Animated Video logo

Animated Video

Community
bluzir
animated-video

Build animated motion design (explainer, transition reel, product intro). Uses Stage/Sprite timeline from animations.jsx for in-browser compositions or Remotion for full video/MP4 workflows.

Overview

Publisherbluzir
Repositoryclaude-code-design
Skill nameanimated-video
Stars
107
Forks
11
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by bluzir on GitHub. Read the source before you install it.

Installation

Install the Animated Video 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/bluzir/claude-code-design/tree/main/.claude/skills/animated-video
  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.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/bluzir/claude-code-design.git /tmp/claude-code-design
mkdir -p .claude/skills
cp -r /tmp/claude-code-design/.claude/skills/animated-video .claude/skills/animated-video
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Animated Video 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 Animated Video 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 Animated Video 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.

Animated Video

Two paths depending on complexity. Decide first, tell the user which path you're taking.

Phase 0 — Context pre-flight (auto-detect, ONE question max)

Before deciding Path A vs B, silently check for context:

  1. Read .claude/design-tokens.json if exists
  2. Bash(ls ~/.claude/design-systems/ 2>/dev/null) — brand folder match
  3. Glob codebase tokens
  4. Scan brief for github / Figma / image / PRD attachment → dispatch ingestion skills

If nothing — ONE AskUserQuestion: design system / codebase / screenshot / Figma / none / decide. Report "Using . Proceeding."

Path A — Standalone HTML with Stage/Sprite

For any animation that can live in one HTML file (explainer reel, product intro, transition sequences, hero animations — <60s typical).

Uses the Remotion-compatible in-browser engine in starters/animations.jsx. Same mental model as Remotion — different runtime (no build step, runs under Babel standalone).

Available primitives:

PrimitiveRole
<Stage duration width height [id] [loop] [showControls]>Root composition. Owns one RAF clock, scale-to-fit canvas, scrubber UI, play/pause. Reads/writes position in localStorage.
<Sprite start end [easing]>Active only in [start..end]ms window. Children can be element or (localT) => element. Unmounts when out of range.
useTime({ stopAt? })Returns current ms. Inside Stage: reads shared clock (free). Standalone: spawns its own RAF (costlier).
useSprite()Returns local t ∈ [0,1] within the current Sprite.
Easinglinear, inQuad, outQuad, inOutCubic, outQuart, inOutExpo, spring(stiffness, damping)
interpolate(t, [in], [out], { clamp?, easing? })Piecewise lerp. Supports numbers and hex colors.
<FadeIn>, <FadeOut>, <SlideIn from=...>, <ScaleIn from=...>, <Reveal from=...>Entry/exit sugar. Persist after their animation window (unlike Sprite).
<Transition from to duration>Standalone one-shot wrapper (no Stage needed).

Steps:

  1. Invoke Skill: frontend-design for aesthetic direction
  2. Create artifacts/<slug>.html with React + Babel + animations.jsx
  3. Bash(cp starters/animations.jsx "$(dirname <html>)/") — copy starter next to the HTML
  4. Run /serve (required for external .jsx CORS)
  5. Compose the scene. Pattern:
jsx
function Scene() {
  const t = useTime();  // Stage-shared clock
  // drive properties via interpolate()
  const bg = interpolate(t, [0, 2000, 5000], ['#fef9f3', '#f3d8a8', '#8a5a22'], { easing: Easing.inOutCubic });
  return (
    <div style={{ position: 'absolute', inset: 0, background: bg }}>
      <FadeIn start={0} duration={500}>
        <h1>Entry stays visible after 500ms</h1>
      </FadeIn>
      <Reveal start={400} duration={700} from="bottom" distance={40}>
        <p>Fade + slide combo</p>
      </Reveal>
      <Sprite start={1500} end={3500} easing={Easing.outQuart}>
        {(local) => <div style={{ opacity: local, transform: `scale(${local})` }}>Bounded — disappears after 3500</div>}
      </Sprite>
    </div>
  );
}

function App() {
  return <Stage duration={5000} width={1920} height={1080} loop={false}><Scene/></Stage>;
}
  1. /done http://127.0.0.1:4567/artifacts/<slug>.html — verify scrubber works, animation plays cleanly, console clean
  2. For exporting frames/seeking for PPTX: external tools can send window.postMessage({ seekMs: N, playing: false }, '*') — Stage listens and jumps

Path B — Remotion (MP4 export, multi-scene video)

For long-form (>60s), multi-scene narrative, or MP4-export needs.

  1. Delegate to Skill: remotion-best-practices — full Remotion workflow
  2. Set up artifacts/<slug>-remotion/ as a separate Remotion project
  3. Return a preview HTML and MP4 artifact when done

When to pick which

NeedPath
Single scene, any lengthA
Product intro, explainer under a minuteA
Multi-scene narrativeB
MP4 export requiredB
Browser-only preview (ship an HTML)A
Exact frame timing (e.g. 30fps video)B (Remotion is frame-based)
Physics / gesture-drivenA with Popmotion <script src> fallback, or B

Popmotion fallback

For real spring physics, keyframe math, or gesture tracking beyond what Easing.spring() supports, add:

html
<script src="https://unpkg.com/popmotion@11.0.5/dist/popmotion.min.js"></script>

and use window.popmotion directly.

Verify

Path A: /done <url> — scrubber reaches end, clicking bar seeks, play/pause toggles, console clean. If the user wants PPTX frames of this animation: seek via postMessage before each screenshot.

Path B: Remotion preview server at localhost:3000 + exported MP4.

Frequently asked questions

What does the Animated Video AI skill do?

Build animated motion design (explainer, transition reel, product intro). Uses Stage/Sprite timeline from animations.jsx for in-browser compositions or Remotion for full video/MP4 workflows.

Why use Animated Video on TypingMind?

Because you install it once and use it with any model. Animated Video 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 Animated Video in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bluzir/claude-code-design/tree/main/.claude/skills/animated-video. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Animated Video?

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 Animated Video?

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

Is the Animated Video AI skill free?

It is published on GitHub by bluzir. 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 👇