launchframe 0.4.1 → 0.4.3

package/README.md

@@ -2,7 +2,7 @@
 
 <a href="https://github.com/JCodesMore/ai-website-cloner-template/blob/master/LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue" alt="MIT License" /></a> <a href="https://github.com/JCodesMore/ai-website-cloner-template/stargazers"><img src="https://img.shields.io/github/stars/JCodesMore/ai-website-cloner-template?style=flat" alt="Stars" /></a> <a href="https://discord.gg/hrTSX5yTpB"><img src="https://img.shields.io/discord/1400896964597383279?label=discord" alt="Discord" /></a>
 
-Scaffold a Next.js + shadcn/ui project from **a reference URL you want to copy** plus **your SaaS idea** that drives landing-page positioning. Use **`npx launchframe@latest`** or the slash command **`/launchframe <url> "your idea"`** to scaffold, then run **`/clone-website`** so your AI agent reverse-engineers the reference layout while preserving your messaging inputs (`launchframe.context.json`, `docs/research/LAUNCHFRAME.md`, `src/lib/launchframe-config.ts`).
+**`/launchframe`** — full pixel-perfect reverse-engineer of the reference page **plus** a SaaS pitch (two parameters: URL and quoted idea). Config is stored in `src/lib/launchframe-config.ts`, `launchframe.context.json`, and `docs/research/LAUNCHFRAME.md`. **CLI:** **`npx launchframe@latest`** (no args) only **unpacks this template** into an empty directory; then run **`/launchframe <url> "…"`** in that project.
 
 **Recommended: [Claude Code](https://docs.anthropic.com/en/docs/claude-code) with Opus 4.7 for best results** — but works with a variety of AI coding agents.
 
@@ -14,45 +14,36 @@ Scaffold a Next.js + shadcn/ui project from **a reference URL you want to copy**
 
 ## Quick Start
 
-### AI agents (slash command)
+### 1. New project (empty folder)
 
-In Cursor, Claude Code, Continue, and other synced tools:
-
-```text
-/launchframe https://example.com "Your SaaS idea in plain language"
-```
-
-The agent runs **`npx launchframe@latest`** with those arguments (see `.cursor/commands/launchframe.md`). Output must be **outside** the template package directory when developing from a clone of this repo — use `--dir ../my-app` or an absolute path.
-
-### CLI (same as slash command)
-
-From an empty folder (or anywhere you want the project folder created):
+Create an **empty** directory, go into it, run the CLI with **no parameters** — files are written to **that folder** (your project root):
 
 ```bash
-npx launchframe@latest https://example.com "Your SaaS idea in plain language"
+mkdir my-app
+cd my-app
+npx launchframe@latest
 ```
 
-Scaffolding copies the full template at the repository root — including **hidden agent config** (for example `.cursor/`, `.claude/`, `.github/`, `.amazonq/`, `.augment/`, and other dotfiles) so tools see the same rules and commands as this template.
+Optional: set `LAUNCHFRAME_SOURCE_URL` and `LAUNCHFRAME_SAAS_IDEA` in the environment before running to pre-fill config without editing files.
 
-Optional flags:
+Then run `npm run dev` and your agent with **`/launchframe <url> "your saas idea"`**.
 
-- `--dir my-app` / `-o my-app` — output folder name (default: `<hostname>-launchframe`)
-- `--skip-install` — scaffold files only; run `npm install` yourself
+### AI agents
 
-Then:
+Use **`/launchframe <url> "saas idea"`** — the only clone workflow for this template (URL + SaaS positioning; full extraction/build pipeline).
 
-```bash
-cd <your-project-folder>
-npm run dev
-```
+To start from zero files in a folder, run **`npx launchframe@latest`** once, then **`/launchframe`** in that project.
+
+### Optional flags
 
-Open your AI agent and run `/clone-website <same-reference-url>` so it rebuilds the reference site into components while aligning hero copy with your SaaS idea files above.
+- `--dir path` / `-o path` — scaffold into another folder instead of the current directory (must be empty)
+- `--skip-install` — skip `npm install`
 
 ### Git template (advanced)
 
 1. Clone this repository and `npm install`
-2. Replace `src/lib/launchframe-config.ts` or run `npx launchframe@latest ...` into a fresh folder
-3. Run `/clone-website <target-url>` from your agent
+2. Point `src/lib/launchframe-config.ts` at your site, or create a sibling folder and run **`npx launchframe@latest`** there
+3. Run **`/launchframe <url> "saas idea"`** from your agent
 
 > Using a different agent? Open `AGENTS.md` for project instructions — most agents pick it up automatically.
 
@@ -88,7 +79,7 @@ Open your AI agent and run `/clone-website <same-reference-url>` so it rebuilds
 
 ## How It Works
 
-The `/clone-website` skill runs a multi-phase pipeline:
+The **`/launchframe`** skill runs a multi-phase pipeline:
 
 1. **Reconnaissance** — screenshots, design token extraction, interaction sweep (scroll, click, hover, responsive)
 2. **Foundation** — updates fonts, colors, globals, downloads all assets
@@ -130,7 +121,7 @@ docs/
   design-references/ # Screenshots
 scripts/
   sync-agent-rules.sh  # Regenerate agent instruction files
-  sync-skills.mjs      # Regenerate /clone-website for all platforms
+  sync-skills.mjs      # Regenerate /launchframe for all platforms
 AGENTS.md           # Agent instructions (single source of truth)
 CLAUDE.md           # Claude Code config (imports AGENTS.md)
 GEMINI.md           # Gemini CLI config (imports AGENTS.md)
@@ -160,7 +151,7 @@ Two source-of-truth files power all platform support. Edit the source, then run
 | What                   | Source of truth                         | Sync command                       |
 | ---------------------- | --------------------------------------- | ---------------------------------- |
 | Project instructions   | `AGENTS.md`                             | `bash scripts/sync-agent-rules.sh` |
-| `/clone-website` skill | `.claude/skills/clone-website/SKILL.md` | `node scripts/sync-skills.mjs`     |
+| `/launchframe` skill | `.claude/skills/launchframe/SKILL.md` | `node scripts/sync-skills.mjs`     |
 
 Each script regenerates the platform-specific copies automatically. Agents that read the source files natively need no regeneration.
 

package/bin/launchframe.mjs

@@ -1,21 +1,26 @@
 #!/usr/bin/env node
 /**
- * Scaffold a Launchframe project: clone reference URL via AI workflow + SaaS landing copy.
- * Usage: npx launchframe@latest <url> "<saas-idea>" [--dir=name] [--skip-install]
+ * Scaffold a Launchframe project into the current directory (or --dir).
+ * Usage: npx launchframe@latest [--dir=path] [--skip-install]
+ * Optional: LAUNCHFRAME_SOURCE_URL, LAUNCHFRAME_SAAS_IDEA env vars, or legacy CLI args.
  */
 
-import { cp, mkdir, readdir, readFile, writeFile } from "fs/promises";
+import { cp, mkdir, readdir, readFile, stat, writeFile } from "fs/promises";
 import { spawn } from "node:child_process";
-import { dirname, isAbsolute, join, relative, resolve } from "node:path";
+import { basename, dirname, isAbsolute, join, relative, resolve } from "node:path";
 import { fileURLToPath } from "node:url";
 
 const __dirname = dirname(fileURLToPath(import.meta.url));
 const PKG_ROOT = resolve(__dirname, "..");
 
+const DEFAULT_URL = "https://example.com";
+const DEFAULT_SAAS_IDEA =
+  "Edit your SaaS pitch in src/lib/launchframe-config.ts, then run /launchframe with your reference URL and the same pitch.";
+
 /**
  * Never copy these root entries into a scaffolded app (build artifacts, VCS, the CLI itself).
  * All other root files and folders are copied as-is — including every dotfile and dot-directory
- * so AI agents see the same agent rules, skills, and IDE metadata as this template.
+ * so AI agents see the same agent rules and commands as this template.
  */
 const SKIP_DIR_NAMES = new Set([
   "bin",
@@ -34,29 +39,44 @@ const SKIP_ROOT_FILES = new Set([
   "Thumbs.db",
 ]);
 
+async function pathExists(p) {
+  try {
+    await stat(p);
+    return true;
+  } catch {
+    return false;
+  }
+}
+
 function printHelp() {
   console.log(`
-launchframe — scaffold a Next.js app for cloning a reference site + your SaaS idea
+launchframe — scaffold a Next.js app into the current directory (project root)
 
 Usage:
-  npx launchframe@latest <url> "<saas-idea>" [options]
+  npx launchframe@latest
 
-Arguments:
-  <url>           HTTPS URL of the site to reverse-engineer (visual reference)
-  "<saas-idea>"   Short pitch / positioning that should appear on the landing page
+This unpacks the template into the folder you are in (where you ran the command).
+No URL or SaaS arguments are required — edit src/lib/launchframe-config.ts after scaffold.
+
+Optional environment variables (same session):
+  LAUNCHFRAME_SOURCE_URL     Reference site to clone later (https://...)
+  LAUNCHFRAME_SAAS_IDEA     Short landing-page pitch text
+
+Legacy (optional positional args, for scripts only):
+  npx launchframe@latest <url> "<saas-idea>"
 
 Options:
-  --dir, -o       Output folder (default: first label of hostname + "-launchframe")
+  --dir, -o       Scaffold into this folder instead of the current directory (must be empty)
   --skip-install  Do not run npm install after scaffolding
   -h, --help      Show this message
 
 Note:
-  The output folder must not live inside the Launchframe package directory (the folder that contains this CLI).
-  Scaffolding copies every root file and folder from the template (including dotfiles such as .cursor, .claude,
-  .github, etc.) except build/cache directories, so your AI tools see the same rules and commands as upstream.
+  Run inside an empty project folder (no existing package.json / src / next.config).
+  The output folder must not be inside the Launchframe npm package directory.
 
 Example:
-  npx launchframe@latest https://stripe.com "AI invoicing for freelancers"
+  mkdir my-app && cd my-app
+  npx launchframe@latest
 `);
 }
 
@@ -114,20 +134,8 @@ function validateUrl(raw) {
   return u.href;
 }
 
-function defaultDirName(urlStr) {
-  try {
-    const host = new URL(urlStr).hostname.replace(/^www\./i, "");
-    const label = host.split(".")[0] || "site";
-    const safe = label.replace(/[^a-zA-Z0-9-_]/g, "-").toLowerCase();
-    return `${safe || "site"}-launchframe`;
-  } catch {
-    return "launchframe-app";
-  }
-
-}
-
-function slugFromDir(dir) {
-  const base = dir.replace(/\\/g, "/").split("/").filter(Boolean).pop() ?? "launchframe-app";
+function slugFromDir(destRootAbs) {
+  const base = basename(resolve(destRootAbs));
   return base
     .toLowerCase()
     .replace(/[^a-z0-9-_]/g, "-")
@@ -193,7 +201,8 @@ async function writeGeneratedPackageJson(destRoot, npmPackageName) {
 
 async function writeLaunchframeArtifacts(destRoot, url, idea) {
   const configTs = `/**
- * Written by Launchframe CLI — edit freely after scaffolding.
+ * Set your reference site and positioning, then use /launchframe with the same URL and SaaS idea.
+ * Written by Launchframe CLI — edit freely.
  */
 export const LAUNCHFRAME_SOURCE_URL = ${tsStringLiteral(url)} as const;
 
@@ -206,7 +215,7 @@ export const LAUNCHFRAME_SAAS_IDEA = ${tsStringLiteral(idea)} as const;
     sourceUrl: url,
     saasIdea: idea,
     notes:
-      "Use /clone-website with sourceUrl for pixel-perfect extraction. Align landing copy with saasIdea.",
+      "Edit this file or src/lib/launchframe-config.ts. Use /launchframe with sourceUrl and your SaaS idea for pixel-perfect extraction.",
   };
   await writeFile(
     join(destRoot, "launchframe.context.json"),
@@ -224,7 +233,7 @@ ${url}
 
 ${idea}
 
-When running \`/clone-website\`, pass the reference URL above. After structural cloning, rewrite headings and hero copy so they clearly communicate the SaaS idea while respecting attribution and copyright for third-party brands.
+When running \`/launchframe\` with your agent, use the reference URL above and align hero copy with your SaaS idea while respecting attribution and copyright for third-party brands.
 `;
 
   await mkdir(join(destRoot, "docs", "research"), { recursive: true });
@@ -236,7 +245,14 @@ async function writeReadme(destRoot, npmPackageName, url, idea) {
 
 Created with [\`launchframe\`](https://www.npmjs.com/package/launchframe).
 
-## Inputs
+## Configure
+
+Edit \`src/lib/launchframe-config.ts\`:
+
+- \`LAUNCHFRAME_SOURCE_URL\` — site to reverse-engineer
+- \`LAUNCHFRAME_SAAS_IDEA\` — landing copy / positioning
+
+Current values (from scaffold):
 
 - **Reference site:** ${url}
 - **SaaS idea:** ${idea}
@@ -248,13 +264,7 @@ npm install
 npm run dev
 \`\`\`
 
-Open your AI agent (Cursor, Claude Code, etc.) and run:
-
-\`\`\`
-/clone-website ${url}
-\`\`\`
-
-Keep the SaaS positioning from \`launchframe.context.json\` / \`src/lib/launchframe-config.ts\` when adapting cloned sections.
+Open your AI agent and run \`/launchframe <your-reference-url> "your pitch"\` (same values as in the config).
 
 See \`AGENTS.md\` for full agent instructions.
 `;
@@ -262,6 +272,21 @@ See \`AGENTS.md\` for full agent instructions.
   await writeFile(join(destRoot, "README.md"), body, "utf8");
 }
 
+/** Refuse to stomp an existing Next-style project in the target directory. */
+async function assertScaffoldTargetVacant(destRoot) {
+  const conflicts = ["package.json", "next.config.ts", "src"];
+  for (const c of conflicts) {
+    if (await pathExists(join(destRoot, c))) {
+      console.error(
+        `Refusing to scaffold: "${c}" already exists in this folder.\n` +
+          `Create a new empty directory, cd into it, then run:\n` +
+          `  npx launchframe@latest\n`,
+      );
+      process.exit(1);
+    }
+  }
+}
+
 function runNpmInstall(cwd) {
   return new Promise((resolvePromise, reject) => {
     const child = spawn("npm", ["install"], {
@@ -277,6 +302,17 @@ function runNpmInstall(cwd) {
   });
 }
 
+function resolveUrlAndIdea(args) {
+  const envUrl =
+    process.env.LAUNCHFRAME_SOURCE_URL?.trim() || process.env.LAUNCHFRAME_URL?.trim();
+  const envIdea = process.env.LAUNCHFRAME_SAAS_IDEA?.trim();
+
+  let urlRaw = args.url?.trim() || envUrl || DEFAULT_URL;
+  let ideaRaw = args.idea?.trim() || envIdea || DEFAULT_SAAS_IDEA;
+
+  return { urlRaw, ideaRaw };
+}
+
 async function main() {
   const args = parseArgs(process.argv.slice(2));
   if (args.help) {
@@ -284,36 +320,31 @@ async function main() {
     process.exit(0);
   }
 
-  if (!args.url || !args.idea) {
-    console.error("Error: missing URL or SaaS idea.\n");
-    printHelp();
+  const destRoot = args.dir?.trim()
+    ? resolve(process.cwd(), args.dir.trim())
+    : resolve(process.cwd());
+
+  if (isForbiddenOutput(PKG_ROOT, destRoot)) {
+    console.error(
+      "Output folder cannot be inside the Launchframe package directory. Create a new folder outside this package and cd into it, then run npx launchframe@latest again.",
+    );
     process.exit(1);
   }
 
+  await assertScaffoldTargetVacant(destRoot);
+
+  const { urlRaw, ideaRaw } = resolveUrlAndIdea(args);
+
   let url;
   try {
-    url = validateUrl(args.url);
+    url = validateUrl(urlRaw);
   } catch (e) {
     console.error(String(e.message));
     process.exit(1);
   }
 
-  const idea = args.idea.trim();
-  if (!idea) {
-    console.error("Error: SaaS idea cannot be empty.");
-    process.exit(1);
-  }
-
-  const dirName = args.dir?.trim() || defaultDirName(url);
-  const destRoot = resolve(process.cwd(), dirName);
-  const npmPackageName = slugFromDir(dirName);
-
-  if (isForbiddenOutput(PKG_ROOT, destRoot)) {
-    console.error(
-      "Output folder cannot be inside the Launchframe package directory. Run from a parent folder or choose another path.",
-    );
-    process.exit(1);
-  }
+  const idea = ideaRaw.trim() || DEFAULT_SAAS_IDEA;
+  const npmPackageName = slugFromDir(destRoot);
 
   await mkdir(destRoot, { recursive: true });
 
@@ -323,22 +354,23 @@ async function main() {
   await writeLaunchframeArtifacts(destRoot, url, idea);
   await writeReadme(destRoot, npmPackageName, url, idea);
 
-  console.log(`\nCreated Launchframe project at ${destRoot}`);
+  console.log(`\nScaffolded Launchframe in:\n  ${destRoot}`);
   console.log(`  Reference URL: ${url}`);
   console.log(`  SaaS idea: ${idea}\n`);
+  console.log("Edit src/lib/launchframe-config.ts if you need different values.\n");
 
   if (!args.skipInstall) {
     console.log("Running npm install...\n");
     try {
       await runNpmInstall(destRoot);
-      console.log("\nDone. Next: cd " + JSON.stringify(dirName) + " && npm run dev\n");
+      console.log("\nDone. From this folder: npm run dev\n");
     } catch (e) {
       console.error(String(e.message));
-      console.error("\nDependencies were not installed. Run npm install inside the folder manually.\n");
+      console.error("\nRun npm install in this folder manually.\n");
       process.exit(1);
     }
   } else {
-    console.log("Skipped npm install (--skip-install). Run npm install inside the folder.\n");
+    console.log("Skipped npm install (--skip-install). Run npm install in this folder.\n");
   }
 }
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "launchframe",
-  "version": "0.4.1",
+  "version": "0.4.3",
   "private": false,
   "description": "Scaffold a Next.js app from a reference URL plus your SaaS idea — AI-ready website cloning",
   "author": "JCodesMore",

package/scripts/sync-skills.mjs

@@ -14,20 +14,13 @@ import { fileURLToPath } from "node:url";
 const ROOT = join(dirname(fileURLToPath(import.meta.url)), "..");
 
 const SKILLS = [
-  {
-    id: "clone-website",
-    sourceRel: ".claude/skills/clone-website/SKILL.md",
-    shortDesc: "Reverse-engineer and clone any website as a pixel-perfect replica",
-    plainSubstitution: "the target URL provided by the user",
-    augmentArgumentHint: "<url>",
-  },
   {
     id: "launchframe",
     sourceRel: ".claude/skills/launchframe/SKILL.md",
     shortDesc:
-      "Scaffold a Next.js app with npx launchframe@latest from a reference URL and SaaS idea",
+      "Reverse-engineer a reference URL into this repo + SaaS landing copy — /launchframe",
     plainSubstitution:
-      "the reference URL and SaaS idea from the user (see slash command arguments)",
+      "the reference URL(s) and SaaS idea the user passed with /launchframe",
     augmentArgumentHint: "<url> \"<saas-idea>\"",
   },
 ];
@@ -121,4 +114,4 @@ for (const skill of SKILLS) {
 }
 
 const totalFiles = SKILLS.length * 9;
-console.log(`\nDone! ${totalFiles} platform files generated (${SKILLS.length} skills \u00d7 9 targets).`);
+console.log(`\nDone! ${totalFiles} platform files generated (${SKILLS.length} skill(s) \u00d7 9 targets).`);

package/src/app/page.tsx

@@ -29,7 +29,7 @@ export default function Home() {
         <p className="text-pretty text-sm text-muted-foreground">
           Run{" "}
           <code className="rounded-md bg-muted px-2 py-1 font-mono text-foreground">
-            /clone-website {LAUNCHFRAME_SOURCE_URL}
+            /launchframe {LAUNCHFRAME_SOURCE_URL} &quot;…your saas idea…&quot;
           </code>{" "}
           with your AI agent to rebuild this layout from the reference site while keeping the SaaS
           positioning above.

