yuv-video-director

name

yuv-video-director

description

Yuval's all-in-one AI video pipeline. Turns an idea/script into a finished, on-brand MP4 by orchestrating HyperFrames (HTML→deterministic video render), Lottie (branded motion graphics), ManimCE (math / neural-network / concept animations), and a transcribe→approve caption flow — all wrapped in the YUV.AI Neon Phoenix brand via a frame.md. Use whenever Yuval wants to make, edit, or explain something as a video: promo, explainer, launch, social reel, "make a video about X", "explain X as a video", "neural network animation", "turn this into a video", captioned tutorial, 16:9 or 9:16. Triggers: video, explainer, promo, reel, manim, lottie, hyperframes, animation, "make a video", "explain ... as a video", מצגת וידאו, סרטון, הסבר וידאו. Routes each beat to the right engine, wraps in brand, self-verifies, and renders.

yuv-video-director

The conductor for YUV.AI video. You (the agent) decide what each beat needs, route it to the right engine, compose everything into one HyperFrames composition, wrap it in the YUV.AI Neon Phoenix brand, self-verify, and render to MP4. This skill is the router + the working reference implementations; load a reference file only when that engine is in play.

Design source of truth: the yuv-design-system skill (Neon mode — pink #FF1464, cyan #00E5FF, rich-black/white, Anton+Inter+JetBrains Mono, neural-net phoenix motif). The video form of it is frame.md — see references/frame-md.md. Bundled template: assets/FRAME.md. Drop it in the project root; HyperFrames reads it.

The one law (decides everything)

HyperFrames renders by seeking each frame in headless Chrome → FFmpeg (frameIndex = floor(t·fps), same input → same output). So every visual is one of two kinds: