
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
在项目根目录生成 AGENTS.md 文件和 docs/ 知识库骨架,建立 agent-first 仓库的文档治理体系。手动触发,检查是否存在后写入模板。
在项目根目录生成 AGENTS.md 文件和 docs/ 知识库骨架,建立 agent-first 仓库的文档治理体系。手动触发,检查是否存在后写入模板。
在项目根目录生成 CLAUDE.md 文件和 .claude/ 配置骨架,建立 Claude Code 项目级指令体系。手动触发,检查是否存在后写入模板。
Use when user mentions '/lesson', '记录经验', '铁律', or wants to capture lessons learned. Automatically extracts insights from conversation and writes them to project's MEMORY.md. Also triggers when agent makes mistakes or discovers important patterns.
Use when creating a minimal agent prompt for small models, when user wants to generate a lightweight agent with strict tool/skill limitations, or when asked to '创建 agent', '写一个 agent prompt', '生成 agent 配置', 'sop agent'
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
Describe what this skill does and when Claude/OpenCode should use it. Be specific about trigger phrases and scenarios. Write it 'pushy' — err on the side of triggering too often rather than too little.
在项目根目录生成 CLAUDE.md 文件和 .claude/ 配置骨架,采用 DDD 架构模式,包含标准化架构设计文档和代码模板。手动触发,检查是否存在后写入模板。