Token导航 LogoToken导航TokenDH.com
前端设计需要联网github未标认证来源可访问许可证需确认审计提醒

design-mirror设计镜子

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

1,395

周安装

57

GitHub Stars

68

下载量

447
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-mirror(设计镜子)
来源仓库:https://github.com/brightdata/skills
仓库路径:skills/design-mirror
安装命令:
npx skills add https://github.com/brightdata/skills --skill design-mirror
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/brightdata/skills --skill design-mirror

简介

通过 Bright Data Web Unlocker 实时抓取网站视觉语言并应用至代码库。

  • 提取色彩、字体、间距、阴影等全套设计系统要素。
  • 使用时需指定目标站点,自动分析截图与 CSS 结构生成适配代码。
  • 安装方式:GitHub,命令为 npx skills add https://github.com/brightdata/skills --skill design-mirror。
  • 注意:依赖 Bright Data 服务可用性,抓取结果可能受反爬机制影响。

SKILL.md

Design Mirror

Capture the visual design language of any website and apply it to your existing codebase — colors, typography, spacing, layout rhythm, component shapes, and overall aesthetic — all extracted live via Bright Data's Web Unlocker.

What This Skill Does

  1. Capture — Screenshot + HTML scrape the inspiration site via Bright Data
  2. Extract — Identify the full design system: colors, fonts, spacing scale, border radii, shadows, component patterns
  3. Analyze — Study the screenshot visually and the CSS structurally to understand the design language
  4. Apply — Translate that design system into the user's existing codebase (their framework, their components)

You are not copying content or functionality. You're understanding the *design language* — the palette, the type scale, the card shapes, the hover states, the overall aesthetic feel.

Important: This skill is for design inspiration and learning — extracting publicly visible design tokens (colors, fonts, spacing) to inform your own UI work. Always use it respectfully and in accordance with the terms of service of the sites you reference.

Setup

Requires:

  • BRIGHTDATA_API_KEY — from brightdata.com/cp → Account Settings
  • BRIGHTDATA_UNLOCKER_ZONE — create an Unlocker zone at brightdata.com/cp
export BRIGHTDATA_API_KEY="your-api-key"
export BRIGHTDATA_UNLOCKER_ZONE="your-zone-name"

Step-by-Step Process

Step 1: Capture the Inspiration Site

Run both captures in parallel — screenshot (for visual analysis) and HTML scrape (for CSS extraction):

# Screenshot (save as PNG)
bash scripts/screenshot.sh "https://inspiration-site.com" "/tmp/target_screenshot.png"

# HTML + CSS scrape
bash scripts/scrape_html.sh "https://inspiration-site.com" "/tmp/target_page.html"

Read references/capture-guide.md for how to extract CSS from the raw HTML and handle common issues.

Step 2: Analyze the Design System

After capturing, analyze both in parallel:

Visual analysis (screenshot): Read the PNG image and identify:

  • Primary, secondary, accent colors
  • Background colors (page bg, card bg, surface hierarchy)
  • Typography: font families visible, size hierarchy (h1 → body → caption)
  • Layout: is it centered/constrained-width? Grid? Sidebar?
  • Card/container shapes: border radius size, shadow style (hard, soft, none, colored)
  • Button styles: pill, rectangle, ghost, gradient?
  • Navigation: sticky? Glass/blur effect? Dark or light?
  • Overall mood: dark, light, minimal, brutalist, glassmorphism, corporate, startup?

CSS analysis (HTML): Extract from <style> tags and inline styles:

  • CSS custom properties (:root {--color-...}) — publicly declared design tokens
  • Font imports (@import from Google Fonts, etc.)
  • Tailwind config if present
  • Repeated class patterns that reveal the spacing scale

Read references/css-extraction.md for the extraction playbook.

