README

AI Website Cloner Template

 Clone any website with one command

Give your AI coding agent a URL and watch it recreate the website as a clean Next.js app.

Best results with Claude Code + Opus 5.5. Also supports Codex, Cursor, and OpenCode.

 

Quick Start · Watch Demo · Supported Platforms

  

   



---

 Demo



 Click the image above to watch the full demo on YouTube.

 Quick Start

 1. Set up your project

Recommended: ask your agent. Paste this into Codex, Claude Code, or your coding agent:

text
Set up https://github.com/JCodesMore/ai-website-cloner-template
as a standalone project in a new folder on my computer.
Ask me where to put it. Clone the repository, remove its origin remote,
install dependencies, and run npm run check. Leave it ready for me
to clone a website.


Or create your own GitHub repository:



Give it a name and click Create repository. Then give your agent the new repository's link and ask it to clone it onto your computer, install dependencies, and run npm run check.

 2. Clone a website

Open the project in your agent with browser access enabled. In Claude Code or Cursor, run:

text
/clone-website https://example.com


Replace the URL with the website you want to recreate. Once it's built, ask your agent for any changes you want.

 Supported Platforms

| Agent                                                         | Status                     |
| ------------------------------------------------------------- | -------------------------- |
| Claude Code | Recommended — Opus 5.5 |
| Codex CLI                  | Supported                  |
| OpenCode                              | Supported                  |
| Cursor                                 | Supported                  |

 Prerequisites

- Node.js 24+
- An AI coding agent (see Supported Platforms)

 Tech Stack

- Next.js 16 — App Router, React 19, TypeScript strict
- shadcn/ui — Base UI primitives + Tailwind CSS v4
- Tailwind CSS v4 — oklch design tokens
- Lucide React — default icons (replaced by extracted SVGs during cloning)

 How It Works

The /clone-website skill follows four steps:

1. Map — map source URLs to local routes and preserve existing work.
2. Observe — inspect desktop/mobile pages, extract real assets and fonts, and exercise alternate states.
3. Build — implement editable components and working interactions; delegate independent sections when useful.
4. Compare — review source and local pages at matched sizes/states, repair visible differences, and run the production check.

Framer pages and animated sites have focused inspection guidance for responsive variants, media, sticky scenes, and scroll/time-driven motion. Direct HTTP or asset tools handle extraction where practical; browser comparisons establish appearance and behavior. Deliverables include route mappings, run instructions, comparison screenshots, and any remaining gaps.

 Use Cases

- Platform migration — rebuild a site you own from WordPress/Webflow/Squarespace into a modern Next.js

Top issues

Latest release

Sharper cloning guidance that catches more fidelity drift with fewer, more general directives.

- Treat each observation as a sample of a rule: read declared values and vary viewport width (including wider than the design), height, input, and state.
- Use the files the source actually loads, and build shared components and page-wide behavior, such as smooth scrolling, from every observed state.
- Compare beyond the design width and judge scroll and pointer behavior with real input.

Full changelog: https://github.com/JCodesMore/ai-website-cloner-template/compare/v0.6.0...v0.6.1