Token导航 LogoToken导航

Agent Skill · 前端设计

brainstorm(头脑风暴)

brainstorm 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

brainstorm 是前端设计类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在前端设计类的 10,216 个 Skill 里排第 1,121。

总安装 7,564周安装 309GitHub Stars 45下载 2,447核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:brainstorm(头脑风暴)
来源仓库:https://github.com/buiducnhat/agent-skills
仓库路径:skills/brainstorm
安装命令:
npx skills add https://github.com/buiducnhat/agent-skills --skill brainstorm
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/buiducnhat/agent-skills --skill brainstorm

这个 Skill 是做什么的

前端设计类 Skill 关注页面结构、视觉规范和组件写法,输出通常是可运行的界面代码。

brainstorm 用于将模糊想法转化为可评审的设计方案,通过结构化对话明确需求、权衡选项并输出设计简报。它结合项目上下文分析约束条件,生成包含替代方案和 trade-off 分析的 concrete 交付物。使用时需提供初步构想和项目背景,Agent 会引导完成从澄清到验证的完整流程,最终移交规划阶段。

安装前请确认仓库权限、维护状态,以及是否会读取现有代码或生成新文档文件。brainstorm 属于前端设计类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/brainstorm

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/buiducnhat/agent-skills --skill brainstorm;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

brainstorm 怎么安装?

在终端执行 npx skills add https://github.com/buiducnhat/agent-skills --skill brainstorm。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

brainstorm 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

brainstorm 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

brainstorm 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

brainstorm 用的人多吗?

公开数据是累计安装 7,564 次,近一周安装 309 次,下载 2,447 次,GitHub 45 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

brainstorm 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理前端设计类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

前端设计类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
frontend-design

前端设计 · Codex、Claude

8,823,360126,072只读MIT通过
vercel-composition-patterns

Vercel 组合模式 · Codex、Claude

3,858,81625,893需要联网MIT通过
vercel-react-native-skills

Vercel React native skills 前端 · Codex、Claude

2,468,66425,878只读MIT通过
adapt

adapt 搜索 · Codex、Claude

2,027,04023,125操作浏览器未明确通过
bolder

bolder 分析 · Codex、Claude

2,004,28823,130只读未明确通过
brainstorm

头脑风暴 · 本页

7,56445只读未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Brainstorm

Overview

Use this skill to convert rough ideas into clear, reviewable design outputs through structured dialogue.

The goal is to:

  1. Clarify requirements and constraints
  2. Explore alternatives with trade-offs
  3. Produce a concrete, validated design brief in artifacts or a handoff to planning

Workflow

Step 1: Gather Project Context

Load project context per the shared Context Loading Protocol. Also check key implementation files relevant to the idea and note constraints from existing architecture, dependencies, and conventions.

Keep this pass focused. Only gather what is needed for the current idea.

Step 2: Clarify Requirements

Ask targeted questions sequentially to remove ambiguity. Follow the Question Tool mandate.

  • Focus on:

- Objective and user value - Scope boundaries - Constraints (technical, UX, performance, timeline) - Success criteria - Non-goals

Do not jump to implementation details too early.

Step 3: Explore Approaches

Propose 2-5 viable approaches.

For each approach, include:

  • Short summary
  • Pros
  • Cons / risks
  • Complexity estimate
  • Recommended use conditions

Lead with your recommended option and explain why it best fits the project context and constraints.

After presenting all approaches, use Question Tool to let the user pick their preferred approach. List the summary options. Example:

  1. Approach A, short summary
  2. Approach B, short summary
  3. Approach C, short summary
  4. Other (please specify)

with the tag added for the recommended approach to guide the user.

Step 4: Present the Design Incrementally

Once requirements are clear, present the design incrementally in logical phases (about 200-300 words per phase) to avoid overwhelming the user.

  • Phase 1: Foundation - Problem framing, goals, and proposed architecture/flow.
  • Phase 2: Technical Details - Data model, interfaces, error handling, and edge cases.
  • Phase 3: Delivery - Testing/verification strategy and rollout considerations (if applicable).

After presenting each phase, use Question Tool immediately to ask whether to:

  1. Proceed to the next phase
  2. Adjust the current phase
  3. Revisit a previous phase

Step 5: Close the Loop

After you and the user have worked through requirements and the design is validated, determine the next actions.

  1. Use Question Tool to present the user with three high-level next actions:

- "Write plan immediately (in current context)" - skip the artifact step and move straight to a write-plan handoff. - "Write artifacts" - continue by authoring the brainstorm documents described in Step 6. - "End session (already provided enough information for user)" - stop; the conversation has produced enough insight for now.

  1. If the user picks Write artifacts, proceed to Step 6. Once the draft artifacts exist, use Question Tool again to validate them with options:

- "Write plan with current artifacts, context" - "End session - artifacts are sufficient for now" - "Need changes" (free-form text) - collect the feedback, revise the artifacts, and re-ask.

  1. If the user picked Write plan immediately, initiate a handoff to use skill write-plan using the current brainstorming context; no additional artifact validation is required.
  2. If the user picked End session, simply stop. The information collected so far is considered sufficient.

Step 6 (optional): Write Brainstorm Artifacts

Only perform this step after the user has explicitly chosen "Write artifacts" during Step 5.

Persist results to the standardized location:

  • Directory: docs/brainstorms/YYMMDD-HHmm-<topic-slug>/
  • Main file (required): docs/brainstorms/YYMMDD-HHmm-<topic-slug>/SUMMARY.md
  • Optional supporting files:

- docs/brainstorms/YYMMDD-HHmm-<topic-slug>/section-01-<slug>.md - docs/brainstorms/YYMMDD-HHmm-<topic-slug>/section-02-<slug>.md - etc.

SUMMARY.md format: strictly follow the template inside references/summary-template.md.

Rules

  • Do not write production code or make implementation changes in this skill in the brainstorm session.
  • Keep interaction lightweight and iterative; every step should be run in the same session.
  • Prefer clarity over completeness when uncertain; ask a follow-up question.
  • Align all recommendations with project documentation and standards.
  • Keep assumptions explicit; do not guess silently.
  • Think before coding: Surface assumptions explicitly. If multiple interpretations exist, present them — don't pick silently. If a simpler approach exists, say so and push back when warranted.

平台分布

Codex

36.8%
按下载量换算900

Claude

30.84%
按下载量换算755

Cursor

19.91%
按下载量换算487

Gemini CLI

9.92%
按下载量换算243

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills