video-to-game
Type: SkillCategory: Generation
video-to-game is an agent skill in our Generation category. lovis' agent skill (Claude Code, Codex, Cursor, Gemini) that turns a 10 to 15 s MiniMax H3 Max gameplay clip into a playable single-file Three.js browser game: it studies the clip frame by frame, generates every image, 3D model, sound and music track with fal, writes the game, then plays and films it as proof. The README lists 31 games for $202 in total (about $6 each), with a live gallery. MIT.
Where it fits: Audio, voice & music, Open-weight video & audio models.
Listing isn’t endorsement. This is our summary of the project’s own docs. Check the licence and requirements at the source before you build on it.
Related Lab posts
- Fish Audio Drama 3 final weights top open TTS arenas
- anymove: creature mocap from one two-view AI video
- Mickmumpitz's one-model H3 short film and Singularity V2
- PopTok: a fully local pipeline from one prompt to a lip-synced music video (ACE-Step, LTX-2.5, InfiniteTalk)
- Stop re-explaining your edits: Kyle Balmer's habit of turning each correction into a rule for the agent
- huashu-motion: an open skill that writes the launch film, scores it, and lets you point at the frame to fix it
Similar skills & repos
- Kitty Open Studio · MCP, Generation
- anymove · Skill, Generation
- Pika H3 Flex · Repo, Generation
- video-editor-skills · Skill, Motion graphics
- story-to-handdrawn-video · Skill, Code-to-video engine
- Open-H3-Regenerate-2K · Repo, Generation