skills.rest
WebSmartTeam
WebSmartTeamOFFICIAL
Explore all skills by this author →
WebsiteGitHub

site-harvest

Harvests website HTML, CSS, JS, and assets into a structured format.

Updated Aug 23, 2026
Search Tags:#design system#migration#content extraction#website#scrape#harvest#rebuild
One-click install
npx skills add https://github.com/WebSmartTeam/COR-CODE --skill site-harvest
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: site-harvest
Source: https://github.com/WebSmartTeam/COR-CODE/tree/main/skills/site-harvest
Command: npx skills add https://github.com/WebSmartTeam/COR-CODE --skill site-harvest

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires firecrawl, chrome-tab, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the comprehensive extraction of website content, design elements, and assets, enabling accurate rebuilding or migration of digital properties.

Core Features & Use Cases

  • Full Site Archiving: Captures all text content, HTML structure, CSS, images, fonts, and icons.
  • Design System Extraction: Identifies and documents brand colors, typography, spacing, and component styles.
  • Automated Rebuild Reference: Generates a detailed "Theme Skill" file that serves as the definitive guide for recreating the site's design and functionality.
  • Use Case: A company needs to migrate its outdated website to a new platform. This Skill can archive the entire existing site, providing all necessary assets and design specifications to ensure the new site is a pixel-perfect replica with modern code.

Quick Start

Use the site-harvest skill to harvest the website located at https://example.com.

Frequently Asked Questions about site-harvest

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

FAQPage Schema
How do I extract a complete design system and content from an existing website?▼

To extract a website design system, this Skill captures text, HTML structure, CSS, images, fonts, and icons using Firecrawl and Chrome. It identifies brand colors, typography, spacing, and component styles to document the full design system.

Can I scrape website assets like CSS, fonts, and icons for a site migration?▼

Yes, you can scrape website assets like CSS, fonts, and icons for site migration. The Skill performs full site archiving to capture all text, HTML structure, images, and assets needed for rebuilding or migrating digital properties.

What is the best way to clone a website design for a pixel-perfect rebuild?▼

To clone a website design for a pixel-perfect rebuild, this Skill generates an automated rebuild reference. It creates a detailed theme skill file that serves as the definitive guide for recreating the site's design and functionality with modern code.

Does this website extraction tool work with Firecrawl and Chrome?▼

Yes, this website extraction tool works with Firecrawl and Chrome as its core dependencies. It uses these tools to comprehensively extract website content, design elements, and assets for enabling accurate rebuilding or migration of digital properties.

How do I grab design tokens and component styles from a website?▼

Grabbing design tokens and component styles from a website is done through design system extraction. The Skill identifies and documents brand colors, typography, spacing, and component styles to ensure the new site is a pixel-perfect replica.

Related Skills

Explore More Software Engineering Skills→
ajianazajianaz
4

browser

Automate Chrome browser control for site exploration and scraping via CDP.

Community
Advanced
vikingokftvikingokft

stitch::extract-design-md

Extract a Stitch-compatible DESIGN.md from frontend source code.

Official
Intermediate
HouseGarofaloHouseGarofalo
3

web-automation

Automate browser interactions and web scraping with Playwright, Puppeteer, Selenium, and Scrapy.

Official
Intermediate
OpenAEC-FoundationOpenAEC-Foundation
163

frappe-website-deploy

Deploy ERPNext/Frappe websites via REST API with Page Builder.

Official
Advanced