← Back to Skills Marketplace
566
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install core-brainstorming
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 instruction-only and appears coherent for in-repo brainstorming. Before installing or invoking it: (1) only run it in repositories you trust because it will read files and recent commits and will create and git-commit design docs; (2) ensure the agent's runtime has the intended git configuration/credentials if you want commits to succeed; (3) verify you are comfortable with the skill invoking the declared sub-skill(s) (core-writing-plans and any recommended embedded/simulation helpers) since those may perform further actions; (4) if you need stricter limits, run the skill in a sandboxed workspace or temporarily revoke write access to the repository.
Capability Analysis
Type: OpenClaw Skill
Name: core-brainstorming
Version: 0.1.0
The core-brainstorming skill bundle is a standard design and planning tool intended to guide an AI agent through a collaborative requirement-gathering process. The instructions in SKILL.md define a structured workflow for exploring project ideas, proposing architectural solutions, and documenting the final design in the docs/plans/ directory. There are no indicators of malicious intent, data exfiltration, or unauthorized command execution; the file system and git interactions are consistent with the stated purpose of project documentation.
Capability Assessment
Purpose & Capability
Name/description match the instructions: the skill is meant to run a collaborative design brainstorm and the SKILL.md's steps (gather context, ask questions, propose options, write design) align with that purpose.
Instruction Scope
The instructions tell the agent to inspect the current project state (files, docs, recent commits) and to write a design file under docs/plans/... and commit it to git. Those filesystem and git actions are expected for an in-repo brainstorming workflow, but they grant the skill read/write access to the repository and history—ensure you run it only in trusted projects.
Install Mechanism
No install spec or code is provided (instruction-only), so nothing will be downloaded or written by an installer.
Credentials
The skill declares no environment variables or credentials. However, committing to git and reading recent commits implies the agent will need repository access and possibly configured git credentials; this is plausible but not explicitly declared.
Persistence & Privilege
always is false and the skill does not request persistent privileges or to modify other skills. It does reference required/recommended sub-skills, which is normal.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install core-brainstorming - After installation, invoke the skill by name or use
/core-brainstorming - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
core-brainstorming 0.1.0
- Initial release introducing a structured, dialogue-driven brainstorming workflow.
- Guides users from clarifying ideas to stepwise design presentation and validation.
- Emphasizes asking one focused question at a time, preferring multiple choice format.
- Includes extension hooks for embedded and simulation projects.
- Outlines documentation and handoff to implementation planning.
Metadata
Frequently Asked Questions
What is Core Brainstorming?
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 566 downloads so far.
How do I install Core Brainstorming?
Run "/install core-brainstorming" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Core Brainstorming free?
Yes, Core Brainstorming is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Core Brainstorming support?
Core Brainstorming is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Core Brainstorming?
It is built and maintained by tlreal (@tlreal); the current version is v0.1.0.
More Skills