clone-website

Prompt file imported from Tan-Long/thegrainoftommorrow (.windsurf/workflows/clone-website.md). Copyright stays with the author.

Clone Website

You are about to reverse-engineer and rebuild the target URL provided by the user as pixel-perfect clones.

When multiple URLs are provided, process them independently and in parallel where possible, while keeping each site's extraction artifacts isolated in dedicated folders (for example, docs/research/<hostname>/).

This is not a two-phase process (inspect then build). You are a foreman walking the job site — as you inspect each section of the page, you write a detailed specification to a file, then hand that file to a specialist builder agent with everything they need. Extraction and construction happen in parallel, but extraction is meticulous and produces auditable artifacts.

By default, this is a multi-page clone. Treat each starting URL as the root of a same-origin site graph. Discover the page itself plus its internal child pages, then rebuild the route structure in Next.js so links like docs, pricing, register, product details, and other internal destinations work inside the clone.

Scope Defaults

The target is whatever page the target URL provided by the user resolves to. Unless the user specifies otherwise, use these defaults:

• Fidelity level: Pixel-perfect — exact match in colors, spacing, typography, animations
• Page coverage: Clone the starting page and all same-origin internal child pages you can discover from navigation, CTAs, cards, footer links, sitemap sections, and in-content links
• In scope: Visual layout and styling, component structure and interactions, responsive design, mock data for demo purposes
• Out of scope: Real backend / database, authentication, real-time features, SEO optimization, accessibility audit, user-specific/private pages, checkout/account flows that require server state
• Customization: None — pure emulation

Apply these crawl boundaries unless the user overrides them:

• Follow only http/https links on the same origin or an explicitly approved sibling subdomain
• Skip external links, mailto:, tel:, hash-only anchors, file downloads, logout links, and obvious session-specific endpoints
• Normalize URLs before deduping: drop hash fragments, sort query params, and collapse duplicate trailing-slash variants
• Treat faceted search, sort/filter permutations, and infinite pagination as unbounded spaces; ask the user whether to include them before cloning hundreds of near-duplicate pages

If the user provides additional instructions (specific fidelity level, customizations, extra context), honor those over the defaults.

Pre-Flight

1. Browser automation is required. Check for available browser MCP tools (Chrome MCP, Playwright MCP, Browserbase MCP, Puppeteer MCP, etc.). Use whichever is available — if multiple exist, prefer Chrome MCP. If none are detected, ask the user which browser tool they have and how to connect it. This skill cannot work without browser automation.
2. Parse the target URL provided by the user as one or more URLs. Normalize and validate each URL; if any are invalid, ask the user to correct them before proceeding. For each valid URL, verify it is accessible via your browser MCP tool.
3. Verify the base project builds: npm run build. The Next.js + shadcn/ui + Tailwind v4 scaffold should already be in place. If not, tell the user to set it up first.
4. Create the output directories if they don't exist: docs/research/, docs/research/components/, docs/design-references/, scripts/. For multiple clones, also prepare per-site folders like docs/research/<hostname>/ and docs/design-references/<hostname>/.
5. Before building anything, discover the internal route graph for each target and write it down. Produce docs/research/<hostname>/SITE_MAP.md (or docs/research/SITE_MAP.md for a single site) with every normalized internal URL, how it was discovered, its route depth, and its page family (marketing, docs, blog, pricing, product, product detail, auth, etc.).
6. If the route graph is obviously huge or unbounded (for example, hundreds of product detail pages, faceted search URLs, calendar archives, or paginated listings), stop and ask the user whether they want the full crawl, a capped representative subset, or only key route families.
7. When working with multiple sites in one command, optionally confirm whether to run them in parallel (recommended, if resources allow) or sequentially to avoid overload.

Guiding Principles

These are the truths that separate a successful clone from a "close enough" mess. Internalize them — they should inform every decision you make.

