A reusable template for reverse-engineering any website and rebuilding it as a pixel-perfect clone using Claude Code.
Point it at a URL, run /clone-website, and Claude Code will inspect the site via Chrome MCP, extract design tokens and assets, write component specs, and dispatch parallel builder agents to reconstruct every section — all in isolated git worktrees that merge automatically.
- Use this template — click "Use this template" on GitHub (or clone it)
- Install dependencies
npm install
- Edit
TARGET.md— set the URL, scope, and fidelity level for the site you want to clone - Run the skill in Claude Code:
/clone-website <url> - Customize (optional) — after the base clone is built, modify as needed
- Node.js 20+
- Claude Code with Chrome MCP enabled (required for site inspection)
- Next.js 16 — App Router, React 19, TypeScript strict
- shadcn/ui — Radix primitives + Tailwind CSS v4
- Tailwind CSS v4 — oklch design tokens
- Lucide React — default icons (replaced by extracted SVGs during cloning)
The /clone-website skill runs a multi-phase pipeline:
- Reconnaissance — screenshots, design token extraction, interaction sweep (scroll, click, hover, responsive)
- Foundation — updates fonts, colors, globals, downloads all assets
- Component Specs — writes detailed spec files (
docs/research/components/) with exact computed CSS values, states, behaviors, and content - Parallel Build — dispatches builder agents in git worktrees, one per section/component
- Assembly & QA — merges worktrees, wires up the page, runs visual diff against the original
Each builder agent receives the full component specification inline — exact getComputedStyle() values, interaction models, multi-state content, responsive breakpoints, and asset paths. No guessing.
src/
app/ # Next.js routes
components/ # React components
ui/ # shadcn/ui primitives
icons.tsx # Extracted SVG icons
lib/utils.ts # cn() utility
types/ # TypeScript interfaces
hooks/ # Custom React hooks
public/
images/ # Downloaded images from target
videos/ # Downloaded videos from target
seo/ # Favicons, OG images
docs/
research/ # Extraction output & component specs
design-references/ # Screenshots
scripts/ # Asset download scripts
TARGET.md # Clone target configuration
AGENTS.md # Agent instructions & code style
npm run dev # Start dev server
npm run build # Production build
npm run lint # ESLint checkEdit TARGET.md before cloning:
- URL — the site to reverse-engineer
- Pages — which pages to replicate
- Fidelity — pixel-perfect, high fidelity, or structural
- Scope — what's in/out of scope
- Customization plans — modifications to apply after the base clone
MIT