clone-website

julianromli/ai-skills · updated Apr 17, 2026

$npx skills add https://github.com/julianromli/ai-skills --skill clone-website
0 commentsdiscussion
summary

Transform any website into production-ready Next.js 16 code using Firecrawl.

  • Scrapes target websites and extracts HTML/markdown, with fallback crawling if initial scrape fails
  • Mandatory analysis phase presents detected sections, design tokens, images, and file structure to user before code generation
  • Generates complete Next.js 16 projects with TypeScript, Tailwind CSS v4, Shadcn UI components, and Lucide icons
  • Supports partial cloning by section (hero, pricing, footer) or full-pag
skill.md

Clone Website Skill

Transform any website into production-ready Next.js 16 code using Firecrawl MCP.

Workflow

Execute these 3 phases in order. Never skip Phase 2.

Phase 1: Scrape

  1. Extract URL from user request
  2. Identify section filter if specified (e.g., "hero only", "just the pricing")
  3. Scrape using Firecrawl:
firecrawl-mcp___firecrawl_scrape:
  url: [TARGET_URL]
  formats: ["markdown", "html"]
  onlyMainContent: true
  1. If scrape fails, fallback to firecrawl-mcp___firecrawl_crawl

Phase 2: Analysis (MANDATORY)

STOP. Present analysis to user before ANY code generation.

Read references/analysis-template.md and fill out the template with:

  • Detected sections and component breakdown
  • Extracted design tokens (colors, typography, spacing)
  • Image inventory with download/fallback status
  • Proposed file structure

Ask user: "Ready to proceed? (y/n or request modifications)"

Do not generate code until user confirms.

Phase 3: Code Generation

After user confirmation, generate files in this order:

  1. app/globals.css - Design tokens as CSS variables
  2. app/layout.tsx - Root layout with SEO metadata
  3. components/landing/[Section].tsx - Each component
  4. app/page.tsx - Main page composing components
  5. Download images to public/images/

Reference references/tech-stack.md for Next.js 16 conventions. Reference references/component-patterns.md for component structure.

Tech Stack (Fixed)

Layer Technology
Framework Next.js 16 (App Router)
Language TypeScript (strict)
Styling Tailwind CSS v4
Components Shadcn UI
Icons Lucide React
Font Geist Sans (default) or extracted

Image Handling

  1. Extract all image URLs from scraped content
  2. Attempt download via fetch
  3. On failure, use Unsplash fallback:
    • Hero: https://images.unsplash.com/photo-[id]?w=1920&h=1080
    • Avatars: https://images.unsplash.com/photo-[id]?w=100&h=100
    • Features: Prefer Lucide icons over images
  4. Save to public/images/ with descriptive kebab-case names

Partial Cloning

Parse user request for section filters:

Request Action
"clone the hero from X" Generate only Hero.tsx
"clone pricing and footer" Generate Pricing.tsx + Footer.tsx
"clone X" (no filter) Full page clone

Code Standards

  • Mobile-first responsive design
  • Use Tailwind arbitrary values for pixel-perfection: w-[347px]
  • Extract repeated colors to CSS variables
  • Use cn() utility for conditional classes
  • Add brief comments only for non-obvious patterns
  • Prefer gap-* over margins for flex/grid spacing
  • Use size-* over w-* h-* when values match

Discussion

Product Hunt–style comments (not star reviews)
  • No comments yet — start the thread.
general reviews

Ratings

4.627 reviews
  • Zaid Desai· Dec 24, 2024

    clone-website has been reliable in day-to-day use. Documentation quality is above average for community skills.

  • Valentina Torres· Dec 12, 2024

    clone-website fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.

  • Pratham Ware· Dec 8, 2024

    clone-website is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

  • Yash Thakker· Nov 27, 2024

    Keeps context tight: clone-website is the kind of skill you can hand to a new teammate without a long onboarding doc.

  • Anika Perez· Nov 15, 2024

    Useful defaults in clone-website — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • Isabella Shah· Nov 3, 2024

    We added clone-website from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.

  • Hiroshi Mehta· Oct 22, 2024

    Solid pick for teams standardizing on skills: clone-website is focused, and the summary matches what you get after install.

  • Dhruvi Jain· Oct 18, 2024

    clone-website has been reliable in day-to-day use. Documentation quality is above average for community skills.

  • Aarav Wang· Oct 6, 2024

    clone-website is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

  • Benjamin Iyer· Sep 13, 2024

    clone-website fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.

showing 1-10 of 27

1 / 3