1. Completeness Beats Speed

Every builder agent must receive everything it needs to do its job perfectly: screenshot, exact CSS values, downloaded assets with local paths, real text content, component structure. If a builder has to guess anything — a color, a font size, a padding value — you have failed at extraction. Take the extra minute to extract one more property rather than shipping an incomplete brief.

2. Small Tasks, Perfect Results

When an agent gets "build the entire features section," it glosses over details — it approximates spacing, guesses font sizes, and produces something "close enough" but clearly wrong. When it gets a single focused component with exact CSS values, it nails it every time.

Look at each section and judge its complexity. A simple banner with a heading and a button? One agent. A complex section with 3 different card variants, each with unique hover states and internal layouts? One agent per card variant plus one for the section wrapper. When in doubt, make it smaller.

Complexity budget rule: If a builder prompt exceeds ~150 lines of spec content, the section is too complex for one agent. Break it into smaller pieces. This is a mechanical check — don't override it with "but it's all related."

3. Real Content, Real Assets

Extract the actual text, images, videos, and SVGs from the live site. This is a clone, not a mockup. Use element.textContent, download every <img> and <video>, extract inline <svg> elements as React components. The only time you generate content is when something is clearly server-generated and unique per session.

Layered assets matter. A section that looks like one image is often multiple layers — a background watercolor/gradient, a foreground UI mockup PNG, an overlay icon. Inspect each container's full DOM tree and enumerate ALL <img> elements and background images within it, including absolutely-positioned overlays. Missing an overlay image makes the clone look empty even if the background is correct.

4. Foundation First

Nothing can be built until the foundation exists: global CSS with the target site's design tokens (colors, fonts, spacing), TypeScript types for the content structures, and global assets (fonts, favicons). This is sequential and non-negotiable. Everything after this can be parallel.

For multi-page sites, foundation also means shared layouts, shell components, route helpers, and content schemas. Build the pieces that every page depends on before dispatching page-specific builders.

5. Extract How It Looks AND How It Behaves

A website is not a screenshot — it's a living thing. Elements move, change, appear, and disappear in response to scrolling, hovering, clicking, resizing, and time. If you only extract the static CSS of each element, your clone will look right in a screenshot but feel dead when someone actually uses it.

For every element, extract its appearance (exact computed CSS via getComputedStyle()) AND its behavior (what changes, what triggers the change, and how the transition happens). Not "it looks like 16px" — extract the actual computed value. Not "the nav changes on scroll" — document the exact trigger (scroll position, IntersectionObserver threshold, viewport intersection), the before and after states (both sets of CSS values), and the transition (duration, easing, CSS transition vs. JS-driven vs. CSS animation-timeline).

Examples of behaviors to watch for — these are illustrative, not exhaustive. The page may do things not on this list, and you must catch those too:

• A navbar that shrinks, changes background, or gains a shadow after scrolling past a threshold
• Elements that animate into view when they enter the viewport (fade-up, slide-in, stagger delays)
• Sections that snap into place on scroll (scroll-snap-type)
• Parallax layers that move at different rates than the scroll
• Hover states that animate (not just change — the transition duration and easing matter)
• Dropdowns, modals, accordions with enter/exit animations
• Scroll-driven progress indicators or opacity transitions
• Auto-playing carousels or cycling content
• Dark-to-light (or any theme) transitions between page sections
• Tabbed/pill content that cycles — buttons that switch visible card sets with transitions
• Scroll-driven tab/accordion switching — sidebars where the active item auto-changes as content scrolls past (IntersectionObserver, NOT click handlers)
• Smooth scroll libraries (Lenis, Locomotive Scroll) — check for .lenis class or scroll container wrappers

6. Identify the Interaction Model Before Building

This is the single most expensive mistake in cloning: building a click-based UI when the original is scroll-driven, or vice versa. Before writing any builder prompt for an interactive section, you must definitively answer: Is this section driven by clicks, scrolls, hovers, time, or some combination?

