Token导航 LogoToken导航

Agent Skill · 前端设计

brainstorming(头脑风暴)

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

brainstorming 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;许可证为 MIT,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 10,088。

总安装 186周安装 8GitHub Stars 3下载 65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
MIT

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:brainstorming(头脑风暴)
来源仓库:https://github.com/trancong12102/ccc
仓库路径:skills/brainstorming
安装命令:
npx skills add https://github.com/trancong12102/ccc --skill brainstorming
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/trancong12102/ccc --skill brainstorming

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。

brainstorming 用于辅助安全审计、权限检查和凭据风险分析,适合梳理敏感配置和鉴权逻辑。适用于生成安全复核清单和排查常见漏洞。通过 npx skills add 命令从 GitHub 仓库安装使用。不能将工具输出直接当作最终结论,需确认最小权限和操作边界。涉及密钥或用户数据时应先进行脱敏处理。

来源仓库内路径:skills/brainstorming

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/trancong12102/ccc --skill brainstorming;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

brainstorming 怎么安装?

在终端执行 npx skills add https://github.com/trancong12102/ccc --skill brainstorming。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

brainstorming 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。

brainstorming 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。

brainstorming 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

brainstorming 用的人多吗?

公开数据是累计安装 186 次,近一周安装 8 次,下载 65 次,GitHub 3 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。

brainstorming 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。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 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。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 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
brainstorming

头脑风暴 · 本页

1863只读MIT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

Brainstorming Ideas Into Designs

Overview

Help turn ideas into fully formed designs and specs through natural collaborative dialogue.

Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design in small sections (200-300 words), checking after each section whether it looks right so far.

Tool Usage

ALWAYS use the AskUserQuestion tool when asking questions to the user. This provides a structured interface for gathering input.

  • Use multiSelect: false for single-choice questions (most common)
  • Use multiSelect: true when multiple options can be selected together
  • Provide 2-4 clear options with descriptions
  • Keep the header short (max 12 chars) - e.g., "Approach", "Auth type", "Storage"
  • Always include your recommendation: Put your recommended option first and add "(Recommended)" to the label
  • Always explain why: In the question text or option descriptions, explain your reasoning for the recommendation

The Process

Understanding the idea:

  • Check out the current project state first (files, docs, recent commits)
  • Use AskUserQuestion to ask one question at a time to refine the idea
  • Prefer multiple choice questions when possible, but open-ended is fine too
  • Only one question per message - if a topic needs more exploration, break it into multiple questions
  • Focus on understanding: purpose, constraints, success criteria

Exploring approaches:

  • Propose 2-3 different approaches with trade-offs
  • Present options conversationally with your recommendation and reasoning
  • Lead with your recommended option and explain why
  • Consult the Oracle when facing complex architectural decisions (see below)

Presenting the design:

  • Once you believe you understand what you're building, present the design
  • Break it into sections of 200-300 words
  • Use AskUserQuestion after each section to validate (e.g., "Does this section look right?")
  • Cover: architecture, components, data flow, error handling, testing
  • Be ready to go back and clarify if something doesn't make sense

Key Principles

  • Use AskUserQuestion tool - Always use the tool for structured user input
  • Recommend with reasoning - Every question must include your recommendation and why
  • Consult Oracle proactively - Get second opinions on complex decisions
  • One question at a time - Don't overwhelm with multiple questions
  • Multiple choice preferred - Easier to answer than open-ended when possible
  • YAGNI ruthlessly - Remove unnecessary features from all designs
  • Explore alternatives - Always propose 2-3 approaches before settling
  • Incremental validation - Present design in sections, validate each
  • Be flexible - Go back and clarify when something doesn't make sense

Oracle Consultation

Proactively invoke the Oracle skill to get a second opinion when:

  • Complex architectural decisions - Multiple viable patterns with significant trade-offs (e.g., microservices vs monolith, event-driven vs request-response)
  • Security-sensitive designs - Authentication flows, data encryption, access control patterns
  • Performance-critical choices - Caching strategies, database indexing, algorithm selection
  • You're uncertain - When you have a recommendation but want validation before presenting to the user

How to Consult

Use the Skill tool to invoke the oracle: Skill(skill: "oracle"). The oracle's instructions will be loaded and guide you through the consultation process.

Reaching Consensus

When Oracle's opinion differs from yours:

  1. Present both perspectives to the user with clear reasoning
  2. Highlight where opinions align - these are likely the right choices
  3. Explain disagreements honestly - "Oracle suggests X because [reason], but I lean toward Y because [reason]"
  4. Let the user decide on contentious points with full context

When NOT to Consult

  • Simple, straightforward decisions with obvious answers
  • Minor implementation details that don't affect architecture
  • When the user has already expressed a strong preference

平台分布

Antigravity

29.29%
按下载量换算19

Claude Code

22.96%
按下载量换算15

windsurf

20.44%
按下载量换算13

trae

12.71%
按下载量换算8

OpenCode

8.51%
按下载量换算6

Codex

3.34%
按下载量换算2

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。

继续浏览同类 Skills