Token导航 LogoToken导航

Agent Skill · 研究检索

design-system(设计系统)

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。

design-system 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为调用外部服务;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,674 个 Skill 里排第 38,566。

总安装 1,542周安装 63GitHub Stars 2下载 494核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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:design-system(设计系统)
来源仓库:https://github.com/jwilger/agent-skills
仓库路径:skills/design-system
安装命令:
npx skills add https://github.com/jwilger/agent-skills --skill design-system
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/jwilger/agent-skills --skill design-system

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

design-system 用于辅助界面设计、视觉规范和交互体验优化。适合生成 UI 方案、检查视觉一致性或改进组件层级。使用时需结合现有品牌和设计系统,避免堆砌装饰元素。

安装命令:npx skills add https://github.com/jwilger/agent-skills --skill design-system 涉及页面改动时应通过截图或浏览器预览检查文本溢出和对齐。

来源仓库内路径:skills/design-system

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/jwilger/agent-skills --skill design-system;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要调用外部服务,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

design-system 怎么安装?

在终端执行 npx skills add https://github.com/jwilger/agent-skills --skill design-system。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

design-system 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

design-system 需要什么权限?

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

design-system 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

design-system 用的人多吗?

公开数据是累计安装 1,542 次,近一周安装 63 次,下载 494 次,GitHub 2 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

design-system 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
design-system

设计系统 · 本页

1,5422调用外部服务未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Design System

Value: Communication -- a documented design system creates shared vocabulary for every visual decision. When philosophy is explicit and tokens are named, contributors extend the system consistently without guessing at intent.

Purpose

Facilitates collaborative creation of a design system specification. Produces an artifact at docs/design-system.pen (if Pencil MCP is available) or docs/design-system.html (single-file fallback) that documents philosophy, tokens, and the full component hierarchy from atoms through templates.

Practices

Detect Artifact Format

Check whether the mcp__pencil__get_editor_state tool is available.

  • Present: Use .pen format. Follow references/pencil-workflow.md.
  • Absent: Use HTML format. Follow references/html-artifact.md.

Decide the format before starting any design work. Do not switch formats mid-process.

Follow the Seven-Phase Collaborative Process

You MUST follow references/design-phases.md for the full methodology. Each phase completes before the next begins.

Phases at a glance:

  1. Philosophy & Constraints -- Brand, principles, accessibility, responsive strategy, constraints. Every subsequent decision traces here.
  2. Design Tokens -- Color, typography, spacing, radii, elevation, motion, breakpoints, opacity. Each token cites a philosophy principle.
  3. Atoms -- Indivisible elements (buttons, inputs, labels, icons). Each documents states and references only tokens.
  4. Molecules -- Functional units composed of atoms (form fields, search bars). Documents composition and interaction.
  5. Organisms -- Distinct UI sections composed of molecules and atoms (headers, forms, data tables). Documents layout behavior.
  6. Templates -- Page layouts arranging organisms. Defines structure, content slots, and breakpoint behavior.
  7. Artifact Assembly -- Compile into the chosen format with philosophy as the first section.

Facilitate, Do Not Assume

You are a facilitator, not a stenographer. Ask probing questions at each phase. Challenge choices that conflict with stated philosophy. Use references/facilitation-questions.md for question banks.

  1. Do not assume visual preferences -- ask
  2. Do not skip ahead when the user gives a partial answer -- probe deeper
  3. If event model wireframes exist in docs/event_model/, use them to identify required components, but still confirm with the user
  4. Present token proposals informed by the philosophy and ask for adjustments

Enforce Philosophy Traceability

Every design decision traces back to the philosophy.

  • Tokens cite which philosophy principle they serve (e.g., P1)
  • Atoms reference which tokens they use
  • Molecules document which atoms they compose
  • Organisms document which molecules and atoms they compose
  • Templates document which organisms they arrange

If a token cannot cite a principle, either the token is unnecessary or the philosophy is incomplete. Resolve before proceeding.

Do:

  • Define philosophy before any visual decisions
  • Use only token references in components -- never raw values
  • Complete each phase before starting the next
  • Verify traceability at every level
  • Refer to references/token-categories.md for comprehensive token guidance

Do not:

  • Make technology decisions (CSS framework, component library) -- those belong in architecture-decisions
  • Skip the philosophy phase or treat it as optional
  • Use raw color codes, pixel values, or font names in components
  • Design multiple phases simultaneously
  • Proceed with gaps -- if something is undefined, ask

Enforcement Note

Advisory in all modes. Phase gates are self-enforced: the agent must complete each phase's outputs and get user confirmation before proceeding. Token traceability is self-enforced: the agent must verify every component references tokens, not raw values.

Hard constraints:

  • Phase ordering (complete each phase before starting the next): [RP]

Constraints

  • "No raw values in components": This means no literal color codes, pixel values, font sizes, or spacing values anywhere in component definitions. "I defined a token for it" is not sufficient if the component file contains the raw value instead of the token reference. Defining many single-use tokens to technically satisfy this rule while defeating reusability is also a violation.
  • Philosophy phase: Philosophy means named principles with enough specificity to guide decisions. "Modern and clean" is not a philosophy -- it constrains nothing. Each principle should be testable: given a design decision, the principle should help you choose between options. If it doesn't eliminate any option, it's not specific enough.

Verification

After completing work guided by this skill, verify:

  • Philosophy documented with named principles before any components
  • Tokens defined for all visual categories (color, typography, spacing, radii, elevation, motion, breakpoints, opacity)
  • Every token cites a philosophy principle
  • Atoms reference only tokens (no raw values)
  • Molecules compose only atoms from the catalog
  • Organisms compose only molecules and atoms from the catalog
  • Templates arrange only organisms from the catalog
  • All component states documented (default, hover, focus, disabled, error as applicable)
  • Wireframe fields mapped to components if event model exists
  • Artifact exists at docs/design-system.pen or docs/design-system.html
  • Philosophy is the first section in the artifact

If any criterion is not met, revisit the relevant phase before proceeding.

Dependencies

This skill works standalone. For enhanced workflows, it integrates with:

  • event-modeling: Wireframes from event modeling sessions identify which components the design system must include. Run event-modeling first for best results.
  • architecture-decisions: The design system specification informs technology decisions for UI implementation (CSS framework, component library, build tooling). Run design-system before architecture-decisions.
  • atomic-design: The design system specification provides the token definitions, component catalog, and hierarchy that atomic-design implements in code.
  • tdd: Token values and component specifications become testable contracts -- visual regression tests verify token compliance.

Missing a dependency? Install with:

npx skills add jwilger/agent-skills --skill event-modeling

平台分布

Codex

33.81%
按下载量换算167

Claude

31.22%
按下载量换算154

Cursor

18.2%
按下载量换算90

Gemini CLI

10.53%
按下载量换算52

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

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。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills