Motion Canvas logo

Motion Canvas

Community
dracohu2025-cloud
motion-canvas

Production pipeline for Motion Canvas — TypeScript-based programmatic vector animation with real-time preview. Use when users want explainer videos, technical demos, timeline-based motion graphics, code animations, animated UI mockups, or synchronized voice-over scenes built with Motion Canvas.

Overview

Publisherdracohu2025-cloud
Repositorydraco-skills-collection
Skill namemotion-canvas
Stars
228
Forks
37
Bundled files
6
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 6 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by dracohu2025-cloud on GitHub. Read the source before you install it.

Installation

Install the Motion Canvas AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/Ark%20Agent%20Plan%20Version/motion-canvas
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Use it in TypingMind

Enable Motion Canvas in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Motion Canvas on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Motion Canvas is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Motion Canvas Production Pipeline

Motion Canvas sits between Manim and Remotion.

  • Manim thinks in objects + transforms
  • Remotion thinks in React components per frame
  • Motion Canvas thinks in scenes + timeline + reactive properties

Use this skill when the user wants code-driven animation but prefers TypeScript, real-time preview, scene choreography, vector motion graphics, or synced narration.

Best fit

Choose Motion Canvas when the task looks like one of these:

  • animated explainers
  • technical demos and mechanism walkthroughs
  • data visualization with staged reveals
  • animated UI / product mockups
  • code walkthroughs with highlighted ranges
  • timeline-synced narration

Avoid it when the real need is:

  • pure math / formula-heavy proof animation → prefer manim-video
  • bulk React template videos / content factory → prefer Remotion-style workflow
  • browser-interactive art toy / open-ended generative sketch → prefer p5js

Core mental model

A Motion Canvas project is:

  1. project.ts — declares scenes, fps, size, optional audio
  2. scene generator — function* (view) { ... }
  3. nodes — Rect, Circle, Txt, Line, Code, Img, layouts
  4. refs — access nodes later with createRef() / createRefArray()
  5. signals — reactive values you can read, set, and animate
  6. timeline flow — yield*, all(), sequence(), waitFor(), waitUntil()

The key move is simple:

Set up scene state, then drive properties over time with yield*.

Bootstrap

Current scaffold route validated here:

bash
npx @motion-canvas/create@latest
cd <project>
npm install
npm start

The create package currently exists as @motion-canvas/create; npm view on this machine reports it as “Quickly scaffold Motion Canvas projects”.

CLI gotcha validated here

  • npx create-motion-canvas@latest failed against the current npm mirror because that package name does not exist there.
  • npx @motion-canvas/create@latest is the working package route.
  • Calling npx @motion-canvas/create@latest --help on this machine still dropped into an interactive Project name prompt instead of printing normal help.

So for automation, do not assume a harmless --help or non-interactive probe. Treat the scaffold command as interactive unless you have re-verified the exact flags in a PTY.

Typical structure:

text
project/
├── src/
│   ├── project.ts
│   └── scenes/
│       └── intro.tsx
├── package.json
└── vite.config.ts

Authoring rules

1. One scene, one idea

If you are explaining a mechanism, do not jam five concepts into one scene. Motion Canvas is strong at staged reveals. Use that.

2. Start from the final visual story

Before coding, state:

  • what appears first
  • what changes next
  • what the viewer should understand by the end of the scene

3. Prefer refs + named helpers over anonymous chaos

If a node will move later, give it a ref. If an animation pattern repeats, wrap it in a generator helper.

4. Animate meaningfully

Do not animate everything just because you can. Use motion to direct attention.

5. Keep scenes composable

Short scenes with clean entrances/exits beat one giant timeline blob.

Workflow

  1. Plan — scene list, key beats, narration markers, visual hierarchy
  2. Scaffold — create project, wire project.ts, create scene files
  3. Block — place the main nodes with static layout first
  4. Animate — add yield* timing, then parallel/stagger effects
  5. Sync — use waitUntil() / duration markers if narration matters
  6. Preview — iterate in the editor before worrying about final render
  7. Render — export once timing and layout are stable

Minimum working example

tsx
import {makeScene2D, Circle} from '@motion-canvas/2d';
import {all, createRef} from '@motion-canvas/core';

export default makeScene2D(function* (view) {
  const circle = createRef<Circle>();

  view.add(
    <Circle
      ref={circle}
      size={180}
      fill={'#3b82f6'}
      opacity={0}
      scale={0.6}
    />,
  );

  yield* all(
    circle().opacity(1, 0.6),
    circle().scale(1, 0.6),
    circle().position.x(240, 1.2),
  );
});

This already shows the whole model:

  • add a node to view
  • store a ref
  • animate properties over time with yield*

High-value patterns

  • Sequential: yield* a(); yield* b();
  • Parallel: yield* all(a(), b(), c())
  • Staggered: yield* sequence(0.1, ...anims)
  • Pause: yield* waitFor(0.5)
  • Narration marker: yield* waitUntil('beat-name')
  • Reactive value: const x = createSignal(0) then yield* x(100, 1)
  • Code walkthrough: use Code node and animate selection() / code.replace()

Critical pitfalls

  • scene imports need the ?scene suffix in project.ts
  • refs are functions: use circle() rather than circle
  • node properties are signals; many can be read, set, or animated the same way
  • if layout is still moving, do not polish easing yet
  • if a scene feels muddy, split it rather than stacking more effects

Deliverables

For real work, default to producing:

  • project source
  • at least one clean scene per concept
  • a short README or notes with run/render commands
  • exported preview or final render if requested

References

Load these on demand:

  • references/core-concepts.md
  • references/patterns.md
  • references/selection-guide.md
  • templates/scene-starter.tsx
  • templates/project-starter.ts

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Motion Canvas AI skill do?

Production pipeline for Motion Canvas — TypeScript-based programmatic vector animation with real-time preview. Use when users want explainer videos, technical demos, timeline-based motion graphics, code animations, animated UI mockups, or synchronized voice-over scenes built with Motion Canvas.

Why use Motion Canvas on TypingMind?

Because you install it once and use it with any model. Motion Canvas is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Motion Canvas in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dracohu2025-cloud/draco-skills-collection/tree/main/Ark%20Agent%20Plan%20Version/motion-canvas. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Motion Canvas?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Motion Canvas?

As many as you like. As long as a model supports skills, you can use Motion Canvas with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Motion Canvas AI skill free?

It is published on GitHub by dracohu2025-cloud. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