Token导航 LogoToken导航TokenDH.com
前端设计执行命令github未标认证来源可访问许可证需确认审计通过

design-system设计系统

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

1,882

周安装

80

GitHub Stars

11

下载量

659
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:design-system(设计系统)
来源仓库:https://github.com/akillness/oh-my-skills
仓库路径:skills/design-system
安装命令:
npx skills add https://github.com/akillness/oh-my-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/akillness/oh-my-skills --skill design-system

简介

用于制定共享界面规则,指导产品级 UI 设计和组件体系构建。

  • 适合分类系统问题、选择合适模式、定义视觉规范和维护一致性标准。
  • 使用时需结合品牌资产和设计系统现状,输出可执行的紧凑方案包。
  • 涉及令牌变更或命名规则调整时,应参考治理清单确保向后兼容。
  • design-system 属于前端设计类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Design System

Use this skill when the main question is "what shared UI rules should govern this product or product family before we design or refactor individual screens?"

This is the repo's canonical frontend UI-system anchor. It should:

  1. classify the system problem,
  2. choose the right design-system mode,
  3. route neighboring frontend work out early,
  4. define a compact system packet another human or agent can execute.

Read references/system-modes.md before choosing an approach. Read references/token-and-governance-checklist.md before changing shared tokens, primitives, or naming rules. Read references/scope-boundaries.md when deciding whether the work belongs here, ui-component-patterns, responsive-design, web-accessibility, or web-design-guidelines. Read references/design-system-packet-template.md before writing the final handoff.

When to use this skill

  • Define or refactor a shared design system for a product, product suite, or app + marketing surface
  • Set token policy for color, typography, spacing, radius, elevation, motion, and breakpoint scales
  • Choose primitive naming rules, contribution boundaries, and reusable visual-language conventions
  • Create a coherent system direction for landing pages, dashboards, forms, and component libraries that must feel related
  • Turn vague requests like “our UI feels inconsistent” into a system-level direction packet instead of a one-off page redesign
  • Review whether a team needs a system decision before component, accessibility, or responsive implementation starts
  • Prepare a design-system handoff for Figma, code tokens, primitives, and downstream frontend work

When not to use this skill

  • The main task is reusable primitive / slot / variant API design or component-family extraction → use ui-component-patterns
  • The main task is viewport adaptation, container-query strategy, overflow, or mobile layout verification → use responsive-design
  • The main task is keyboard/focus behavior, WCAG remediation, labels, semantics, contrast, or manual a11y verification → use web-accessibility
  • The main task is a broad page or flow critique for hierarchy, CTA clarity, polish, and launch readiness → use web-design-guidelines
  • The task is implementation-only and the system rules are already clear; implement directly instead of reopening system governance

Core idea

A good design system is not a random palette plus a hero-section mock. It is a shared decision layer that defines:

  • what stays consistent,
  • what may vary by surface,
  • which neighboring skill owns the next implementation step,
  • and what artifact downstream teams should follow.

Do not let this skill become a catch-all for every frontend concern. System governance stays here; specialist remediation routes out.

Instructions

Step 1: Classify the design-system request before generating examples

Pick one primary mode so the answer stays bounded.

Modes:

  • Foundations mode — tokens, scales, naming, motion, density, breakpoint policy
  • Cross-surface alignment mode — landing page + dashboard + app-shell consistency, shared hierarchy, shared brand/system language
  • Primitive governance mode — when the team needs rules for primitive naming, ownership, contribution boundaries, and promotion from product-local UI into shared primitives
  • System handoff mode — package already-decided system rules into a concise artifact for design/dev execution
  • System review mode — assess whether inconsistency is really a design-system problem or should route to a neighboring skill

Quick frame:

Design-system request:
- Surface: marketing site + logged-in dashboard
- Primary mode: cross-surface alignment
- System question: shared tokens and hierarchy, separate page-specific layouts
- Likely route-outs: component API details to ui-component-patterns, responsive verification to responsive-design

Step 2: Define the shared system boundary

Before changing tokens or page direction, decide what the system actually owns.

Keep in design-system when the job is to define:

  • token scales and naming rules
  • primitive naming and contribution policy
  • visual-language principles that should apply across many screens
  • breakpoint or density policy that multiple surfaces should inherit
  • motion principles and accessibility baseline that many components depend on

Do not keep the work here when the question becomes:

  • one reusable component API → ui-component-patterns
  • one page’s layout breakage → responsive-design
  • one accessibility failure or remediation plan → web-accessibility
  • one broad UX/UI critique → web-design-guidelines

Step 3: Make the minimum shared decisions first

Do not start by dumping dozens of example tokens.

For each system request, decide these shared layers first:

  1. Foundations — color, type, spacing, radius, elevation, motion, density, breakpoints
  2. Primitive policy — which primitives exist, how they are named, what is shared vs product-local
  3. Surface rules — how landing pages, dashboards, forms, nav, and data-heavy surfaces should differ while staying coherent
  4. Accessibility baseline — contrast expectations, focus visibility, reduced-motion posture, semantic expectations
  5. Governance — who can add/change tokens or primitives, what must be reviewed, and when work should route to another skill

If a layer is unknown, say so and capture it as an open decision instead of inventing detail.

