Back to directory

Text-to-Lottie

An open-source framework that generates production-ready Lottie animations through Claude Code, Codex, or any other coding agent that supports skills, from a plain-language prompt.

Text-to-Lottie

Text-to-lottie is an open-source framework for generating production-ready Lottie animations with Claude Code, Codex, or any other coding agent that supports skills. After installing the skill, a coding agent is asked to generate an animation from a prompt, which can reference an SVG path, real-world data, or a screenshot to ground the result.

The agent sets up a workspace and a bundled player; each animation lives as a scene loaded from a per-project path in the player, which live-updates as the agent edits the generated file, so the animation can be inspected, scrubbed, and refined in real time. The project's prompt guide recommends using motion-design language such as ease-in and ease-out, describing camera-like pushes, pans, and zooms, explicitly requesting any controls needed beyond a background color, and specifying frame rate and duration. Generated animations can be used directly as Lottie JSON files on the web, in React Native through a Skia-based module, or in iOS through a Lottie library, or imported into After Effects for further refinement.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.