How to determine this:

1. Don't click first. Scroll through the section slowly and observe if things change on their own as you scroll.
2. If they do, it's scroll-driven. Extract the mechanism: IntersectionObserver, scroll-snap, position: sticky, animation-timeline, or JS scroll listeners.
3. If nothing changes on scroll, THEN click/hover to test for click/hover-driven interactivity.
4. Document the interaction model explicitly in the component spec: "INTERACTION MODEL: scroll-driven with IntersectionObserver" or "INTERACTION MODEL: click-to-switch with opacity transition."

A section with a sticky sidebar and scrolling content panels is fundamentally different from a tabbed interface where clicking switches content. Getting this wrong means a complete rewrite, not a CSS tweak.

7. Extract Every State, Not Just the Default

Many components have multiple visual states — a tab bar shows different cards per tab, a header looks different at scroll position 0 vs 100, a card has hover effects. You must extract ALL states, not just whatever is visible on page load.

For tabbed/stateful content:

• Click each tab/button via browser MCP
• Extract the content, images, and card data for EACH state
• Record which content belongs to which state
• Note the transition animation between states (opacity, slide, fade, etc.)

For scroll-dependent elements:

• Capture computed styles at scroll position 0 (initial state)
• Scroll past the trigger threshold and capture computed styles again (scrolled state)
• Diff the two to identify exactly which CSS properties change
• Record the transition CSS (duration, easing, properties)
• Record the exact trigger threshold (scroll position in px, or viewport intersection ratio)

8. Spec Files Are the Source of Truth

Every component gets a specification file in docs/research/components/ BEFORE any builder is dispatched. This file is the contract between your extraction work and the builder agent. The builder receives the spec file contents inline in its prompt — the file also persists as an auditable artifact that the user (or you) can review if something looks wrong.

The spec file is not optional. It is not a nice-to-have. If you dispatch a builder without first writing a spec file, you are shipping incomplete instructions based on whatever you can remember from a browser MCP session, and the builder will guess to fill gaps.

9. Build Must Always Compile

Every builder agent must verify npx tsc --noEmit passes before finishing. After merging worktrees, you verify npm run build passes. A broken build is never acceptable, even temporarily.

Phase 1: Reconnaissance

Navigate to the target URL with browser MCP.

Screenshots

• Take full-page screenshots at desktop (1440px) and mobile (390px) viewports
• Save to docs/design-references/ with descriptive names
• These are your master reference — builders will receive section-specific crops/screenshots later

Global Extraction

Extract these from the page before doing anything else:

Fonts — Inspect <link> tags for Google Fonts or self-hosted fonts. Check computed font-family on key elements (headings, body, code, labels). Document every family, weight, and style actually used. Configure them in src/app/layout.tsx using next/font/google or next/font/local.

Colors — Extract the site's color palette from computed styles across the page. Update src/app/globals.css with the target's actual colors in the :root and .dark CSS variable blocks. Map them to shadcn's token names (background, foreground, primary, muted, etc.) where they fit. Add custom properties for colors that don't map to shadcn tokens.

Favicons & Meta — Download favicons, apple-touch-icons, OG images, webmanifest to public/seo/. Update layout.tsx metadata.

Global UI patterns — Identify any site-wide CSS or JS: custom scrollbar hiding, scroll-snap on the page container, global keyframe animations, backdrop filters, gradients used as overlays, smooth scroll libraries (Lenis, Locomotive Scroll — check for .lenis, .locomotive-scroll, or custom scroll container classes), and any motion/runtime libraries (Framer Motion, GSAP, Lottie, Swiper, Embla, canvas/WebGL renderers). Add these to globals.css, note any libraries that need to be installed, and record where exact runtime reproduction is required instead of CSS-only approximation.

Mandatory Interaction Sweep

This is a dedicated pass AFTER screenshots and BEFORE anything else. Its purpose is to discover every behavior on the page — many of which are invisible in a static screenshot.

