/compliance.md |
执行流程（勿跳步）
- ⓪ 自检：
npm run doctor（环境齐全再开工） - ① 输入：<用户要提供什么>（<并发/批量建议>）
- ② 构建：
npm run pipeline - ③ 验收：
npm run audit→npm run check→ 人工目检（<看什么>） - ④ 交付：
npm run pack
④ 的目检是硬要求：脚本断言替代不了看图/看版式。
质检铁律（不可省略）
- 不编造：查不到就写"未核实"
- 关键产物必须亲眼看（<列出哪些>）
- 改<文案/数据>后必须重跑<哪一步>
- <这个领域最贵的那条教训>
环境依赖
- Node ≥20 +
npm i；<其他依赖与安装方式> - agent 能力要求：文件读写 + Shell + <联网/读图>
- 拿不准先跑
npm run doctor
详细版
references/ 下：<文档清单，一句话各是什么>。
<!--
写 skill 的四条经验（来自本仓库 fanbook 与高星 skill 的对照）：
1. **入口 ≤ 10 KB**：SKILL.md 只放「执行流程 + 质检铁律 + 最硬的坑位 + 路由表 + 环境依赖」，
细节全部下沉到 references/，让 agent 按需读。20 KB 的入口意味着每次触发都要全量吃进上下文。
2. **description 是触发词，不是简介**：写清「用户会怎么说话」和「不用于什么」——
撞车的 skill 会互相抢触发，抢输的那个等于不存在。
3. **同一份内容只放一处**：agent 的 skill 目录常常有多个（如 DSH 会读 ~/.dsh/skills 与 ~/.agents/skills），
同一个 skill 放两处会重复加载、互相抢触发。
4. **把"每次都会错"的环节变成断言或默认行为**：不要写"请注意检查"，要写成 check/audit 的一条断言、
或构建脚本的默认输出。写在文档里的纪律会被忽略，写成断言的不会。
-->Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.