Token导航 LogoToken导航TokenDH.com
效率只读clawhub未标认证来源可访问clear审计通过

game-design-brainstorm-methods游戏设计头脑风暴法

Agent Skill

用于辅助界面设计、视觉规范、排版、配色、布局和交互体验优化。它适合让 Agent 根据产品场景整理页面结构、生成 UI 方案、检查视觉一致性或改进组件层级。使用时需要结合现有品牌、设计系统和用户任务,不应只堆装饰元素;涉及真实页面改动时,应通过截图或浏览器预览检查文本溢出、对齐和响应式表现。

总安装

2,742

周安装

112

GitHub Stars

公开资料未说明

下载量

878
OpenClaw

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

MIT-0

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:game-design-brainstorm-methods(游戏设计头脑风暴法)
来源仓库:https://github.com/stanestane/game-design-brainstorm-methods
安装命令:
openclaw skills install game-design-brainstorm-methods
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 OpenClaw 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。

ClawHubOpenClaw
openclaw skills install game-design-brainstorm-methods

简介

game-design-brainstorm-methods 系统化激发游戏创意与功能构思。

  • 适用于解决卡点问题或拓展玩法边界的设计工作坊场景。
  • 融合经典头脑风暴技巧与游戏行业最佳实践。game-design-brainstorm-methods 属于效率类 Skill,可作为该场景下的辅助能力补充。
  • 轻量级工具,即装即用,适合团队协作快速生成选项。
  • 产出结果需后续评估筛选以避免过度发散偏离主题。

SKILL.md

name
game-design-brainstorm-methods
description
Apply established brainstorming and ideation methodologies to game design problems, features, systems, UX flows, live-ops ideas, content concepts, and stuck team discussions. Use when the user wants a specific brainstorming method rather than generic ideation, or when you should choose and run a method such as SCAMPER, How Might We, Crazy 8s, Six Thinking Hats, Brainwriting 6-3-5, Worst Possible Idea, forced connections, Lotus Blossom, or a morphological matrix.

Game Design Brainstorm Methods

Use named brainstorming methods, not generic idea spray.

This skill helps choose and run a well-known ideation methodology that fits the design problem. The goal is not to mention frameworks for show. The goal is to use the right method to unlock better game design options, surface hidden assumptions, and produce a practical shortlist worth exploring next.

Read references/method-selection.md when choosing a method. Read references/method-patterns.md when you need the exact structure for a method output.

What to produce

Produce:

  1. Problem frame - what the team is trying to solve
  2. Method choice - which brainstorming method is best and why
  3. Method run - the actual brainstorm output in that method's format
  4. Idea clusters - themes, repeated patterns, or promising directions
  5. Shortlist - strongest candidates to pursue next
  6. Next move - recommendation, prototype, or follow-up question

Process

1. Frame the ideation problem

Clarify:

  • what design problem, feature, or system is under discussion
  • whether the need is divergence, reframing, critique, or narrowing
  • what constraints matter most
  • whether the user wants novelty, structure, speed, or alignment

2. Choose the right method

Pick one primary method. Use a second method only when it adds clear value.

Typical fits:

  • SCAMPER - improve or mutate an existing feature
  • How Might We - turn fuzzy problems into opportunity prompts
  • Crazy 8s - force fast variation and volume
  • Six Thinking Hats - structure discussion across multiple lenses
  • Brainwriting 6-3-5 - generate many ideas without one dominant voice
  • Worst Possible Idea - break fixation by inverting bad ideas into useful principles
  • Forced connections - inject novelty through random or adjacent stimuli
  • Lotus Blossom - expand one central idea into adjacent branches
  • Morphological matrix - combine dimensions systematically into new concepts

3. Run the method properly

Do not collapse the method into generic bullets. Preserve the logic of the method. For example:

  • SCAMPER should actually walk through substitute, combine, adapt, modify, put to other use, eliminate, reverse/rearrange
  • Six Thinking Hats should clearly separate hat modes
  • Brainwriting should show rounds, seeds, or parallel idea contributions
  • Morphological matrix should define dimensions before combining them

4. Extract the design value

After the method run, identify:

  • repeated themes
  • strongest directions
  • strange but interesting outliers
  • weak ideas worth discarding
  • what should be prototyped, discussed, or parked

5. Convert brainstorm into action

End with one of these:

  • best 3 candidates
  • one recommended direction and why
  • next prototype question
  • follow-up method if the first method created useful ambiguity but not enough convergence

Response structure

Problem Frame

  • ...

Chosen Method

  • Method: ...
  • Why this method fits: ...

Method Run

  • ...

Idea Clusters

  • ...

Strongest Candidates

  1. ...
  2. ...
  3. ...

Recommended Next Move

  • ...

Fast mode

  • What kind of ideation problem is this?
  • Which method fits best?
  • Run that method clearly.
  • Pull out the 3 strongest design directions.
  • Recommend what to do next.

Working principle

Different brainstorming problems need different tools. Do not default to freeform ideation when a specific method would produce better thinking.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

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

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

OpenClaw

83.07%
按下载量换算729

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

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