website-to-hyperframes

# Website to HyperFrames Capture a website, then produce a professional video from it. Users say things like: - "Capture https://... and make me a 25-second product launch video" - "Turn this website into a 15-second social ad for Instagram" - "Create a 30-second product tour from https://..." The workflow has 7 steps. Each produces an artifact that gates the next. --- ## Single-voice craft (do NOT parallelize) This is a **creative direction** job, not an audit. One coherent visual + narrative voice runs the whole film: the same eye that wrote the storyboard's mood must steer the script's tone, the VO's pacing, and each composition's motion. **Do NOT fan out the creative steps to parallel sub-agents** — split direction across agents and the colors, rhythm, and personality fracture (DESIGN.md says "calm minimalist" while a beat ships frantic neon). Run the 7 steps sequentially, in one head. The ONLY work that may parallelize is mechanical and voice-neutral: independent asset captures, or building several already-storyboarded compositions in parallel **after** STORYBOARD.md is locked (Step 4 done) — because by then the single voice is already written down and each build just executes it. **Three craft anchors (use them every run):** 1. **Vibe-lock before you build.** The one-sentence vibe from Step 1 (e.g. *"confident, fast, premium SaaS — Linear-clean, not loud"*) is the contract. Every later decision — a font weight, an easing curve, a cut — is checked against it. If a beat fights the vibe, the beat is wrong. 2. **Worked micro-example (15s social ad, 3 beats):** - Beat 1 (0–4s) — Hook: hero headline draws on with a SVG stroke reveal over a blurred screenshot, VO *"Your site, in motion."* Easing `power3.out`, no bounce (premium ≠ playful). - Beat 2 (4–10s) — Proof: two product shots slide in on a shared MotionPath, depth via parallax, VO names the value. - Beat 3 (10–15s) — CTA: logo + URL settle, micro-scale 1.0→1.03 breathing loop, hard cut to end card. - Each beat's choices trace back to the vibe; nothing is decorative-for-its-own-sake. 3. **Evidence over invention — capture is ground truth.** Colors, fonts, copy, and assets come from the **captured site data** (Step 1) and `DESIGN.md`, never invented. If a hex, font, or product claim isn't in the capture, do not assert it — re-capture or mark it `TODO: verify`. No hallucinated brand colors, no fabricated taglines. ### Output contract - **Artifacts (in the project directory):** `DESIGN.md`, `SCRIPT.md`, `STORYBOARD.md`, `narration.wav`/`.mp3` + `transcript.json`, the built HyperFrames compositions, and `HANDOFF.md`. - **Final deliverable:** a lint-clean, validated HyperFrames video matching the requested type/duration/format from the Quick Reference table. ### Verify (run before claiming done) 1. `npx hyperframes lint` → zero errors. 2. `npx hyperframes validate` → zero errors. 3. Preview the render and confirm: requested duration ±1s, correct aspect ratio, VO synced to beats, **no overlapping elements / no static images without motion**, and the result honors the Step-1 vibe. 4. Spot-check every brand color/font/claim against the captured data — drop or flag anything not grounded in the capture. --- ## Step 1: Capture & Understand **Read:** [references/step-1-capture.md](references/step-1-capture.md) Run the capture, read the extracted data, and build a working summary using the write-down-and-forget method. **Gate:** Print your site summary (name, top colors, fonts, key assets, one-sentence vibe). --- ## Step 2: Write DESIGN.md **Read:** [references/step-2-design.md](references/step-2-design.md) Write a simple brand reference for the captured website. 6 sections, ~90 lines. This is a cheat sheet, not the creative plan — that comes in Step 4. **Gate:** `DESIGN.md` exists in the project directory. --- ## Step 3: Write SCRIPT **Read:** [references/step-3-script.md](references/step-3-script.md) Write the narration script. The story backbone. Scene durations come from the narration, not from guessing. **Gate:** `SCRIPT.md` exists in the project directory. --- ## Step 4: Write STORYBOARD **Read:** [references/step-4-storyboard.md](references/step-4-storyboard.md) Write per-beat creative direction: mood, camera, animations, transitions, assets, depth layers, SFX. This is the creative north star — the document the engineer follows to build each composition. **Gate:** `STORYBOARD.md` exists with beat-by-beat direction and an asset audit table. --- ## Step 5: Generate VO + Map Timing **Read:** [references/step-5-vo.md](references/step-5-vo.md) Generate TTS audio, transcribe for word-level timestamps, and map timestamps to beats. Update STORYBOARD.md with real durations. **Gate:** `narration.wav` (or .mp3) + `transcript.json` exist. Beat timings in STORYBOARD.md updated. --- ## Step 6: Build Compositions **Read:** The `/hyperframes` skill (invoke it — every rule matters) **Read:** [references/step-6-build.md](references/step-6-build.md) Build each composition following the storyboard. After each one: self-review for layout, asset placement, and animation quality. **Gate:** Every composition has been self-reviewed. No overlapping elements, no misplaced assets, no static images without motion. --- ## Step 7: Validate & Deliver **Read:** [references/step-7-validate.md](references/step-7-validate.md) Lint, validate, preview. Create a HANDOFF.md for multi-session continuity. **Gate:** `npx hyperframes lint` and `npx hyperframes validate` pass with zero errors. --- ## Quick Reference ### Video Types | Type | Duration | Beats | Narration | | --------------------- | -------- | ----- | ---------------------- | | Social ad (IG/TikTok) | 10-15s | 3-4 | Optional hook sentence | | Product demo | 30-60s | 5-8 | Full narration | | Feature announcement | 15-30s | 3-5 | Full narration | | Brand reel | 20-45s | 4-6 | Optional, music focus | | Launch teaser | 10-20s | 2-4 | Minimal, high energy | ### Format - **Landscape**: 1920x1080 (default) - **Portrait**: 1080x1920 (Instagram Stories, TikTok) - **Square**: 1080x1080 (Instagram feed) ### Reference Files | File | When to read | | ------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [step-1-capture.md](references/step-1-capture.md) | Step 1 — reading captured data | | [step-2-design.md](references/step-2-design.md) | Step 2 — writing DESIGN.md | | [step-3-script.md](references/step-3-script.md) | Step 3 — writing the narration script | | [step-4-storyboard.md](references/step-4-storyboard.md) | Step 4 — per-beat creative direction | | [step-5-vo.md](references/step-5-vo.md) | Step 5 — TTS, transcription, timing | | [step-6-build.md](references/step-6-build.md) | Step 6 — building compositions with self-review | | [step-7-validate.md](references/step-7-validate.md) | Step 7 — lint, validate, preview, handoff | | [techniques.md](references/techniques.md) | Steps 4 & 6 — 10 visual techniques with code patterns (SVG drawing, Canvas 2D, 3D, typography, Lottie, video, typing, variable fonts, MotionPath, transitions) |