package/src/lib/launchframe-config.ts

@@ -1,8 +1,7 @@
 /**
- * Defaults for local development before running `npx launchframe`.
- * The Launchframe CLI overwrites this file in scaffolded projects.
+ * Defaults before scaffolding. After `npx launchframe@latest`, edit these values.
  */
 export const LAUNCHFRAME_SOURCE_URL = "https://example.com" as const;
 
 export const LAUNCHFRAME_SAAS_IDEA =
-  'Run `npx launchframe <url> "your SaaS idea"` to scaffold with real inputs.' as const;
+  "Edit your SaaS pitch here, then run /launchframe with LAUNCHFRAME_SOURCE_URL and the same pitch in quotes." as const;

package/.amazonq/cli-agents/clone-website.json

@@ -1,9 +0,0 @@
-{
-  "name": "clone-website",
-  "description": "Reverse-engineer and clone any website as a pixel-perfect replica",
-  "prompt": "\n# Clone Website\n\nYou are about to reverse-engineer and rebuild **the target URL provided by the user** as pixel-perfect clones.\n\nWhen 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>/`).\n\nThis 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.\n\n## Scope Defaults\n\nThe target is whatever page `the target URL provided by the user` resolves to. Clone exactly what's visible at that URL. Unless the user specifies otherwise, use these defaults:\n\n- **Fidelity level:** Pixel-perfect — exact match in colors, spacing, typography, animations\n- **In scope:** Visual layout and styling, component structure and interactions, responsive design, mock data for demo purposes\n- **Out of scope:** Real backend / database, authentication, real-time features, SEO optimization, accessibility audit\n- **Customization:** None — pure emulation\n\nIf the user provides additional instructions (specific fidelity level, customizations, extra context), honor those over the defaults.\n\n## Pre-Flight\n\n1. **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.\n2. 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.\n3. 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.\n4. 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>/`.\n5. 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.\n\n## Guiding Principles\n\nThese are the truths that separate a successful clone from a \"close enough\" mess. Internalize them — they should inform every decision you make.\n\n### 0. Visual crawl priority (images, SVGs, motion — first)\n\nWhen you traverse the DOM and the Network panel, do **not** treat all nodes equally. Work in this **priority order** so the clone feels like the original, not a wireframe:\n\n1. **Images (raster + video stills)** — Enumerate `<img>`, `<picture>`, responsive `srcset`, `data-*` lazy URLs, **computed `background-image`** on the element and parents (including pseudo-elements), mask images, `<video poster>`, hero media. **Scrape:** download binary assets to `public/images/` (or `public/videos/`) with stable paths referenced in specs. **Create** a replacement PNG/WebP/SVG only when the asset is blocked (CORS, auth cookie, 403), ephemeral, or impossible to URL-fetch — use a high-DPI screenshot crop, traced artwork, or CSS gradient approximation, and mark `ASSET_SOURCE: generated` in the component spec with a short reason.\n2. **SVGs & iconography** — Inline `<svg>`, sprite `symbol` defs, **SVG used as masks/filters**, icon fonts (prefer path extraction). Convert to `@/components/icons.tsx` (or section-local components) with meaningful names. Prioritize crisp edges and correct `viewBox` over shrinking bundle size during emulation.\n3. **Motion & animation** — CSS `@keyframes`, `animation`, `animation-timeline`, `transition`, `transform`, will-change hints; JS-driven motion (carousel timing, IntersectionObserver reveals); libraries (GSAP, Framer, Lottie JSON, Lenis). Capture **numbers** (ms, easing curves, stagger, scroll thresholds), not adjectives. Include **reduced-motion** behavior if present.\n\nOnly after the above are accounted for should you spend cycle time on minor text or non-visual refactors. A perfect grid with missing hero art and dead animation still fails the clone.\n\n### 1. Completeness Beats Speed\n\nEvery 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.\n\n### 2. Small Tasks, Perfect Results\n\nWhen 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.\n\nLook 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.\n\n**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.\"\n\n### 3. Real Content, Real Assets\n\nExtract 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.\n\n**Prioritize** (see §0): downloadable imagery and backgrounds first, then SVG/icon layers, then motion. If you must **fabricate** an asset, prefer screenshot-based exports or traced vectors tied to measured box sizes — avoid unrelated stock art.\n\n**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.\n\n### 4. Foundation First\n\nNothing 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.\n\n### 5. Extract How It Looks AND How It Behaves\n\nA 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.\n\nFor 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`).\n\nExamples 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:\n- A navbar that shrinks, changes background, or gains a shadow after scrolling past a threshold\n- Elements that animate into view when they enter the viewport (fade-up, slide-in, stagger delays)\n- Sections that snap into place on scroll (`scroll-snap-type`)\n- Parallax layers that move at different rates than the scroll\n- Hover states that animate (not just change — the transition duration and easing matter)\n- Dropdowns, modals, accordions with enter/exit animations\n- Scroll-driven progress indicators or opacity transitions\n- Auto-playing carousels or cycling content\n- Dark-to-light (or any theme) transitions between page sections\n- **Tabbed/pill content that cycles** — buttons that switch visible card sets with transitions\n- **Scroll-driven tab/accordion switching** — sidebars where the active item auto-changes as content scrolls past (IntersectionObserver, NOT click handlers)\n- **Smooth scroll libraries** (Lenis, Locomotive Scroll) — check for `.lenis` class or scroll container wrappers\n\n### 6. Identify the Interaction Model Before Building\n\nThis 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?