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

develop-design-rationale制定设计原理

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

1,011

周安装

43

GitHub Stars

168

下载量

354
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:develop-design-rationale(制定设计原理)
来源仓库:https://github.com/product-on-purpose/pm-skills
仓库路径:skills/develop-design-rationale
安装命令:
npx skills add https://github.com/product-on-purpose/pm-skills --skill develop-design-rationale
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/product-on-purpose/pm-skills --skill develop-design-rationale

简介

develop-design-rationale 捕捉设计决策背后的原因、约束与替代方案考量。

  • 区别于设计本身展示“做什么”,此技能保存“为什么这么做”的推理过程。
  • 适用于 UX 重大决策、设计评审准备与新成员 onboarding 场景。
  • 确保组织记忆不被遗忘,支持后续重构与方案回溯分析。
  • 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

Design Rationale

A design rationale document captures the "why" behind design decisions.the context, constraints, alternatives considered, and reasoning that led to a particular solution. While designs themselves show what was built, rationale documents preserve institutional knowledge about why it was built that way.

When to Use

  • When making significant UX decisions that affect user experience
  • Before design reviews to prepare stakeholder discussions
  • When multiple valid approaches exist and the choice needs justification
  • To onboard new team members to existing design decisions
  • When revisiting past decisions to understand original reasoning
  • During design system evolution to document pattern choices

Instructions

When asked to document design rationale, follow these steps:

  1. State the Decision Begin with a clear, one-sentence summary of what design decision was made. This becomes the title and reference point for the document.
  2. Describe the Context Explain the situation that prompted this decision. What problem were you solving? What constraints existed? What user needs informed the direction? Include relevant research findings.
  3. List Options Considered Document at least 2-3 alternatives that were evaluated. For each option, describe what it would look like and its key characteristics. Be fair to all options.avoid strawmen.
  4. Define Evaluation Criteria Specify how options were assessed: usability heuristics, technical feasibility, brand alignment, user research findings, business requirements, or design principles.
  5. Explain the Reasoning Walk through why the chosen option best meets the criteria. Be explicit about trade-offs.what you gained and what you sacrificed. Acknowledge where the decision is reversible vs. irreversible.
  6. Document Trade-offs Accepted Every design decision involves trade-offs. Name what you gave up and why it was acceptable. This honesty helps future teams understand constraints.
  7. Note Follow-up Considerations Capture anything that needs attention later: metrics to watch, conditions that might warrant revisiting the decision, or related decisions to make.

Output Format

Use the template in references/TEMPLATE.md to structure the output.

Quality Checklist

Before finalizing, verify:

  • Decision is clearly stated in one sentence
  • Context explains the "why now" and constraints
  • Multiple alternatives are documented fairly
  • Evaluation criteria are explicit
  • Reasoning addresses why chosen option beats alternatives
  • Trade-offs are honestly acknowledged
  • Document is useful to someone inheriting this design

Examples

See references/EXAMPLE.md for a completed example.

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

35.86%
按下载量换算127

Claude

30.1%
按下载量换算107

Cursor

18.42%
按下载量换算65

Gemini CLI

10.53%
按下载量换算37

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