Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问clear审计通过

brainstorm-diverge-converge头脑风暴 分歧 汇聚

Agent Skill

brainstorm-diverge-converge 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。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

2,130

周安装

87

GitHub Stars

85

下载量

682
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

3

许可证

MIT

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-diverge-converge(头脑风暴 分歧 汇聚)
来源仓库:https://github.com/lyndonkl/claude
仓库路径:skills/brainstorm-diverge-converge
安装命令:
npx skills add https://github.com/lyndonkl/claude --skill brainstorm-diverge-converge
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/lyndonkl/claude --skill brainstorm-diverge-converge

简介

brainstorm-diverge-converge 采用三阶段法:发散→聚类→收敛,避免过早评判创意。

  • 适用于用户体验优化、功能优先级排序或商业模式探索等复杂议题。
  • 输出包含原始点子清单、主题分组依据及加权评分矩阵供后续决策参考。
  • 建议在时间充裕时使用,单轮对话难以完成完整流程迭代。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Brainstorm Diverge-Converge

Table of Contents

- 1. Gather Requirements - 2. Diverge (Generate Ideas) - 3. Cluster (Group Themes) - 4. Converge (Evaluate & Select) - 5. Document & Validate

Three phases: Diverge (generate many ideas without judgment), Cluster (group into themes), Converge (evaluate against criteria and select).

Quick Example:

# Problem: How to improve customer onboarding?

## Diverge (30 ideas)
- In-app video tutorials
- Interactive walkthroughs
- Email drip campaign
- Live webinar onboarding
- 1-on-1 concierge calls
- ... (25 more ideas)

## Cluster (6 themes)
1. **Self-serve content** (videos, docs, tooltips)
2. **Interactive guidance** (walkthroughs, checklists)
3. **Human touch** (calls, webinars, chat)
4. **Motivation** (gamification, progress tracking)
5. **Timing** (just-in-time help, preemptive)
6. **Social** (community, peer examples)

## Converge (Top 3)
1. Interactive walkthrough (high impact, medium effort) - 8.5/10
2. Email drip campaign (medium impact, low effort) - 8.0/10
3. Just-in-time tooltips (medium impact, low effort) - 7.5/10

Workflow

Copy this checklist and track your progress:

Brainstorm Progress:
- [ ] Step 1: Gather requirements
- [ ] Step 2: Diverge (generate ideas)
- [ ] Step 3: Cluster (group themes)
- [ ] Step 4: Converge (evaluate and select)
- [ ] Step 5: Document and validate

Step 1: Gather requirements

Clarify topic/problem (what are you brainstorming?), goal (what decision will this inform?), constraints (must-haves, no-gos, boundaries), evaluation criteria (what makes an idea "good" - impact, feasibility, cost, speed, risk, alignment), target quantity (suggest 20-50 ideas), and rounds (single session or multiple rounds, default: 1).

Step 2: Diverge (generate ideas)

Generate 20-50 ideas without judgment or filtering. Suspend criticism (all ideas valid during divergence), aim for quantity and variety (different types, scales, approaches), and use creative prompts: "What if unlimited resources?", "What would competitor do?", "Simplest approach?", "Most ambitious?", "Unconventional alternatives?". Output: Numbered list of raw ideas. For simple topics → generate directly. For complex topics → Use resources/template.md for structured prompts.

Step 3: Cluster (group themes)

Organize ideas into 4-8 distinct clusters by identifying patterns, creating categories (mechanism, user/audience, timeline, effort, risk, strategic objective), naming clusters clearly, and checking coverage (distinct approaches). Fewer than 4 = not enough variety, more than 8 = too fragmented. Output: Ideas grouped under cluster labels.

Step 4: Converge (evaluate and select)

Define criteria (from step 1), score ideas on criteria (1-10 or Low/Med/High scale), rank by total/weighted score, select top 3-5 options, and document tradeoffs (why chosen, what deprioritized). Evaluation patterns: Impact/Effort matrix, weighted scoring, must-have filtering, pairwise comparison. See Common Patterns for domain-specific approaches.

Step 5: Document and validate

Create brainstorm-diverge-converge.md with: problem statement, diverge (full list), cluster (organized themes), converge (scored/ranked/selected), and next steps. Validate using resources/evaluators/rubric_brainstorm_diverge_converge.json: verify 20+ ideas with variety, distinct clusters, explicit criteria, consistent scoring, top selections clearly better, actionable next steps. Minimum standard: Score ≥ 3.5.

Common Patterns

For product/feature ideation:

  • Diverge: 30-50 feature ideas
  • Cluster by: User need, use case, or feature type
  • Converge: Impact vs. effort scoring
  • Select: Top 3-5 for roadmap

For problem-solving:

  • Diverge: 20-40 solution approaches
  • Cluster by: Mechanism (how it solves problem)
  • Converge: Feasibility vs. effectiveness
  • Select: Top 2-3 to prototype

For research questions:

  • Diverge: 25-40 potential questions
  • Cluster by: Research method or domain
  • Converge: Novelty, tractability, impact
  • Select: Top 3-5 to investigate

For strategic planning:

  • Diverge: 20-30 strategic initiatives
  • Cluster by: Time horizon or strategic pillar
  • Converge: Strategic value vs. resource requirements
  • Select: Top 5 for quarterly planning

Guardrails

Do:

  • Generate at least 20 ideas in diverge phase (quantity matters)
  • Suspend judgment during divergence (criticism kills creativity)
  • Create distinct clusters (avoid overlap and confusion)
  • Use explicit, relevant criteria for convergence (not vague "goodness")
  • Score consistently across all ideas
  • Document why top ideas were selected (transparency)
  • Include "runner-up" ideas (for later consideration)

Don't:

  • Filter ideas during divergence (defeats the purpose)
  • Create clusters that are too similar or overlapping
  • Use vague evaluation criteria ("better", "more appealing")
  • Cherry-pick scores to favor pet ideas
  • Select ideas without systematic evaluation
  • Ignore constraints from requirements gathering
  • Skip documentation of the full process

Quick Reference

  • Template: resources/template.md - Structured prompts and techniques for diverge-cluster-converge
  • Quality rubric: resources/evaluators/rubric_brainstorm_diverge_converge.json
  • Output file: brainstorm-diverge-converge.md
  • Typical idea count: 20-50 ideas → 4-8 clusters → 3-5 selections
  • Common criteria: Impact, Feasibility, Cost, Speed, Risk, Alignment

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

04

需要参考平台分布和安装热度时

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

补充不同宿主或平台的使用分布数据

能力 5

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

Claude Code

28.64%
按下载量换算195

Gemini CLI

24.55%
按下载量换算167

Antigravity

20.53%
按下载量换算140

OpenCode

12.2%
按下载量换算83

Cursor

9.09%
按下载量换算62

windsurf

3.36%
按下载量换算23

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。

来源信息

继续浏览同类 Skills