Back to directory

AI Website Cloner Template

A project template that has an AI coding agent recreate any website as a clean Next.js application, using a multi-phase pipeline of screenshots, extracted design specs and parallel builder agents.

AI Website Cloner Template

The template adds a /clone-website skill that, given a URL, runs a multi-phase pipeline: a reconnaissance pass takes screenshots, extracts design tokens, and sweeps through interactions such as scroll, click and hover; a foundation pass sets up fonts, colors and downloads assets; a component-spec pass writes detailed files with exact computed CSS values, states and content for each section; a parallel build pass dispatches separate builder agents in their own git worktrees, one per section or component; and an assembly pass merges the worktrees, wires up the page, and runs a visual diff against the original site.

The generated project uses Next.js with the App Router, React, TypeScript, shadcn/ui and Tailwind CSS. It supports Claude Code, Codex CLI, OpenCode and Cursor, and is intended for migrating a site the user owns to a modern stack, recovering lost source code, or studying how an existing site achieves its layout and behavior; the README states it must not be used for phishing, impersonation, or reproducing someone else's design or copy as one's own.

It is written in TypeScript and licensed under the MIT license.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.