Scroll sweep: Scroll the page slowly from top to bottom via browser MCP. At each section, pause and observe:

• Does the header change appearance? Record the scroll position where it triggers.
• Do elements animate into view? Record which ones and the animation type.
• Does a sidebar or tab indicator auto-switch as you scroll? Record the mechanism.
• Are there scroll-snap points? Record which containers.
• Is there a smooth scroll library active? Check for non-native scroll behavior.
• For scroll-driven motion, record whether the effect is discrete or scrubbed, which properties are animated, and whether the timing is controlled by CSS, JS, or a third-party library.

Click sweep: Click every element that looks interactive:

• Every button, tab, pill, link, card
• Record what happens: does content change? Does a modal open? Does a dropdown appear?
• For tabs/pills: click EACH ONE and record the content that appears for each state
• For internal navigation links: record whether they navigate to another page, open a new tab, or reveal in-page content; add newly discovered same-origin destinations to the site map

Hover sweep: Hover over every element that might have hover states:

• Buttons, cards, links, images, nav items
• Record what changes: color, scale, shadow, underline, opacity

Responsive sweep: Test at these viewport widths via browser MCP:

• Desktop XL: 1440px
• Desktop: 1280px
• Laptop: 1024px
• Tablet landscape: 820px
• Tablet portrait: 768px
• Large mobile: 430px
• Mobile: 390px
• Small mobile: 375px
• Narrow mobile: 360px
• At each width, note which sections change layout (column → stack, sidebar disappears, navigation collapses, media crops differently, typography scales, etc.) and the exact breakpoint range where the change occurs.

Save all findings to docs/research/BEHAVIORS.md. This is your behavior bible — reference it when writing every component spec.

Site Graph Discovery

Before diving deep into one page's sections, map the whole cloneable surface area:

• Enumerate every visible same-origin link from the header, footer, sidebars, cards, CTAs, sitemap sections, and in-content rich text
• Visit each unique internal destination and repeat the link discovery pass until no new in-scope pages remain
• Record canonical URL, page title, route depth, parent/source page, page family, and notes about auth/protected/dead-end states
• Detect route templates: pages that share one shell but differ only by content data (for example docs article pages, product detail pages, blog posts)
• Save the final route graph to docs/research/<hostname>/SITE_MAP.md
• For large families, create a representative sample list and a data extraction plan rather than blindly hand-building each page one at a time

Page Topology

For each discovered page, map out every distinct section from top to bottom. Give each a working name. Document:

• Their visual order
• Which are fixed/sticky overlays vs. flow content
• The overall page layout (scroll container, column structure, z-index layers)
• Dependencies between sections (e.g., a floating nav that overlays everything)
• The interaction model of each section (static, click-driven, scroll-driven, time-driven)

Save this as docs/research/<hostname>/<route-slug>/PAGE_TOPOLOGY.md when multiple pages are involved, or docs/research/PAGE_TOPOLOGY.md for a single-page clone — it becomes your assembly blueprint.

Phase 2: Foundation Build

This is sequential. Do it yourself (not delegated to an agent) since it touches many files:

1. Update fonts in layout.tsx to match the target site's actual fonts
2. Update globals.css with the target's color tokens, spacing values, keyframe animations, utility classes, and any global scroll behaviors (Lenis, smooth scroll CSS, scroll-snap on body)
3. Create shared layout primitives — route shell, header, footer, navigation, breadcrumbs, and any shared page chrome used across multiple routes
4. Create TypeScript interfaces in src/types/ for the content structures and route families you've observed
5. Plan the Next.js route tree — map discovered URLs onto src/app/ routes, route groups, dynamic segments, and shared layouts before dispatching page builders
6. Extract SVG icons — find all inline <svg> elements on the page, deduplicate them, and save as named React components in src/components/icons.tsx. Name them by visual function (e.g., SearchIcon, ArrowRightIcon, LogoIcon).
7. Download global assets — write and run a Node.js script (scripts/download-assets.mjs) that downloads all images, videos, and other binary assets from the page to public/. Preserve meaningful directory structure.
8. Verify: npm run build passes

