← Back to Skills Marketplace
112
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install est321
Description
在任何创造性工作之前必须使用 - 创建功能、构建组件、添加新功能或修改行为。通过协作对话探索用户意图、需求和设计。
README (SKILL.md)
\r \r
Brainstorming - 将想法转化为设计\r
\r
概述\r
\r 通过自然的协作对话，帮助将模糊的想法转化为完整的设计和规格说明。\r \r 首先了解当前项目上下文，然后逐个提问来完善想法。一旦理解了要构建的内容，以小节形式（200-300字）呈现设计，每节后确认是否正确。\r \r
流程\r
\r
理解想法\r
\r
- 首先查看当前项目状态（文件、文档、最近提交）\r
- 逐个提问来完善想法\r
- 尽可能使用选择题，开放题也可以\r
- 每条消息只问一个问题 - 如果需要更多探索，分多个问题\r
- 聚焦于理解：目的、约束、成功标准\r \r
探索方案\r
\r
- 提出 2-3 种不同方案及其权衡\r
- 以对话方式呈现选项，包括推荐和理由\r
- 优先展示推荐方案并解释原因\r \r
呈现设计\r
\r
- 确信理解了要构建的内容后，呈现设计\r
- 分成 200-300 字的小节\r
- 每节后询问是否正确\r
- 涵盖：架构、组件、数据流、错误处理、测试\r
- 准备好返回澄清不清楚的地方\r \r
设计完成后\r
\r
文档输出\r
\r
- 将验证通过的设计写入
docs/plans/YYYY-MM-DD-\x3Ctopic>-design.md\r - 提交设计文档到 git\r \r
继续实施（如果需要）\r
\r
- 询问：「准备好开始实施了吗？」\r
- REQUIRED SUB-SKILL: 使用
core-writing-plans创建详细实施计划\r \r
领域扩展钩子\r
\r 如果是嵌入式项目：\r
- RECOMMENDED: 使用
embedded-datasheet-analysis分析硬件数据手册\r - RECOMMENDED: 使用
embedded-feasibility-assessment评估硬件约束\r - RECOMMENDED: 使用
embedded-platform-selection选择合适平台\r \r 如果是仿真项目：\r - RECOMMENDED: 使用
simulation-requirements分析仿真需求\r - RECOMMENDED: 使用
simulation-architecture设计仿真架构\r \r
核心原则\r
\r
- 一次一个问题 - 不要用多个问题压垮用户\r
- 首选选择题 - 比开放题更容易回答\r
- YAGNI 原则 - 从所有设计中移除不必要的功能\r
- 探索替代方案 - 在确定之前始终提出 2-3 种方案\r
- 增量验证 - 分节呈现设计，验证每节\r
- 保持灵活 - 当某些内容不清楚时返回澄清\r
Usage Guidance
This skill is coherent and appears to do what it says: guide interactive brainstorming, read the project workspace, produce a design, and commit a design document to the repo. Before installing or enabling it, consider: (1) Are you comfortable letting the agent read all files and recent commits in the project workspace? That may include sensitive data. (2) Do you want the agent to automatically create commits? If not, remove or modify the auto-commit step or require explicit user confirmation. (3) The skill references and may invoke other sub-skills (core-writing-plans, embedded-*, simulation-*); only allow trusted sub-skills. (4) If you need tighter control, restrict the agent's repo permissions or run the skill in an isolated copy of the project so it can’t modify production branches or access secrets.
Capability Analysis
Type: OpenClaw Skill
Name: est321
Version: 1.0.0
The skill bundle defines a structured brainstorming and design workflow for an AI agent. It focuses on collaborative dialogue, incremental validation of design ideas, and documenting results in the 'docs/plans/' directory. No malicious code, data exfiltration, or harmful prompt injection patterns were found in SKILL.md or _meta.json.
Capability Assessment
Purpose & Capability
The name/description describe a brainstorming/design helper. The SKILL.md asks the agent to understand project context, propose alternatives, produce validated design sections, write docs under docs/plans/..., and commit to git — all of which are reasonable and proportionate for a design-brainstorming skill.
Instruction Scope
The instructions explicitly tell the agent to inspect the current project state (files, documentation, recent commits) and to write/commit a design document. This is within the skill's purpose but does grant the skill (when invoked) access to the repository workspace and git history and permission to create commits. Also references required/recommended sub-skills (e.g., core-writing-plans, embedded-*). Confirm you are comfortable with the agent reading/writing repository files and invoking those sub-skills.
Install Mechanism
No install spec and no code files — instruction-only. This is the lowest-risk install mechanism (nothing is downloaded or written by an installer).
Credentials
The skill declares no required environment variables, credentials, or config paths. The SKILL.md does not request external secrets. This is proportionate to its stated functionality.
Persistence & Privilege
always:false and default autonomous invocation are used. The skill does not request permanent presence or modify other skills. It may invoke other sub-skills as described — standard for modular skills.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install est321 - After installation, invoke the skill by name or use
/est321 - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Introduced a new brainstorming skill for creative work, focusing on collaborative dialogue to transform ideas into designs
- Structured process with three phases: understanding ideas, exploring solutions, and presenting designs incrementally
- Added domain-specific hooks for embedded and simulation projects with recommended sub-skills
- Emphasizes core principles like asking one question at a time and exploring multiple alternatives
- Integrates with documentation and implementation workflows, requiring sub-skills for detailed planning
Metadata
Frequently Asked Questions
What is 头脑超级风暴?
在任何创造性工作之前必须使用 - 创建功能、构建组件、添加新功能或修改行为。通过协作对话探索用户意图、需求和设计。 It is an AI Agent Skill for Claude Code / OpenClaw, with 112 downloads so far.
How do I install 头脑超级风暴?
Run "/install est321" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is 头脑超级风暴 free?
Yes, 头脑超级风暴 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does 头脑超级风暴 support?
头脑超级风暴 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created 头脑超级风暴?
It is built and maintained by LKY115 (@lky115); the current version is v1.0.0.
More Skills