{{skill-name}}
Skill2 starsChanged 2 months agoMITView on GitHub
{{一句话用途（what）}}。当 {{触发时机（when）}} 时使用；覆盖 {{范围边界与检查顺序}}。
2 other projects use a version of this.
Adopted by
Most recently taken up by
- mercmorandi/agents-kittheir own version, first seen Oct 25, 2026
- ellmos-ai/skillstheir own version, first seen Sep 11, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- ellmos-ai/skills★ 4same name
- mercmorandi/agents-kit★ 0same name
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.
In this repository5 other files it gives its agents.
- code-reviewSkill
- project-initializationSkill
- task-planningSkill
- verificationSkill
- feature-developmentSkill
The file
Files
{{Skill 展示名}}
<!-- 使用方式：
1. 复制本文件到 skills/{{分类}}/{{skill-name}}/SKILL.md（目录名 = frontmatter 的 name），
并把首行 $schema 注释的相对路径加深一级（../../ → ../../../）；
2. 逐节替换 {{占位}}、删除全部 HTML 注释提示（含本条）；
3. 章节顺序固定不增删（docs/skill-authoring.md；Common Rationalizations 可按复杂度判据省略）；
全文控制在 ~150 行内（含 frontmatter、不含注释提示），超出的资料下沉 references/。 -->Purpose
<!-- 一句话：这个 skill 解决什么问题、产出的结果是什么。不写背景故事，不写使用动机。 -->{{解决什么问题，产出什么结果}}
When to Use
<!-- 触发场景清单：与 description 的触发线索一致，逐条可被 Agent 比对；每条以「当…」开头。 -->- 当 {{场景 1}} 时
- 当 {{场景 2}} 时
When NOT to Use
<!-- 相邻但不该用本 skill 的场景，并指明应改用哪个 skill / rule / upstream，防止误触发。 -->- {{相邻场景}}：改用 {{对应 skill / rule}}
Inputs
<!-- 需要哪些上下文（文件 / 参数 / 环境），以及缺失时怎么处理：询问、跳过还是报错。 -->- {{必需输入}}：缺失时 {{处理方式}}
Workflow
<!-- 工作流固定四节：Inspect / Plan / Implement / Verify。写可执行动作与判断标准，不写原则口号。
四节是通用脚手架，非编码型 skill 同样适用：Implement = 执行本 skill 的主要动作
（如 verification 的 Implement = 运行 typecheck / lint / test / build 检查阶梯），不限于写代码。 -->1. Inspect
<!-- 动手前看什么：相关文件、现状、已有实现、约束条件。 -->- {{检查项}}
2. Plan
<!-- 决定怎么做：改动范围、顺序、影响面；发现歧义先问，不自行假设。 -->- {{计划项}}
3. Implement
<!-- 执行本 skill 的主要动作：编码 skill 写最小修改与每步完成标准；非编码 skill 列动作序列与判断标准。 -->- {{执行项}}
4. Verify
<!-- 工作流内的验证步骤：本 skill 自身要求的检查、工具与执行顺序。 -->- {{验证项}}
Rules
<!-- 硬约束：执行本工作流时必须保留什么、禁止什么。写可判定的规则，不写形容词。 -->- 必须 {{约束}}
- 禁止 {{约束}}
Common Failure Modes
<!-- 常见错误，写「症状 → 纠正动作」。复杂 skill 必写；简单 skill 至少留一行。 -->| 症状 | 纠正 |
| {{错误现象}} | {{纠正动作}} |
Common Rationalizations
<!-- 反合理化表格：复杂 skill（多步骤 且 有明确验证门槛）必含；单步或无验证门槛可整节省略。
经典种子（verification 类 skill 可直接搬用）：
| Agent says | Correct response |
| --- | --- |
| "这个改动很简单，不需要测试" | 运行最小相关测试 |
| "以后再补测试" | 当前任务完成前验证 |
| "我已经看过代码了" | 提供具体文件 / 证据 |
| "应该不会影响其他地方" | 执行受影响范围的验证 | -->| Agent says | Correct response |
| "{{跳步借口}}" | {{正确响应}} |
Verification
<!-- Agent 怎么证明自己完成了：可执行命令 + 具体证据（文件 / 路径 / 检查项）。
不接受「看起来没问题」；按任务性质从 typecheck / lint / test / build / 浏览器验证中选并写明顺序。 -->- {{命令}} → {{证据}}
Exit Criteria
<!-- 可逐条勾选的完成判据，全部满足才允许报告完成；与 Verification 的证据一一对应。 -->- {{判据 1}}
- {{判据 2}}
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.