design-mirror
Replicate the visual style of any website and apply it to your existing codebase. Use this skill whenever the user wants to match a site's design, mirror a UI aesthetic, make their app look like another site, or replicate a specific visual style from a URL. Trigger on phrases like 'make it look like', 'match the design of', 'copy the style from', 'I want my app to look like X', 'mirror this design', 'inspired by [url]', or any time the user points at a website and says they want their frontend to match it.
What this skill does
# 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](https://brightdata.com/cp) → Account Settings
- `BRIGHTDATA_UNLOCKER_ZONE` — create an Unlocker zone at brightdata.com/cp
```bash
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):
```bash
# 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.
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.