motion2code
Type: SkillCategory: Motion graphics
motion2code is an agent skill in our Motion graphics category. Rebuilds an AI-generated motion-design clip (or fake app screen recording) as one self-contained HTML page: inline SVG on a single seekable GSAP timeline, seamless loop, vector-sharp at any size. Scripts study the video (frames, cuts, palette), frame-diff source vs code, check the loop seam and render frame-exact MP4/GIF. Claude Code plugin or npx skills add; Python 3.9+, ffmpeg, Playwright. MIT.
Where it fits: Motion graphics skills.
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.
Lab posts that cover motion2code
Related Lab posts
- Framefields: code-first video for agents that renders on the GPU, with no headless Chrome
- huashu-motion: an open skill that writes the launch film, scores it, and lets you point at the frame to fix it
- motion-prompt: a clickable dictionary of motion names your agent can build from
- Remotion 4.0.536–537: a real editing timeline, then After Effects–style effects
- HyperFrames: HeyGen's bet that agents should write video as HTML
Similar skills & repos
- ffmpeg-skill · Skill, Motion graphics
- huashu-motion · Skill, Motion graphics
- lemo-opuscar · Skill, Motion graphics
- claude-motion-explainer · Skill, Motion graphics
- whiteboard-teacher-video · Skill, Motion graphics
- motion-prompt · Skill, Motion graphics