**\n\nHow to determine this:\n1. **Don't click first.** Scroll through the section slowly and observe if things change on their own as you scroll.\n2. If they do, it's scroll-driven. Extract the mechanism: `IntersectionObserver`, `scroll-snap`, `position: sticky`, `animation-timeline`, or JS scroll listeners.\n3. If nothing changes on scroll, THEN click/hover to test for click/hover-driven interactivity.\n4. Document the interaction model explicitly in the component spec: \"INTERACTION MODEL: scroll-driven with IntersectionObserver\" or \"INTERACTION MODEL: click-to-switch with opacity transition.\"\n\nA 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.\n\n### 7. Extract Every State, Not Just the Default\n\nMany 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.\n\nFor tabbed/stateful content:\n- Click each tab/button via browser MCP\n- Extract the content, images, and card data for EACH state\n- Record which content belongs to which state\n- Note the transition animation between states (opacity, slide, fade, etc.)\n\nFor scroll-dependent elements:\n- Capture computed styles at scroll position 0 (initial state)\n- Scroll past the trigger threshold and capture computed styles again (scrolled state)\n- Diff the two to identify exactly which CSS properties change\n- Record the transition CSS (duration, easing, properties)\n- Record the exact trigger threshold (scroll position in px, or viewport intersection ratio)\n\n### 8. Spec Files Are the Source of Truth\n\nEvery 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.\n\nThe 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.\n\n### 9. Build Must Always Compile\n\nEvery 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.\n\n## Phase 1: Reconnaissance\n\nNavigate to the target URL with browser MCP.\n\nFollow **§0 (Visual crawl priority)** during the entire reconnaissance pass: images and backgrounds → SVGs/icons → motion/animations — before spending time on secondary copy tweaks.\n\n### Screenshots\n- Take **full-page screenshots** at desktop (1440px) and mobile (390px) viewports\n- Save to `docs/design-references/` with descriptive names\n- These are your master reference — builders will receive section-specific crops/screenshots later\n\n### Global Extraction\nExtract these from the page before doing anything else:\n\n**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`.\n\n**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.\n\n**Favicons & Meta** — Download favicons, apple-touch-icons, OG images, webmanifest to `public/seo/`. Update `layout.tsx` metadata.\n\n**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). Add these to `globals.css` and note any libraries that need to be installed.\n\n### Mandatory Interaction Sweep\n\nThis 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.\n\n**Scroll sweep:** Scroll the page slowly from top to bottom via browser MCP. At each section, pause and observe:\n- Does the header change appearance? Record the scroll position where it triggers.\n- Do elements animate into view? Record which ones and the animation type.\n- Does a sidebar or tab indicator auto-switch as you scroll? Record the mechanism.\n- Are there scroll-snap points? Record which containers.\n- Is there a smooth scroll library active? Check for non-native scroll behavior.\n\n**Click sweep:** Click every element that looks interactive:\n- Every button, tab, pill, link, card\n- Record what happens: does content change? Does a modal open? Does a dropdown appear?\n- For tabs/pills: click EACH ONE and record the content that appears for each state\n\n**Hover sweep:** Hover over every element that might have hover states:\n- Buttons, cards, links, images, nav items\n- Record what changes: color, scale, shadow, underline, opacity\n\n**Responsive sweep:** Test at 3 viewport widths via browser MCP:\n- Desktop: 1440px\n- Tablet: 768px\n- Mobile: 390px\n- At each width, note which sections change layout (column → stack, sidebar disappears, etc.) and at approximately which breakpoint the change occurs.\n\nSave all findings to `docs/research/BEHAVIORS.md`. This is your behavior bible — reference it when writing every component spec.\n\n### Page Topology\nMap out every distinct section of the page from top to bottom. Give each a working name. Document:\n- Their visual order\n- Which are fixed/sticky overlays vs. flow content\n- The overall page layout (scroll container, column structure, z-index layers)\n- Dependencies between sections (e.g., a floating nav that overlays everything)\n- **The interaction model** of each section (static, click-driven, scroll-driven, time-driven)\n\nSave this as `docs/research/PAGE_TOPOLOGY.md` — it becomes your assembly blueprint.\n\n## Phase 2: Foundation Build\n\nThis is sequential. Do it yourself (not delegated to an agent) since it touches many files:\n\n1. **Update fonts** in `layout.tsx` to match the target site's actual fonts\n2. **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)\n3. **Create TypeScript interfaces** in `src/types/` for the content structures you've observed\n4. **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`).\n5. **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.\n6. Verify: `npm run build` passes\n\n### Asset Discovery Script Pattern\n\nUse browser MCP to enumerate all assets on the page:\n\n```javascript\n// Run this via browser MCP to discover all assets\nJSON.stringify({\n  images: [...document.querySelectorAll('img')].map(img => ({\n    src: img.src || img.currentSrc,\n    alt: img.alt,\n    width: img.naturalWidth,\n    height: img.naturalHeight,\n    // Include parent info to detect layered compositions\n    parentClasses: img.parentElement?.className,\n    siblings: img.parentElement ? [...img.parentElement.querySelectorAll('img')].length : 0,\n    position: getComputedStyle(img).position,\n    zIndex: getComputedStyle(img).zIndex\n  })),\n  videos: [...document.querySelectorAll('video')].map(v => ({\n    src: v.src || v.querySelector('source')?.src,\n    poster: v.poster,\n    autoplay: v.autoplay,\n    loop: v.loop,\n    muted: v.muted\n  })),\n  backgroundImages: [...document.querySelectorAll('*')].filter(el => {\n    const bg = getComputedStyle(el).backgroundImage;\n    return bg && bg !