Open-source motion skills for AI coding agents
iart-ai motion-skills is an open-source set of instructions that helps make , animation, and video. It includes 50 skills grouped into 14 installable packs for TikTok, Reels, Shorts, text-message videos, YouTube videos, e-commerce videos, ads, animated data charts, s, map animation, web animation, 3D, WebGL, and Manim math animation. Each skill is a folder an agent can read to learn one workflow, without or a special runtime plugin.
Users can install only the packs they need, and the project says Claude Code, Cursor, Codex, and many other agents can discover the right skill automatically when the prompt matches the task. Skills that create visual output include a check step, such as rendering a frame, taking a screenshot, or inspecting an encoded MP4, so the agent can review its own result. Web skills create standalone HTML, while video skills use Remotion or Manim to render output.
The project is released under the MIT license.
Key points
- The project offers 50 open-source skills for that make motion and video assets.
- The skills are split into 14 installable packs, so teams can add only the workflows they need.
- Claude Code, Cursor, Codex, and other agents are described as able to auto-discover matching skills.
- Visual-output skills include review steps such as screenshots, frame checks, or MP4 inspection.
- The project uses the MIT license, so it is broadly usable for experiments and internal workflows.