Light 3D Reel
A premium talking-head reel in code: face card, head above every graphic, 3D components, checked after every edit.
A light canvas, the speaker in a rounded card with the head popping above every graphic, dimensional components for every thing said (counters, phones, prompt bars, checklists, terminals, comment cards), quiet captions and a new beat about every two seconds. The pack holds the component library, the measured style spec, the principles behind it and the gates: 4 fps contact sheets, a DOM audit, an SFX audit and a render verifier, run after every edit. Works with a selfie cutout or with a pixel avatar. Built in code with HyperFrames; nothing renders until you say go.
- Raw in
- A script and a voice track (or a selfie A-roll for the face-card version), plus the real logos, icons and clips of the things you talk about. The pack ships a neutral demo avatar and generic placeholders.
- Finished out
- A 1080x1920, 30 fps HyperFrames project: light canvas, face card, 3D components on your words, captions, an SFX mix at -14 LUFS, contact sheets and gate reports for every edit. Nothing renders until you say go.
Reference video coming. Until it lands, this is exactly what the skill takes and gives back.
The look
- a face card with the head above every graphic
- white glass cards with soft shadow and one blue
- a new beat about every 2 seconds, each tied to a spoken word
- quiet 2-4 word captions
The first thing you paste
Use the light-3d-reel skill. My script is ./script.txt and my voice take is ./voice.wav (word times: ./words.json).
Write the beat sheet first: for every spoken noun, the real asset it needs. Then build the project from the example,
run every gate and show me the contact sheets. Do not render until I say go.Best for
- talking-head explainers and tool demos
- founder and creator reels that need to look premium
- turning a flat edit into a dimensional one
- anyone who wants Claude to check its own frames before showing them
What is in the zip
- SKILL.md (the loop, a gate at each step)
- stage library: 3D components, motion presets, captions
- measured style spec and principles
- component API with recipes and a motion verb bank
- gates: preview sheets, DOM audit, SFX audit, render verifier, lip-sync check
- head-cutout and face-detection sources (macOS)
- asset fetcher with provenance manifest
- a working 4-beat example project
- neutral demo avatar + original sound kit + OFL fonts
- self-test