Step 4: Keep examples subordinate to the rules

Examples are useful only after the shared rules are explicit.

Good example usage:

  • show one token naming pattern
  • show one page-system contrast between landing and dashboard surfaces
  • show one primitive promotion rule
  • show one motion baseline or accessibility baseline

Bad example usage:

  • dumping a full palette, TS token file, CSS animation sheet, and JSX screen mock before saying what problem the system is solving

Use this rule:

  • rules first,
  • one or two illustrative examples second,
  • handoff packet last.

Step 5: Route neighboring frontend work out early

Mixed requests are normal. Split them explicitly.

Examples:

  • if the team asks for button variants, slot structure, and controlled/uncontrolled behavior, keep the system naming/tokens here but route API design to ui-component-patterns
  • if the team asks how cards collapse on mobile, keep shared breakpoint policy here but route layout adaptation to responsive-design
  • if the team asks whether icon-only buttons meet keyboard/focus/label requirements, keep baseline a11y expectations here but route remediation to web-accessibility
  • if the request is “audit this dashboard and tell us what feels off,” route the broad critique to web-design-guidelines

Do not hide unclear ownership by calling everything “design-system work.”

Step 6: Produce the design-system packet

End with a concise artifact that downstream design/dev work can follow.

Preferred format:

# Design System Packet

## Scope
- Products / surfaces covered:
- Primary mode:
- Shared system goal:

## Foundations
- Color / semantic token rules:
- Typography / spacing / radius / elevation:
- Motion / density / breakpoint policy:

## Primitive policy
- Shared primitives:
- Naming rules:
- What stays product-local:

## Surface guidance
- Landing / marketing:
- Dashboard / app shell:
- Forms / workflows:

## Accessibility baseline
- Contrast / focus / reduced motion / semantics:

## Route-outs
- `ui-component-patterns`:
- `responsive-design`:
- `web-accessibility`:
- `web-design-guidelines`:

## Open decisions
- ...

If the user asks for a terse answer, keep the same sections but compress them into bullets.

Step 7: Only then add a small illustrative example when needed

Use at most one or two examples and keep them obviously subordinate to the packet.

Healthy example shapes:

  • semantic color tokens (surface/default, surface/emphasis, text/muted) instead of giant fixed palettes
  • landing-page hero vs dashboard header comparison to show shared hierarchy but different density
  • primitive promotion rule such as “shared button stays primitive; billing-upsell banner stays product-local”

Step 8: Finish with a boundary sentence

End with a sentence that prevents overlap drift.

Examples:

  • "This packet defines the shared UI system; component API extraction belongs in ui-component-patterns."
  • "This packet sets breakpoint and density policy; page-level layout fixes belong in responsive-design."
  • "This packet sets accessibility baseline expectations; remediation and verification belong in web-accessibility."

Examples

Example 1: shared landing page + dashboard system

Input: "We need one design system for our marketing site and B2B dashboard so tokens, typography, and motion feel related without making both surfaces identical."

Good response shape:

  • choose cross-surface alignment mode
  • define shared foundations and surface-specific differences
  • leave one compact design-system packet
  • route component-family API design to ui-component-patterns

Example 2: token and primitive governance

Input: "Our team keeps adding random colors and spacing values. We need naming rules and a review policy for shared primitives."

Good response shape:

  • choose foundations or primitive governance mode
  • define token/naming rules and review thresholds
  • keep one or two naming examples only
  • avoid turning the answer into a full page mock

Example 3: mixed system + responsive request

Input: "Should the dashboard and mobile web app share one breakpoint policy, and how should the layout collapse on small screens?"

Good response shape:

  • keep shared breakpoint/density policy in design-system
  • route the actual collapse strategy and verification to responsive-design
  • make the split explicit in the packet

Example 4: accessibility-heavy follow-up

Input: "We already have tokens, but our forms still fail focus visibility and error-state accessibility."

Good response shape:

  • note the design-system baseline briefly
  • route the real remediation and manual verification to web-accessibility
  • do not absorb the full a11y fix into this skill

Best practices

  1. Decide the mode first so the skill stays bounded.
  2. Define shared rules before examples to avoid overfitting on one mockup.
  3. Keep governance explicit: token changes, primitive promotion, and ownership rules are part of the system.
  4. Use route-outs early so design-system does not steal layout, component-API, accessibility, or broad-audit work.
  5. Leave a compact packet another human or agent can follow.
  6. Keep the alias narrow: frontend-design-system remains a compatibility redirect, not a peer canonical skill.

References

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

36.81%
按下载量换算243

Claude

29.96%
按下载量换算197

Cursor

21.3%
按下载量换算140

Gemini CLI

9.29%
按下载量换算61

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/akillness/oh-my-skills --skill design-system 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

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