Asset Discovery Script Pattern

Use browser MCP to enumerate all assets on the page:

// Run this via browser MCP to discover all assets
JSON.stringify({
  images: [...document.querySelectorAll('img')].map(img => ({
    src: img.src || img.currentSrc,
    alt: img.alt,
    width: img.naturalWidth,
    height: img.naturalHeight,
    // Include parent info to detect layered compositions
    parentClasses: img.parentElement?.className,
    siblings: img.parentElement ? [...img.parentElement.querySelectorAll('img')].length : 0,
    position: getComputedStyle(img).position,
    zIndex: getComputedStyle(img).zIndex
  })),
  videos: [...document.querySelectorAll('video')].map(v => ({
    src: v.src || v.querySelector('source')?.src,
    poster: v.poster,
    autoplay: v.autoplay,
    loop: v.loop,
    muted: v.muted
  })),
  backgroundImages: [...document.querySelectorAll('*')].filter(el => {
    const bg = getComputedStyle(el).backgroundImage;
    return bg && bg !== 'none';
  }).map(el => ({
    url: getComputedStyle(el).backgroundImage,
    element: el.tagName + '.' + el.className?.split(' ')[0]
  })),
  svgCount: document.querySelectorAll('svg').length,
  fonts: [...new Set([...document.querySelectorAll('*')].slice(0, 200).map(el => getComputedStyle(el).fontFamily))],
  favicons: [...document.querySelectorAll('link[rel*="icon"]')].map(l => ({ href: l.href, sizes: l.sizes?.toString() }))
});

Then write a download script that fetches everything to public/. Use batched parallel downloads (4 at a time) with proper error handling.

Phase 3: Component Specification & Dispatch

This is the core loop. Work page family by page family, then section by section. For each discovered route, you do THREE things: extract, write the spec file, then dispatch builders.

Start with shared templates before leaf pages:

• Build the global app shell and navigation once
• Build route-family templates next (for example docs index, docs article, pricing, blog index, blog post, product listing, product detail)
• Finally build page-specific exceptions that do not fit an existing template

If ten pages share one template, do not dispatch ten unrelated builders. Dispatch one builder for the shared template and one data-extraction task for the per-page content.

Step 1: Extract

For each page section, use browser MCP to extract everything:

1. Screenshot the section in isolation (scroll to it, screenshot the viewport). Save to docs/design-references/.

2. Extract CSS for every element in the section. Use the extraction script below — don't hand-measure individual properties. Run it once per component container and capture the full output:

// Per-component extraction — run via browser MCP
// Replace SELECTOR with the actual CSS selector for the component
(function(selector) {
  const el = document.querySelector(selector);
  if (!el) return JSON.stringify({ error: 'Element not found: ' + selector });
  const props = [
    'fontSize','fontWeight','fontFamily','lineHeight','letterSpacing','color',
    'textTransform','textDecoration','backgroundColor','background',
    'padding','paddingTop','paddingRight','paddingBottom','paddingLeft',
    'margin','marginTop','marginRight','marginBottom','marginLeft',
    'width','height','maxWidth','minWidth','maxHeight','minHeight',
    'display','flexDirection','justifyContent','alignItems','gap',
    'gridTemplateColumns','gridTemplateRows',
    'borderRadius','border','borderTop','borderBottom','borderLeft','borderRight',
    'boxShadow','overflow','overflowX','overflowY',
    'position','top','right','bottom','left','zIndex',
    'opacity','transform','transition','cursor',
    'objectFit','objectPosition','mixBlendMode','filter','backdropFilter',
    'whiteSpace','textOverflow','WebkitLineClamp'
  ];
  function extractStyles(element) {
    const cs = getComputedStyle(element);
    const styles = {};
    props.forEach(p => { const v = cs[p]; if (v && v !== 'none' && v !== 'normal' && v !== 'auto' && v !== '0px' && v !== 'rgba(0, 0, 0, 0)') styles[p] = v; });
    return styles;
  }
  function walk(element, depth) {
    if (depth > 4) return null;
    const children = [...element.children];
    return {
      tag: element.tagName.toLowerCase(),
      classes: element.className?.toString().split(' ').slice(0, 5).join(' '),
      text: element.childNodes.length === 1 && element.childNodes[0].nodeType === 3 ? element.textContent.trim().slice(0, 200) : null,
      styles: extractStyles(element),
      images: element.tagName === 'IMG' ? { src: element.src, alt: element.alt, naturalWidth: element.naturalWidth, naturalHeight: element.naturalHeight } : null,
      childCount: children.length,
      children: children.slice(0, 20).map(c => walk(c, depth + 1)).filter(Boolean)
    };
  }
  return JSON.stringify(walk(el, 0), null, 2);
})('SELECTOR');

