Token导航 LogoToken导航TokenDH.com
前端设计执行命令github未标认证来源可访问许可证需确认审计通过

brainstorming头脑风暴

Agent Skill

brainstorming 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

264

周安装

11

GitHub Stars

1

下载量

88
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:brainstorming(头脑风暴)
来源仓库:https://github.com/freeacger/loom
仓库路径:skills/brainstorming
安装命令:
npx skills add https://github.com/freeacger/loom --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。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/freeacger/loom --skill brainstorming

简介

brainstorming 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 中围绕仓库状态或协作事项进行整理。
  • 通过 npx skills add 命令从指定仓库安装并使用该技能。
  • 安装前需确认权限范围、维护状态及是否触发联网或文件操作。
  • 建议结合原始 README 核验具体用法和功能边界。

SKILL.md

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 and get user approval.

Session Map

Before asking the first question, declare the session structure upfront:

This brainstorming session will take approximately N questions across these topics: ① [Topic A] → ② [Topic B] → ③ [Topic C] → ④ [Topic D] Current: Question X/N

Derive N and the topic list from the idea's complexity after exploring project context (Step 1). For a simple feature, N is typically 3–5; for a complex system, 6–8. State N honestly — do not compress to seem fast.

Anti-Pattern: "This Is Too Simple To Need A Design"

Every project goes through this process. A todo list, a single-function utility, a config change — all of them. "Simple" projects are where unexamined assumptions cause the most wasted work. The design can be short (a few sentences for truly simple projects), but you MUST present it and get approval.

Checklist

You MUST create a task for each of these items and complete them in order:

  1. Explore project context — check files, docs, recent commits
  2. Ask clarifying questions — one at a time, understand purpose/constraints/success criteria
  3. Propose exactly 4 approaches — with trade-offs and your recommendation
  4. Present design — in sections scaled to their complexity, get user approval after each section
  5. Write design doc — save to docs/design-decisions/YYYY-MM-DD-<topic>-design.md with frontmatter, run gen_index.sh, and commit
  6. Transition to implementation — invoke writing-plans skill to create implementation plan

Process Flow

digraph brainstorming {
    "Explore project context" [shape=box];
    "Ask clarifying questions" [shape=box];
    "Propose exactly 4 approaches" [shape=box];
    "Present design sections" [shape=box];
    "User approves design?" [shape=diamond];
    "Write design doc" [shape=box];
    "Invoke writing-plans skill" [shape=doublecircle];

    "Explore project context" -> "Ask clarifying questions";
    "Ask clarifying questions" -> "Propose exactly 4 approaches";
    "Propose exactly 4 approaches" -> "Present design sections";
    "Present design sections" -> "User approves design?";
    "User approves design?" -> "Present design sections" [label="no, revise"];
    "User approves design?" -> "Write design doc" [label="yes"];
    "Write design doc" -> "Invoke writing-plans skill";
}

The terminal state is invoking writing-plans. Do NOT invoke frontend-design, mcp-builder, or any other implementation skill. The ONLY skill you invoke after brainstorming is writing-plans.

The Process

Understanding the idea:

  • Check out the current project state first (files, docs, recent commits)
  • Ask questions one 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
  • Every question must use the Question Card format (see below)
  • Focus on understanding: purpose, constraints, success criteria

Exploring approaches:

  • Always propose exactly 4 approaches — this ensures divergent thinking
  • Present using the Approach Comparison table:
ApproachCore ideaProsCons
A. [name].........
B. [name].........
C. [name].........
D. [name].........
Recommendation: [A / A+C combination / etc.] Reasoning: [1–2 sentences explaining why single or combination is recommended]

Presenting the design:

  • Once you believe you understand what you're building, present the design
  • Scale each section to its complexity: a few sentences if straightforward, up to 200-300 words if nuanced
  • Ask after each section whether it looks right so far
  • Cover: architecture, components, data flow, error handling, testing
  • Be ready to go back and clarify if something doesn't make sense

Question Card Format

Every clarifying question must be rendered exactly as follows:

**Question X/N: [topic]**
Background: [1 sentence explaining why this information is needed]
Question: [the specific question]
Options:
  A. ...
  B. ...
  C. Other (please specify)

(omit Options if the answer space cannot be enumerated)

Rules:

  • X/N must stay current across every message
  • Background is mandatory — it shows the user why the question matters
  • Options are preferred; each option on its own line; omit only when the answer space cannot be enumerated
  • Keep each card to ≤ 5 lines visible to the user

Batching Rule

Default: one card per message.

Exception — light batching (2–3 questions in one message) is allowed only when ALL of the following hold:

  1. All questions are purely factual/context-gathering (e.g., "What stack are you on?", "Is there an existing auth system?")
  2. None is a critical design decision (approach, architecture, trade-offs)
  3. The total card count does not exceed 3

When batching, render each question as a separate numbered card. Critical decision questions are ALWAYS sent alone.

After the Design

Documentation:

  • The target path is docs/design-decisions/YYYY-MM-DD-<topic>-design.md
  • Before writing, check if the file already exists. Another agent may have written a design for the same topic. If the file exists, append a variant suffix: -v2, -v3, etc. (e.g. 2026-03-24-feature-x-design-v2.md). Never overwrite an existing design document.
  • Write the validated design to the resolved path
  • The file MUST begin with this frontmatter block (fill all fields before writing): ` --- title: <full title of the design> status: Active area: <top-level/sub-area, kebab-case> description: <one sentence: what problem this design solves> supersedes: "" superseded_by: "" authors: <run git config user.name> model: <current model id, e.g. claude-sonnet-4-6> --- `
  • area format: <top-level>/<sub-area> in kebab-case (e.g. auth/session, billing/refund, infra/ci). Sub-area is optional. Derive top-level from the project's directory structure, module names, or domain language. If docs/design-decisions/ already contains design docs, reuse an existing area value when the topic fits — consistency matters more than precision.
  • Allowed status values: Active, Implemented, Superseded, Archived. New designs always start as Active.
  • Use elements-of-style:writing-clearly-and-concisely skill if available
  • After writing the file, regenerate the index: bash scripts/gen-design-index.sh --root "$(pwd)" If scripts/gen-design-index.sh does not exist in the project, skip this step and inform the user: "Index not regenerated — copy scripts/gen-design-index.sh from the brainstorming skill source to enable it."
  • Stage both the new design doc and the updated docs/design-decisions/index.md in the same commit

Implementation:

  • Invoke the writing-plans skill to create a detailed implementation plan
  • Do NOT invoke any other skill. writing-plans is the next step.

Key Principles

  • Session map first — Declare the total question count and topic agenda before asking anything
  • Question Card always — Every question uses the fixed card format (X/N, Background, Question, Options each on own line)
  • One decision at a time — Each critical design decision gets its own message; light factual batching (≤3) is the only exception
  • 4 approaches always — Always propose exactly 4 options to ensure divergent thinking; recommend single or combination with reasoning
  • Multiple choice preferred — Easier to answer than open-ended when possible; options on separate lines
  • YAGNI ruthlessly — Remove unnecessary features from all designs
  • Incremental validation — Present design, get approval before moving on
  • Be flexible — Go back and clarify when something doesn't make sense

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

37.34%
按下载量换算33

Claude

30.21%
按下载量换算27

Cursor

16.24%
按下载量换算14

Gemini CLI

8.25%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/freeacger/loom --skill brainstorming 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

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