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-one-thing-to-remove游戏设计需要删除一件事

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

2,376

周安装

101

GitHub Stars

公开资料未说明

下载量

832
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-one-thing-to-remove(游戏设计需要删除一件事)
来源仓库:https://github.com/stanestane/game-design-one-thing-to-remove
安装命令:
openclaw skills install game-design-one-thing-to-remove
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-one-thing-to-remove

简介

识别对项目影响最大的可删除项,简化设计复杂度。

  • 适用于功能冗余、流程冗长或原型过大的优化场景。
  • 基于输入内容分析优先级,提出单一高影响力移除建议。
  • 建议结合团队讨论使用,避免仅依赖自动化判断。
  • game-design-one-thing-to-remove 属于效率类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

name
game-design-one-thing-to-remove
description
Identify the single highest-leverage thing to remove from a game design, feature, system, UX flow, pitch, roadmap item, or prototype in order to improve it significantly. Use when a design feels bloated, muddy, overengineered, overly tutorialized, friction-heavy, or diluted by low-value mechanics, and you want a subtractive critique with rationale, tradeoffs, and a cleaner alternative.

Game Design One Thing To Remove

Improve the design by cutting one thing, not by adding three more.

Use this skill when a design would likely become better through subtraction. The goal is not to nitpick random dislikes. The goal is to identify the one removal with the highest leverage: the thing whose absence would most improve clarity, pacing, focus, emotional impact, usability, production efficiency, or strategic coherence.

Read references/removal-lenses.md when deciding what kind of thing is most worth cutting. Read references/evaluation-patterns.md when you need the exact output pattern.

What to produce

Produce:

  1. Design read - what the design is trying to do
  2. Removal candidate - the one thing to remove
  3. Why this removal has highest leverage - why this cut matters more than others
  4. What improves if removed - concrete downstream effects
  5. Tradeoff - what value is lost too
  6. Value-preserving alternative - how to keep the good part without the bad part, if needed
  7. Verdict - remove now, prototype without it, or cut later if evidence confirms

Process

1. Understand what the design is trying to achieve

Clarify:

  • the intended player experience
  • the core loop or promise
  • which parts feel central versus decorative
  • what business, retention, content, or production realities matter

2. Look for subtractive opportunities

Check whether the design contains:

  • redundant mechanics
  • duplicate progression layers
  • false choices
  • low-value friction
  • weak reward currencies
  • tutorial clutter
  • content burdens that add little value
  • fantasy dilution
  • complexity that does not create meaningful depth

3. Identify the highest-leverage removal

Pick one thing only. Do not list five cuts unless the user explicitly asks. Choose the removal whose absence would improve the design most significantly.

Good candidates include:

  • one mechanic
  • one progression layer
  • one UI step
  • one rule or constraint
  • one reward type
  • one content dependency
  • one feature that muddies the fantasy

4. Explain the mechanism of improvement

Do not say only that the design becomes “cleaner.” Explain exactly what improves, such as:

  • comprehension
  • pacing
  • motivation
  • readability
  • strategic clarity
  • production sustainability
  • onboarding burden
  • player trust
  • emotional focus

5. Acknowledge the loss honestly

A good cut may still remove something useful. State what is lost and whether that loss matters. If appropriate, suggest a lighter substitute that preserves the upside without keeping the full problematic element.

6. Make a practical recommendation

End with a decision such as:

  • remove now
  • prototype without it
  • keep for now, but cut if testing confirms the issue

Response structure

Design Read

  • ...

One Thing I Would Remove

  • ...

Why This Is the Highest-Leverage Cut

  • ...

What Improves If Removed

  • ...

What You Lose

  • ...

How To Preserve the Good Part Without the Bad Part

  • ...

Verdict

  • ...

Fast mode

  • What is the design trying to do?
  • What single element is hurting it most?
  • Why is that element more worth cutting than anything else?
  • What gets better if it disappears?
  • What should replace it, if anything?

Style rules

  • Be decisive.
  • Pick one thing.
  • Prefer mechanism over taste.
  • Do not recommend removal just because something is complex; complexity is acceptable if it creates real value.
  • Distinguish between elegant subtraction and destructive oversimplification.
  • If nothing should be removed, say that clearly and explain why.

Working principle

Many designs get worse because every problem is answered with addition. Sometimes the best improvement is subtraction with intent.

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

79.55%
按下载量换算662

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