Agent skill
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/brainstorming-pianzhu-my-claude-skills
SKILL.md
将想法转化为设计与规格说明
概述
通过自然的协作对话,帮助把想法完善为完整的设计与规格说明。
先理解当前项目上下文,然后一次只问一个问题来逐步细化想法。当你理解了要构建的内容后,将设计按小节呈现(每节约 200–300 个单词),并在每一节结束后确认到目前为止是否符合预期。
流程
理解想法:
- 先查看当前项目状态(代码文件、文档、最近的提交)
- 一次只问一个问题,逐步细化想法
- 能用选择题就优先用选择题;必要时也可以开放式提问
- 每条消息只问一个问题;如果某个主题需要更深入,拆成多个问题
- 重点理解:目标、约束、成功标准
探索方案:
- 提出 2–3 种不同方案,并说明取舍
- 用对话式方式呈现选项,同时给出你的推荐与理由
- 先给出你推荐的方案,再解释原因
呈现设计:
- 当你确信已经理解要构建的内容时,开始呈现设计
- 将设计拆成每节约 200–300 个单词的小节
- 每呈现一节后,询问目前为止是否符合预期
- 覆盖:架构、组件、数据流、错误处理、测试
- 如果有任何不清晰之处,随时回退并澄清
关键原则
- 一次只问一个问题 —— 不要用多个问题同时轰炸对方
- 优先选择题 —— 在可行时,比开放式更容易回答
- 坚决践行“你不会需要它”原则 —— 从所有设计中删去不必要的功能
- 探索替代方案 —— 在定案前总是先给出 2–3 种方案
- 增量验证 —— 分段呈现设计,并逐段确认
- 保持灵活 —— 一旦出现不清晰之处,就回退并澄清
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?