What problem does it solve? Producing motion-graphics videos, captioned talking-head clips, and animated social content normally requires manual timeline editing in video software. This Skill treats HTML as the source of truth for video: you author a composition with data attributes, CSS, and a GSAP timeline, and the HyperFrames engine captures it frame-by-frame and encodes it to MP4 or WebM with FFmpeg. ## Core Features & Use Cases - HTML-to-video rendering: Scaffold projects with npx hyperframes init, preview with live reload, and render deterministic MP4/WebM output at draft, standard, or high quality. - Captions, TTS, and audio-reactive visuals: Generate local TTS narration (Kokoro, 54 voices across 8 languages), transcribe with Whisper for word-level captions, and drive visuals from pre-extracted audio bands. - Transitions and website-to-video: Install shader transitions (flash-through-white, liquid-wipe) and run a 7-step capture-to-video pipeline that turns a URL into a scripted, storyboarded promo. - Use Case: A user provides a product landing page URL and asks for a 30-second vertical promo. The Skill captures the site, derives a DESIGN.md from its brand tokens, writes a narration script, generates TTS audio, builds the composition, and renders a final 1080x1920 MP4. ## Quick Start Ask the assistant to run the setup script and then scaffold a new video project with npx hyperframes init, describing the style, duration, and any media or URL you want included.