Token导航 LogoToken导航TokenDH.com
开发只读github未标认证来源可访问许可证需确认审计通过

brainstorm头脑风暴

Agent Skill

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。

总安装

588

周安装

25

GitHub Stars

7

下载量

206
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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/btraut/skills
仓库路径:skills/brainstorm
安装命令:
npx skills add https://github.com/btraut/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/btraut/skills --skill brainstorm

简介

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。

  • 它主要用于开发场景,引导用户从粗略想法到清晰设计的头脑风暴过程。
  • 可通过 npx skills add 命令从指定 GitHub 仓库安装并使用该技能。
  • 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操作。
  • brainstorm 属于开发类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Brainstorm

Use this skill to guide a user from a rough idea to a clear design/spec by asking targeted questions, one at a time, after first inspecting the project state.

Workflow

  1. Scan the project context

- Review the working directory to understand the current state, constraints, and any existing docs or code. - Summarize what you saw in 2-4 sentences only if it helps frame the next question.

  1. Ask refining questions (one per message)

- Ask exactly one question per response. - Prefer multiple-choice questions with 3-5 options; include an "Other: ____" option when helpful. - For multiple-choice questions, mark exactly one option as recommended so the user has a clear default. - In Codex request_user_input, mark the recommended choice by suffixing the label with (Recommended). In Claude AskUserQuestion, use an explicit recommended flag when available or clearly label one option as recommended. - Use open-ended questions only when options would be misleading. - Sequence questions from highest-uncertainty to lowest-uncertainty. - Do not ask questions that can be trivially answered by inspecting the repo or using available tools; look it up first. - Keep each question tightly scoped and decision-oriented. - For Claude, ask questions via AskUserQuestion.

  1. Converge on understanding

- Once the idea is clear enough to describe a design/spec, stop asking questions. - Explicitly indicate you are switching from questions to describing the design.

  1. Describe the design in sections

- Provide the design/spec in sections of ~200-300 words each. - After each section, ask whether it looks right so far before continuing. - Incorporate feedback and revise the next section accordingly.

  1. Beads + planning handoff

- After the final spec section is approved, summarize the spec into bead fields: title, description, design, acceptance. - Ask one multiple-choice question covering the next step (beads and/or plan), and mark one option as recommended. Example choices: create a single bead, create an epic + milestones, proceed to plan only, or pause. - If beads are requested and granularity is unclear, ask a single follow-up question to choose between a single bead vs an epic with milestone beads. - Decision rule for granularity: - Single bead: 1-3 sessions, cohesive flow, minimal handoffs. - Epic + milestones: longer work or clear checkpoints, even if sequential. Use linear dependencies if steps must be done in order. - If a plan is requested, provide a concise spec recap (goals, non-goals, UX, data/logic, constraints, acceptance) to seed the plan. - If a plan is created later, link it in the bead design field.

Style rules

  • Ask only one question per message.
  • Keep momentum: no long preambles or multi-paragraph lead-ins.
  • Use concrete language and avoid filler.
  • Do not announce the skill or preface with meta statements like "Using the brainstorm skill because...".
  • When asking about beads/plan, use a single multiple-choice question; only follow up if bead granularity needs a choice.
  • For each multiple-choice question, ensure exactly one option is explicitly marked as recommended.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.13%
按下载量换算68

Claude

32.61%
按下载量换算67

Cursor

19.69%
按下载量换算41

Gemini CLI

10.21%
按下载量换算21

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills