Website to HyperFrames

SkillWeb & browsing

Your AI can turn HTML pages into rendered videos. It writes a page in HTML and then renders that page as a video, so the whole process stays in HTML from start to finish. The skill is built for agents, meaning your AI handles both writing the page and producing the video.

Available today. Use it from your connected AI after setup.

After adding it, give your AI an HTML page to convert into a video, or ask it to write the HTML itself and then render it.

Then ask your AI: use the Website to HyperFrames skill

What your AI can do with it

  • Turn HTML pages into rendered videos
  • Create video content by writing HTML
  • Render a finished video from a web page
  • Write the HTML for a new page and render it as a video

What this skill tells your AI

The instructions your AI receives, as published by alecs5am/ralphy in .agents/skills/website-to-hyperframes/SKILL.md and read by ahel’s review.

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.


Step 1: Capture & Understand

Read: 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

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

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

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

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 (load it — every rule matters) Read: 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

Lint, validate, snapshot, preview. Deliver the localhost Studio project URL (http://localhost:<port>/#project/<project-name>) to the user first — only render to MP4 on explicit request. Do not treat index.html as the project handoff link; it is source-code context only.

Gate: npx hyperframes lint and npx hyperframes validate pass with zero errors, and the final response includes the active Studio project URL.


Quick Reference

Video Types

TypeDurationBeatsNarration
Social ad (IG/TikTok)10-15s3-4Optional hook sentence
Product demo30-60s5-8Full narration
Feature announcement15-30s3-5Full narration
Brand reel20-45s4-6Optional, music focus
Launch teaser10-20s2-4Minimal, high energy

Format

  • Landscape: 1920x1080 (default)
  • Portrait: 1080x1920 (Instagram Stories, TikTok)
  • Square: 1080x1080 (Instagram feed)

Reference Files

FileWhen to read
step-1-capture.mdStep 1 — reading captured data
step-2-design.mdStep 2 — writing DESIGN.md
step-3-script.mdStep 3 — writing the narration script
step-4-storyboard.mdStep 4 — per-beat creative direction
step-5-vo.mdStep 5 — TTS, transcription, timing
step-6-build.mdStep 6 — building compositions with self-review
step-7-validate.mdStep 7 — lint, validate, snapshot, preview
techniques.mdSteps 4 & 6 — 11 visual techniques with code patterns (SVG drawing, Canvas 2D, 3D, typography, Lottie, video, typing, variable fonts, MotionPath, transitions, audio-reactive)

Signals

GitHub stars
133
Forks
13
Last commit
Sep 2026

What people say

Users report that HyperFrames lets agents like Claude Code and Codex turn HTML into polished videos with a one-command setup, producing surprisingly good results. The recurring praise is easy setup and agent-native HTML-to-MP4 rendering; the recurring complaint is that output quality depends heavily on investing real effort in the prompt and learning specific workflows.

Praised for
one-command setup
HTML-to-MP4 without React/Remotion complexity
surprisingly good video output
Complaints
quality requires significant prompt/workflow effort

Summarized from 19 public posts. Opinions are theirs, not ahel's.

Advanced
Catalog kind
skill
Gateway key
website-to-hyperframes
Source
github.com/alecs5am/ralphy