clone-website

Extract assets, CSS, and content from websites into auditable artifacts.

5.5k|665|Updated Aug 5, 2024

Search Tags:#automation #documentation #website #clone #builder-agents #css-extraction #assets-extraction

Ready to run

npx skills add https://github.com/yournextstore/yournextstore --skill clone-website-yournextstore

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: clone-website
Source: https://github.com/yournextstore/yournextstore/tree/main/.agents/skills/clone-website
Command: npx skills add https://github.com/yournextstore/yournextstore --skill clone-website-yournextstore

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Clone complex websites by extracting assets, CSS, structure, and content into auditable artifacts that can be rebuilt or analyzed, enabling rapid, repeatable site replication workflows.

Core Features & Use Cases

Automated extraction of assets (images, videos, fonts), CSS rules, and textual content, organized by page sections.
Proactive dispatch of parallel builder agents in worktrees to reconstruct the site while preserving auditable provenance.
Triggered by natural phrases like "make a copy of this site" to initiate a pixel-accurate clone for offline use, redesign, or research.

Quick Start

Provide the target URL as an argument to start the pixel-accurate clone workflow.

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 into build-ready code and assets?▼

To clone a website, provide the target URL to trigger automated extraction of CSS, images, fonts, and content into per-section specs. Specialized builder agents work in parallel worktrees to reconstruct the site while tracking provenance for auditable, pixel-accurate replication.

What is the best way to extract CSS and assets from a live web page for offline analysis?▼

Extracting CSS and assets from a live page requires browser automation tooling that captures styles, images, and fonts by page section. This produces organized, auditable artifacts that preserve design structure for offline replay, research, or site migration workflows.

Can I automate website replication for site migration using parallel builder agents?▼

You can automate website replication by dispatching parallel builder agents into dedicated worktrees. Each agent reconstructs specific page sections simultaneously while a foreman-like workflow tracks provenance and ensures consistency across all extracted artifacts.

Does cloning a complex website require browser automation tooling?▼

Cloning a complex website requires browser automation tooling to operate on live pages and capture assets, CSS rules, and textual content. This enables the extraction of per-section specs and ensures the resulting artifacts are auditable and build-ready.

When should I use an automated website clone tool instead of manual scraping?▼

Use an automated website clone tool when you need pixel-accurate, build-ready specs for complex sites. It coordinates parallel builder agents to extract and rebuild sections with provenance tracking, making it superior to manual scraping for design exploration, offline replay, or migration.

Why does website cloning produce auditable artifacts instead of direct HTML files?▼

Website cloning produces auditable artifacts because it extracts assets, CSS, and content into organized, per-section specifications rather than raw HTML. This approach preserves provenance, enables consistent rebuilding across worktrees, and supports repeatable site replication workflows.