clone-website

Reverse-engineers websites into pixel-perfect Next.js clones using browser automation and parallel builder agents.

Updated Mar 28, 2026
One-click install
npx skills add https://github.com/whatswithavi/Ecchelon_project --skill clone-website-whatswithavi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: clone-website
Source: https://github.com/whatswithavi/Ecchelon_project/tree/main/ai-website-cloner-template-master/.claude/skills/clone-website
Command: npx skills add https://github.com/whatswithavi/Ecchelon_project --skill clone-website-whatswithavi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Manually rebuilding an existing website requires tedious inspection of CSS values, assets, fonts, and interactive behaviors, and approximations lead to clones that look wrong or feel broken. This Skill automates the full reverse-engineering pipeline from live site inspection to a working Next.js codebase. ## Core Features & Use Cases - Automated Extraction: Uses Chrome MCP to capture screenshots, computed CSS via getComputedStyle(), fonts, colors, images, videos, and SVG icons from any live URL. - Behavior & Interaction Capture: Documents scroll-driven animations, hover states, tab switching, and smooth-scroll libraries so the clone behaves like the original, not just looks like it. - Parallel Builder Agents: Writes per-component spec files and dispatches builder agents in git worktrees to construct sections concurrently, then merges and verifies the build. - Use Case: Provide a marketing site's URL and receive a pixel-perfect Next.js + Tailwind + shadcn/ui replica with real content, assets, and responsive layouts at desktop, tablet, and mobile widths. ## Quick Start Ask the AI to clone a website by providing the target URL, for example: clone https://example.com and rebuild it as a pixel-perfect Next.js site.

Frequently Asked Questions about clone-website

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I clone a website with AI?▼

Provide the target URL as an argument to the clone-website skill. It uses Chrome MCP to extract screenshots, computed CSS, assets, and behaviors, then dispatches parallel builder agents to rebuild the site as a Next.js application section by section.

What tools are required to reverse-engineer a website automatically?▼

This workflow requires Chrome MCP for browser automation, a Next.js scaffold with Tailwind v4 and shadcn/ui, and Node.js for build verification. Without Chrome MCP the extraction phase cannot run.

Does website cloning capture scroll animations and hover states?▼

Yes. The process includes a mandatory interaction sweep that records scroll-triggered changes, hover transitions, tab switching, and smooth-scroll libraries like Lenis, capturing before/after computed styles and exact trigger thresholds.

Why does my website clone look different from the original?▼

Common causes are missing layered overlay images, approximated CSS values instead of computed styles, or a wrong interaction model such as click-based tabs when the original is scroll-driven. The skill's visual QA phase compares screenshots side by side to catch these.

Can the clone handle responsive layouts for mobile and tablet?▼

Yes. Extraction runs at 1440px, 768px, and 390px viewports, and each component spec documents responsive behavior and breakpoints so builders implement correct layouts at every width.