scaffold-skills / light
CLAUDE.md2 starsChanged 12 days agoMITView on GitHub
父级：../SKILL.md。轨道怎么选、什么算过、硬约束，都在父级；这里只回答"轻原型这一路走到哪一步"。 判断后说一句"我判断这是 [规模]，流程深度为 [描述]，对吗"，不替用户默认。 用户随时可以说"跳过设计直接写""先写代码后补文档""回到需求改范围""只做集成测试"。跳转不需要回退上游，也不因此记偏离——轨道本身允许非线性。 出现下面任一条，轻原型轨道到顶了，切 ../SKILL.md 的重工程轨道，并把已写下的结论搬过去：
In this repository15 other files it gives its agents.
- ai-code-reviewSkill
- api-design-reviewSkill
- architecture-support-briefSkill
- class-design-reviewSkill
- comment-policySkill
- cpp-exemplarsSkill
- error-code-classificationSkill
- essential-tool-installSkill
- isoSkill
- notion-diagramSkill
- reportSkill
- researchSkill
- incident-reviewSkill
- routerSkill
- test-naming-and-structureSkill
The file
Files
Light —— 轻原型轨道的入口
父级：../SKILL.md。轨道怎么选、什么算过、硬约束，都在父级；这里只回答"轻原型这一路走到哪一步"。
按规模定深度
| 规模 | 判断信号 | 走哪几步 |
| 原型 | "验证""Demo""试试""跑通"，预计 < 1 周 | 问 discover 的核心问题 → 直接实现 |
| 小工具 | "脚本""CLI""工具""转换"，单模块，1-4 周 | discover → implement |
| 业务系统 | "平台""服务""系统"，多模块，> 1 月 | discover → design → implement → deliver |
判断后说一句"我判断这是 [规模]，流程深度为 [描述]，对吗"，不替用户默认。
文件索引
| 文件 | 内容 | 何时读 |
| discover.md | 问题定义 + 范围界定 | 开始 / 需求还没想清楚 |
| design.md | 架构草图（可跳过） | 多模块需要先定边界 |
| implement.md | 实现阶段的产物与确认点 | 写代码 |
| deliver.md | 测试与交付 | "测试""上线""交付" |
| lang/cpp.md · go.md · python.md | 语言速查 | 动手前的语法与惯例对照 |
可跳转
用户随时可以说"跳过设计直接写""先写代码后补文档""回到需求改范围""只做集成测试"。跳转不需要回退上游，也不因此记偏离——轨道本身允许非线性。
什么时候必须切回重工程
出现下面任一条，轻原型轨道到顶了，切 ../SKILL.md 的重工程轨道，并把已写下的结论搬过去：
- 出现第二个子系统，或两个模块要共享一份契约
- 需要向外部交付接口或文档
- 改动会破坏已上线行为
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.