3. Extract multi-state styles — for any element with multiple states (scroll-triggered, hover, active tab), capture BOTH states:

// State A: capture styles at current state (e.g., scroll position 0)
// Then trigger the state change (scroll, click, hover via browser MCP)
// State B: re-run the extraction script on the same element
// The diff between A and B IS the behavior specification

Record the diff explicitly: "Property X changes from VALUE_A to VALUE_B, triggered by TRIGGER, with transition: TRANSITION_CSS."

For animation-heavy sections, also capture:

• duration
• delay
• easing / cubic-bezier
• transform origin
• keyframe names or motion variants
• whether motion is one-shot, looped, staggered, or scroll-scrubbed
• whether the source uses CSS, WAAPI, requestAnimationFrame, canvas, video, or a motion library

4. Extract real content — all text, alt attributes, aria labels, placeholder text. Use element.textContent for each text node. For tabbed/stateful content, click each tab and extract content per state.

5. Identify assets this section uses — which downloaded images/videos from public/, which icon components from icons.tsx. Check for layered images (multiple <img> or background-images stacked in the same container).

6. Assess complexity — how many distinct sub-components does this section contain? A distinct sub-component is an element with its own unique styling, structure, and behavior (e.g., a card, a nav item, a search panel).

Step 2: Write the Component Spec File

For each section (or sub-component, if you're breaking it up), create a spec file in docs/research/components/ or a page-scoped equivalent. This is NOT optional — every builder must have a corresponding spec file.

File path: docs/research/<hostname>/<route-slug>/components/<component-name>.spec.md for multi-page clones, or docs/research/components/<component-name>.spec.md for a single-page clone

Template:

# <ComponentName> Specification

## Overview
- **Target file:** `src/components/<ComponentName>.tsx`
- **Screenshot:** `docs/design-references/<screenshot-name>.png`
- **Interaction model:** <static | click-driven | scroll-driven | time-driven>

## DOM Structure
<Describe the element hierarchy — what contains what>

## Computed Styles (exact values from getComputedStyle)

### Container
- display: ...
- padding: ...
- maxWidth: ...
- (every relevant property with exact values)

### <Child element 1>
- fontSize: ...
- color: ...
- (every relevant property)

### <Child element N>
...

## States & Behaviors

### <Behavior name, e.g., "Scroll-triggered floating mode">
- **Trigger:** <exact mechanism — scroll position 50px, IntersectionObserver rootMargin "-30% 0px", click on .tab-button, hover>
- **State A (before):** maxWidth: 100vw, boxShadow: none, borderRadius: 0
- **State B (after):** maxWidth: 1200px, boxShadow: 0 4px 20px rgba(0,0,0,0.1), borderRadius: 16px
- **Transition:** transition: all 0.3s ease
- **Implementation approach:** <CSS transition + scroll listener | IntersectionObserver | CSS animation-timeline | etc.>
- **Motion fidelity note:** <exact enough with CSS only | requires Framer Motion | requires GSAP timeline | requires canvas/video fallback>