== 'none';\n  }).map(el => ({\n    url: getComputedStyle(el).backgroundImage,\n    element: el.tagName + '.' + el.className?.split(' ')[0]\n  })),\n  svgCount: document.querySelectorAll('svg').length,\n  fonts: [...new Set([...document.querySelectorAll('*')].slice(0, 200).map(el => getComputedStyle(el).fontFamily))],\n  favicons: [...document.querySelectorAll('link[rel*=\"icon\"]')].map(l => ({ href: l.href, sizes: l.sizes?.toString() }))\n});\n```\n\nThen write a download script that fetches everything to `public/`. Use batched parallel downloads (4 at a time) with proper error handling.\n\n## Phase 3: Component Specification & Dispatch\n\nThis is the core loop. For each section in your page topology (top to bottom), you do THREE things: **extract**, **write the spec file**, then **dispatch builders**.\n\n### Step 1: Extract\n\nFor each section, use browser MCP to extract everything:\n\n1. **Screenshot** the section in isolation (scroll to it, screenshot the viewport). Save to `docs/design-references/`.\n\n2. **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:\n\n```javascript\n// Per-component extraction — run via browser MCP\n// Replace SELECTOR with the actual CSS selector for the component\n(function(selector) {\n  const el = document.querySelector(selector);\n  if (!el) return JSON.stringify({ error: 'Element not found: ' + selector });\n  const props = [\n    'fontSize','fontWeight','fontFamily','lineHeight','letterSpacing','color',\n    'textTransform','textDecoration','backgroundColor','background',\n    'padding','paddingTop','paddingRight','paddingBottom','paddingLeft',\n    'margin','marginTop','marginRight','marginBottom','marginLeft',\n    'width','height','maxWidth','minWidth','maxHeight','minHeight',\n    'display','flexDirection','justifyContent','alignItems','gap',\n    'gridTemplateColumns','gridTemplateRows',\n    'borderRadius','border','borderTop','borderBottom','borderLeft','borderRight',\n    'boxShadow','overflow','overflowX','overflowY',\n    'position','top','right','bottom','left','zIndex',\n    'opacity','transform','transition','cursor',\n    'objectFit','objectPosition','mixBlendMode','filter','backdropFilter',\n    'whiteSpace','textOverflow','WebkitLineClamp'\n  ];\n  function extractStyles(element) {\n    const cs = getComputedStyle(element);\n    const styles = {};\n    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; });\n    return styles;\n  }\n  function walk(element, depth) {\n    if (depth > 4) return null;\n    const children = [...element.children];\n    return {\n      tag: element.tagName.toLowerCase(),\n      classes: element.className?.toString().split(' ').slice(0, 5).join(' '),\n      text: element.childNodes.length === 1 && element.childNodes[0].nodeType === 3 ? element.textContent.trim().slice(0, 200) : null,\n      styles: extractStyles(element),\n      images: element.tagName === 'IMG' ? { src: element.src, alt: element.alt, naturalWidth: element.naturalWidth, naturalHeight: element.naturalHeight } : null,\n      childCount: children.length,\n      children: children.slice(0, 20).map(c => walk(c, depth + 1)).filter(Boolean)\n    };\n  }\n  return JSON.stringify(walk(el, 0), null, 2);\n})('SELECTOR');\n```\n\n3. **Extract multi-state styles** — for any element with multiple states (scroll-triggered, hover, active tab), capture BOTH states:\n\n```javascript\n// State A: capture styles at current state (e.g., scroll position 0)\n// Then trigger the state change (scroll, click, hover via browser MCP)\n// State B: re-run the extraction script on the same element\n// The diff between A and B IS the behavior specification\n```\n\nRecord the diff explicitly: \"Property X changes from VALUE_A to VALUE_B, triggered by TRIGGER, with transition: TRANSITION_CSS.\"\n\n4. **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**.\n\n5. **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).\n\n6. **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).\n\n### Step 2: Write the Component Spec File\n\nFor each section (or sub-component, if you're breaking it up), create a spec file in `docs/research/components/`. This is NOT optional — every builder must have a corresponding spec file.\n\n**File path:** `docs/research/components/<component-name>.spec.md`\n\n**Template:**\n\n```markdown\n# <ComponentName> Specification\n\n## Overview\n- **Target file:** `src/components/<ComponentName>.tsx`\n- **Screenshot:** `docs/design-references/<screenshot-name>.png`\n- **Interaction model:** <static | click-driven | scroll-driven | time-driven>\n\n## DOM Structure\n<Describe the element hierarchy — what contains what>\n\n## Computed Styles (exact values from getComputedStyle)\n\n### Container\n- display: ...\n- padding: ...\n- maxWidth: ...\n- (every relevant property with exact values)\n\n### <Child element 1>\n- fontSize: ...\n- color: ...\n- (every relevant property)\n\n### <Child element N>\n...\n\n## States & Behaviors\n\n### <Behavior name, e.g., \"Scroll-triggered floating mode\">\n- **Trigger:** <exact mechanism — scroll position 50px, IntersectionObserver rootMargin \"-30% 0px\", click on .tab-button, hover>\n- **State A (before):** maxWidth: 100vw, boxShadow: none, borderRadius: 0\n- **State B (after):** maxWidth: 1200px, boxShadow: 0 4px 20px rgba(0,0,0,0.1), borderRadius: 16px\n- **Transition:** transition: all 0.3s ease\n- **Implementation approach:** <CSS transition + scroll listener | IntersectionObserver | CSS animation-timeline | etc.>\n\n### Hover states\n- **<Element>:** <property>: <before> → <after>, transition: <value>\n\n## Per-State Content (if applicable)\n\n### State: \"Featured\"\n- Title: \"...