Clone Site takes a URL and rebuilds the page as a Next.js project. It drives Chrome through the Chrome MCP to screenshot the target at desktop, tablet and mobile widths, extracts fonts, colors and every asset, and records scroll, click and hover behavior before anything is built.
For each section it writes a specification file with exact computed CSS values, per-state content and responsive rules, then hands that spec to a builder agent working in its own git worktree. Sections are merged as they finish, the page is assembled, and a side-by-side visual comparison against the original closes the job.
What You Get
- A Next.js site that mirrors the target, runnable with npm run dev
- Downloaded images, videos, fonts and extracted SVG icon components under public and src
- One specification file per component in docs/research/components
- Design reference screenshots and behavior and page topology notes in docs/research and docs/design-references
- A completion report with sections built, assets downloaded, build status and known gaps
Common Use Cases
- Replicate a competitor or inspiration landing page as a starting point for your own
- Rebuild a legacy marketing site on a modern Next.js stack
- Turn a URL into a component library with exact spacing, type and color values
- Recreate scroll-driven and hover-driven interactions you want to study
What Makes It Unique
Most cloning prompts screenshot a page and guess. This one forces extraction first: exact getComputedStyle values, every state of tabs and scroll triggers, the interaction model (click, scroll, hover or time) before building, and a spec file as the contract for every builder. It caps builder prompts at about 150 lines of spec so sections stay small, and it requires a passing build after each merge.
Under The Hood
It runs on your machine through your agent. It controls Chrome through Chrome MCP to load the target site, take screenshots and run JavaScript that reads computed styles. It then writes and runs a Node.js script that downloads the site’s images, videos and fonts into public, writes many files in your project (specs, notes, components), runs npm install and npm run build, and dispatches builder agents in git worktrees that are merged back into main. It fetches web pages and assets from the site you point it at, so use it only on sites you are allowed to copy.