### Hover states
- **<Element>:** <property>: <before> → <after>, transition: <value>

## Per-State Content (if applicable)

### State: "Featured"
- Title: "..."
- Subtitle: "..."
- Cards: [{ title, description, image, link }, ...]

### State: "Productivity"
- Title: "..."
- Cards: [...]

## Assets
- Background image: `public/images/<file>.webp`
- Overlay image: `public/images/<file>.png`
- Icons used: <ArrowIcon>, <SearchIcon> from icons.tsx

## Text Content (verbatim)
<All text content, copy-pasted from the live site>

## Responsive Behavior
- **Desktop XL (1440px):** <layout description>
- **Desktop (1280px):** <what changes>
- **Laptop (1024px):** <what changes>
- **Tablet landscape (820px):** <what changes>
- **Tablet portrait (768px):** <what changes>
- **Large mobile (430px):** <what changes>
- **Mobile (390px):** <what changes>
- **Small mobile (375px):** <what changes>
- **Narrow mobile (360px):** <what changes>
- **Breakpoints:** <exact breakpoint ranges and what changes in each range>

Fill every section. If a section doesn't apply (e.g., no states for a static footer), write "N/A" — but think twice before marking States & Behaviors as N/A. Even a footer might have hover states on links.

Step 3: Dispatch Builders

Based on complexity, dispatch builder agent(s) in worktree(s):

Simple section (1-2 sub-components): One builder agent gets the entire section.

Complex section (3+ distinct sub-components): Break it up. One agent per sub-component, plus one agent for the section wrapper that imports them. Sub-component builders go first since the wrapper depends on them.

What every builder agent receives:

• The full contents of its component spec file (inline in the prompt — don't say "go read the spec file")
• Path to the section screenshot in docs/design-references/
• Which shared components to import (icons.tsx, cn(), shadcn primitives)
• The target file path (e.g., src/components/HeroSection.tsx)
• Instruction to verify with npx tsc --noEmit before finishing
• For responsive behavior: the specific breakpoint values and what changes

Don't wait. As soon as you've dispatched the builder(s) for one section, move to extracting the next section. Builders work in parallel in their worktrees while you continue extraction.

Step 4: Merge

As builder agents complete their work:

• Merge their worktree branches into main
• You have full context on what each agent built, so resolve any conflicts intelligently
• After each merge, verify the build still passes: npm run build
• If a merge introduces type errors, fix them immediately

The extract → spec → dispatch → merge cycle continues until all sections are built.

Phase 4: Page Assembly

After all sections are built and merged, wire everything together in the Next.js route tree:

• Create the required src/app/ pages, layouts, route groups, and dynamic segments for every discovered internal route
• Import all shared shell and page section components
• Implement each page-level layout from its topology doc (scroll containers, column structures, sticky positioning, z-index layering)
• Connect real content to component props or route data files
• Implement page-level behaviors: scroll snap, scroll-driven animations, dark-to-light transitions, intersection observers, smooth scroll (Lenis etc.)
• Verify: npm run build passes clean

Phase 5: Visual QA Diff

After assembly, do NOT declare the clone complete. Take side-by-side comparison screenshots for the homepage and representative child pages:

1. Open the original site and your clone side-by-side (or take screenshots at the same viewport widths)
2. Compare section by section, top to bottom, at 1440px, 1280px, 1024px, 820px, 768px, 430px, 390px, 375px, and 360px
3. For route families, spot-check at least one representative child page per family at the same viewport matrix
4. For each discrepancy found:
   • Check the component spec file — was the value extracted correctly?
   • If the spec was wrong: re-extract from browser MCP, update the spec, fix the component
   • If the spec was right but the builder got it wrong: fix the component to match the spec
5. Test all interactive behaviors: scroll through the page, click every button/tab, hover over interactive elements
6. Verify smooth scroll feels right, header transitions work, tab switching works, animations play at the correct speed/easing, and no layout shifts or crop regressions appear across the viewport matrix
7. If the source uses a motion library or canvas/video-driven effect, verify the implementation approach still matches the perceived behavior instead of silently replacing it with a generic fade/slide

Only after this visual QA pass is the clone complete.