Step 3: Build the Design Token Map

Produce a structured design token map before touching any code:

DESIGN TOKENS FROM [site]
==========================
Colors:
  --bg-primary: #0a0a0f      (page background)
  --bg-surface: #13131a      (card/panel background)
  --text-primary: #ffffff
  --text-muted: #8888aa
  --accent: #7c3aed          (primary CTA color)
  --accent-hover: #6d28d9
  --border: rgba(255,255,255,0.08)

Typography:
  --font-heading: 'Inter', sans-serif
  --font-body: 'Inter', sans-serif
  font-scale: 12/14/16/20/24/32/48px
  heading-weight: 700
  body-weight: 400

Spacing:
  base-unit: 8px
  scale: 4/8/12/16/24/32/48/64px

Borders & Shadows:
  --radius-sm: 6px
  --radius-md: 12px
  --radius-lg: 20px
  --shadow: 0 4px 24px rgba(0,0,0,0.4)

Special effects:
  glass-blur: backdrop-filter: blur(16px)
  gradient: linear-gradient(135deg, #7c3aed, #2563eb)

Show this token map to the user before proceeding. It's the foundation — if it's wrong, the output will be wrong.

Step 4: Understand the User's Codebase

Before writing any code, read the relevant parts of their codebase:

  • What framework? (React, Vue, Next.js, plain HTML?)
  • What styling approach? (Tailwind, CSS modules, styled-components, plain CSS?)
  • Where are global styles defined? (globals.css, theme.ts, tailwind.config.js?)
  • What components need restyling? (ask the user if unclear)

Do not rewrite everything — surgical precision. Apply the design tokens to the existing structure.

Step 5: Apply the Design

The application strategy depends on their stack:

If Tailwind: Update tailwind.config.js with the new color palette, font family, border radius scale. Add custom CSS variables for anything Tailwind can't handle natively.

If CSS/CSS Modules: Create or update a :root variables block in globals.css. Update component stylesheets to use the new variables.

If styled-components/Emotion: Update the theme object. Replace hardcoded color/spacing values with theme tokens.

In all cases:

  • Apply colors, typography, and spacing globally first
  • Then tackle component-level details (buttons, cards, nav) one at a time
  • Preserve all existing functionality and layout structure — only visual properties change
  • Add any special effects (glass blur, gradients, animations) that define the inspiration site's character

Read references/apply-guide.md for framework-specific implementation patterns.

Step 6: Show the Before/After

After applying changes, clearly present:

  • Which files were modified
  • The design token mapping (source → what you set it to)
  • Any special effects added
  • What the user should check visually (hover states, dark/light mode, mobile)

If the user has a dev server running, remind them to check it. Offer to iterate on specific components.

Key Principles

Design language, not markup. The inspiration site's HTML structure and content are theirs. You're extracting the *design language* — how colors relate, how spacing flows, what gives the site its character — to apply as your own creative foundation.

Design tokens first, code second. Rushing to apply colors before understanding the full system leads to inconsistent results. Always build the token map first.

Ask about scope. "Apply the design everywhere" vs "just make the homepage feel like it" vs "only restyle the navbar" are very different jobs. Clarify before proceeding.

Don't break what works. The user's components work. Only change visual properties. If you're uncertain whether a change might break layout, err on the side of caution and flag it.

Iterative is fine. It's often better to get the foundation right (colors, type, spacing) and let the user review before tackling component-level details.

What to Do When...

The site uses a design system (Material, shadcn, etc.): Identify it, tell the user, and ask if they want to adopt the same system or just extract the visual tokens.

The CSS is minified/obfuscated: Fall back to the screenshot + visual analysis. You can still extract colors, spacing, and shapes from visual inspection.

The inspiration site is JS-rendered and the HTML scrape comes back mostly empty: Note this to the user — the screenshot will still work for visual analysis, but CSS extraction will be limited. You can still infer most tokens visually.

The user's codebase uses a component library (shadcn, Chakra, MUI): Apply the design by customizing the library's theme/config rather than overriding individual components.

Multiple pages need to match: Use the homepage for overall design tokens, but offer to check inner pages (e.g., /pricing, /docs) if the user wants to match a specific page's look.

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

36.73%
按下载量换算164

Claude

26.13%
按下载量换算117

Cursor

19.55%
按下载量换算87

Gemini CLI

9.64%
按下载量换算43

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。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