\"\n- Subtitle: \"...\"\n- Cards: [{ title, description, image, link }, ...]\n\n### State: \"Productivity\"\n- Title: \"...\"\n- Cards: [...]\n\n## Assets\n- Background image: `public/images/<file>.webp`\n- Overlay image: `public/images/<file>.png`\n- Icons used: <ArrowIcon>, <SearchIcon> from icons.tsx\n\n## Text Content (verbatim)\n<All text content, copy-pasted from the live site>\n\n## Responsive Behavior\n- **Desktop (1440px):** <layout description>\n- **Tablet (768px):** <what changes — e.g., \"maintains 2-column, gap reduces to 16px\">\n- **Mobile (390px):** <what changes — e.g., \"stacks to single column, images full-width\">\n- **Breakpoint:** layout switches at ~<N>px\n```\n\nFill 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.\n\n### Step 3: Dispatch Builders\n\nBased on complexity, dispatch builder agent(s) in worktree(s):\n\n**Simple section** (1-2 sub-components): One builder agent gets the entire section.\n\n**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.\n\n**What every builder agent receives:**\n- The full contents of its component spec file (inline in the prompt — don't say \"go read the spec file\")\n- Path to the section screenshot in `docs/design-references/`\n- Which shared components to import (`icons.tsx`, `cn()`, shadcn primitives)\n- The target file path (e.g., `src/components/HeroSection.tsx`)\n- Instruction to verify with `npx tsc --noEmit` before finishing\n- For responsive behavior: the specific breakpoint values and what changes\n\n**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.\n\n### Step 4: Merge\n\nAs builder agents complete their work:\n- Merge their worktree branches into main\n- You have full context on what each agent built, so resolve any conflicts intelligently\n- After each merge, verify the build still passes: `npm run build`\n- If a merge introduces type errors, fix them immediately\n\nThe extract → spec → dispatch → merge cycle continues until all sections are built.\n\n## Phase 4: Page Assembly\n\nAfter all sections are built and merged, wire everything together in `src/app/page.tsx`:\n\n- Import all section components\n- Implement the page-level layout from your topology doc (scroll containers, column structures, sticky positioning, z-index layering)\n- Connect real content to component props\n- Implement page-level behaviors: scroll snap, scroll-driven animations, dark-to-light transitions, intersection observers, smooth scroll (Lenis etc.)\n- Verify: `npm run build` passes clean\n\n## Phase 5: Visual QA Diff\n\nAfter assembly, do NOT declare the clone complete. Take side-by-side comparison screenshots:\n\n1. Open the original site and your clone side-by-side (or take screenshots at the same viewport widths)\n2. Compare section by section, top to bottom, at desktop (1440px)\n3. Compare again at mobile (390px)\n4. For each discrepancy found:\n   - Check the component spec file — was the value extracted correctly?\n   - If the spec was wrong: re-extract from browser MCP, update the spec, fix the component\n   - If the spec was right but the builder got it wrong: fix the component to match the spec\n5. Test all interactive behaviors: scroll through the page, click every button/tab, hover over interactive elements\n6. Verify smooth scroll feels right, header transitions work, tab switching works, animations play\n\nOnly after this visual QA pass is the clone complete.\n\n## Pre-Dispatch Checklist\n\nBefore dispatching ANY builder agent, verify you can check every box. If you can't, go back and extract more.\n\n- [ ] Spec file written to `docs/research/components/<name>.spec.md` with ALL sections filled\n- [ ] Every CSS value in the spec is from `getComputedStyle()`, not estimated\n- [ ] Interaction model is identified and documented (static / click / scroll / time)\n- [ ] For stateful components: every state's content and styles are captured\n- [ ] For scroll-driven components: trigger threshold, before/after styles, and transition are recorded\n- [ ] For hover states: before/after values and transition timing are recorded\n- [ ] All images in the section are identified (including overlays and layered compositions)\n- [ ] Responsive behavior is documented for at least desktop and mobile\n- [ ] Text content is verbatim from the site, not paraphrased\n- [ ] The builder prompt is under ~150 lines of spec; if over, the section needs to be split\n\n## What NOT to Do\n\nThese are lessons from previous failed clones — each one cost hours of rework:\n\n- **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.\n- **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+.\n- **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.\n- **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.\n- **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.\n- **Don't build everything in one monolithic commit.** The whole point of this pipeline is incremental progress with verified builds at each step.\n- **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.\n- **Don't skip asset extraction.** Without real images, videos, and fonts, the clone will always look fake regardless of how perfect the CSS is.\n- **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.\n- **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.\n- **Don't skip responsive extraction.** If you only inspect at desktop width, the clone will break at tablet and mobile. Test at 1440, 768, and 390 during extraction.\n- **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.\n- **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.\n\n## Completion\n\nWhen done, report:\n- Total sections built\n- Total components created\n- Total spec files written (should match components)\n- Total assets downloaded (images, videos, SVGs, fonts)\n- Build status (`npm run build` result)\n- Visual QA results (any remaining discrepancies)\n- Any known gaps or limitations\n",
-  "fileContext": [
-    "AGENTS.md",
-    "docs/research/**"
-  ]
-}