Pre-Dispatch Checklist

Before dispatching ANY builder agent, verify you can check every box. If you can't, go back and extract more.

• Spec file written to docs/research/components/<name>.spec.md with ALL sections filled
• Every CSS value in the spec is from getComputedStyle(), not estimated
• Interaction model is identified and documented (static / click / scroll / time)
• For stateful components: every state's content and styles are captured
• For scroll-driven components: trigger threshold, before/after styles, and transition are recorded
• For hover states: before/after values and transition timing are recorded
• All images in the section are identified (including overlays and layered compositions)
• Responsive behavior is documented for 1440, 1280, 1024, 820, 768, 430, 390, 375, and 360
• Motion details are documented with timing, easing, trigger, and implementation approach
• Text content is verbatim from the site, not paraphrased
• The builder prompt is under ~150 lines of spec; if over, the section needs to be split

What NOT to Do

These are lessons from previous failed clones — each one cost hours of rework:

• Don't build click-based tabs when the original is scroll-driven (or vice versa). Determine the interaction model FIRST by scrolling before clicking. This is the #1 most expensive mistake — it requires a complete rewrite, not a CSS fix.
• Don't extract only the default state. If there are tabs showing "Featured" on load, click Productivity, Creative, Lifestyle and extract each one's cards/content. If the header changes on scroll, capture styles at position 0 AND position 100+.
• Don't miss overlay/layered images. A background watercolor + foreground UI mockup = 2 images. Check every container's DOM tree for multiple <img> elements and positioned overlays.
• Don't build mockup components for content that's actually videos/animations. Check if a section uses <video>, Lottie, or canvas before building elaborate HTML mockups of what the video shows.
• Don't approximate CSS classes. "It looks like text-lg" is wrong if the computed value is 18px and text-lg is 18px/28px but the actual line-height is 24px. Extract exact values.
• Don't build everything in one monolithic commit. The whole point of this pipeline is incremental progress with verified builds at each step.
• Don't reference docs from builder prompts. Each builder gets the CSS spec inline in its prompt — never "see DESIGN_TOKENS.md for colors." The builder should have zero need to read external docs.
• Don't skip asset extraction. Without real images, videos, and fonts, the clone will always look fake regardless of how perfect the CSS is.
• Don't give a builder agent too much scope. If you're writing a builder prompt and it's getting long because the section is complex, that's a signal to break it into smaller tasks.
• Don't bundle unrelated sections into one agent. A CTA section and a footer are different components with different designs — don't hand them both to one agent and hope for the best.
• Don't skip responsive extraction. If you only inspect at desktop width, the clone will break at tablet and mobile. Test at 1440, 1280, 1024, 820, 768, 430, 390, 375, and 360 during extraction.
• Don't replace complex motion with generic fades. If the source uses Framer Motion, GSAP, Lottie, video, canvas, or scrubbed scroll animation, document that explicitly and reproduce the perceived behavior as closely as possible.
• Don't forget smooth scroll libraries. Check for Lenis (.lenis class), Locomotive Scroll, or similar. Default browser scrolling feels noticeably different and the user will spot it immediately.
• Don't dispatch builders without a spec file. The spec file forces exhaustive extraction and creates an auditable artifact. Skipping it means the builder gets whatever you can fit in a prompt from memory.

Completion

When done, report:

• Total sections built
• Total components created
• Total spec files written (should match components)
• Total assets downloaded (images, videos, SVGs, fonts)
• Build status (npm run build result)
• Visual QA results (any remaining discrepancies)
• Any known gaps or limitations