AgentsModelsSkillsMemoryBotsEvaluationsGuidesSubmit a resource
Skills

Text-To-Lottie

Open-source agent skill and preview harness for generating production-ready Lottie animations with Codex or Claude Code.

Visit official site Open repository
0.8K Stars
0.1K Forks
MIT License
diffusionstudio Maintainer
2026-06-09 Verified
Overview

What is Text-To-Lottie?

Text-To-Lottie is an open-source skill and harness from Diffusion Studio for generating Lottie animations with AI coding agents. The project includes a Skia CanvasKit / Skottie player, React + TypeScript controls, and a workflow where the agent writes `public/lottie.json` while the dev server hot-reloads the animation.

Agent-ready skill install

The project can be added with `npx skills add diffusionstudio/lottie` and used through the `text-to-lottie` skill.

A skill install path makes it easier for Codex, Claude Code, and similar agents to reuse the workflow without manual prompt setup.

Live Lottie preview loop

The harness watches `public/lottie.json` and hot-reloads the generated animation in a local player.

Motion assets need visual feedback. A live loop lets the agent and human reviewer iterate quickly.

Skottie-based rendering

The preview player uses Skia CanvasKit / Skottie to render Lottie animations in the browser.

Using a real Lottie renderer helps catch animation JSON issues before assets move into product.
Use cases

What Text-To-Lottie is built for

01

Product motion assets

Generate lightweight onboarding, empty-state, loading, or feature-highlight animations for web and app interfaces.

02

Agent creative production

Give a coding agent a repeatable workflow for creating structured Lottie JSON rather than static prompts.

03

Animation prototyping

Use the local preview harness to rapidly test and refine Lottie concepts before handing them to design or engineering.

Quick start

Get started in seconds

terminal
$ npx skills add diffusionstudio/lottie
$ npm install && npm run dev
Open the GitHub repository → Read the launch post →
Comparison

How it stacks up

Choose Text-To-Lottie for agent-authored motion

vs Manual Lottie editing

Manual editors are better for precise timeline work. Text-To-Lottie is better when a coding agent should generate and revise animation JSON inside a local preview loop.

FAQ

Frequently asked questions

Is Text-To-Lottie open source?

Yes. The GitHub repository is listed under the MIT license.

What does the skill generate?

The workflow is designed around generating Lottie JSON, especially `public/lottie.json`, and previewing it live in the included local harness.

Who should evaluate Text-To-Lottie?

Teams using Codex, Claude Code, or similar coding agents to produce product motion assets should evaluate it.