claude-skills-kit
AGENTS.md0 starsChanged 6 months agoMITView on GitHub
本仓库提供通用 Claude/Codex 配置，可复制到新项目中作为 AI 协作底座。
In this repository8 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- claude-config-maintainerSkill
- coderSkill
- engineer-coder-orchestratorSkill
- engineerSkill
- github-repo-standardsSkill
- learning-blogSkill
- unity6-projectSkill
The file
Files
AI 代理交接说明
本仓库提供通用 Claude/Codex 配置，可复制到新项目中作为 AI 协作底座。
基本原则
- 使用中文和用户沟通，代码标识符保持英文。
- 开始前先读项目根目录说明和当前任务相关文件。
- 每次只推进一个可验证的小目标。
- 先明确验收标准，再实现，再验证。
- 不提交密钥、Token、缓存、构建产物、用户本地设置或大型二进制输出。
推荐角色
engineer: 负责需求分析、架构设计、任务拆解和风险识别。coder: 负责按设计实现代码、补测试、修 bug 和运行验证。- 默认代理: 适合小任务、文档整理、简单修复和最终集成。
上下文读取顺序
CLAUDE.mdREADME.md.claude/rules/- 当前任务相关源码、测试和配置
- 必要时再读
docs/
输出要求
完成任务后说明：
- 改了哪些文件。
- 为什么这样改。
- 做了哪些验证。
- 还剩哪些风险或需要用户确认的点。
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.