Motion Design logo

Motion Design

Community
nahid-sparktales
motion-design

Decide what an animation is communicating, then give it a duration, an easing curve, an interruption behaviour and a reduced-motion fallback. Use when adding or reviewing transitions, when a screen feels sluggish or jumpy, when implementing motion specified in a design, or when animation needs to survive users who ask for less of it. Not for static visual design, and not for general performance profiling of code that has no animation.

Overview

Publishernahid-sparktales
Repositoryagent-dispatcher
Skill namemotion-design
Stars
58
Forks
5
Bundled files
1
LicenseMIT
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.

  • 1 bundled files

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

  • Open source

    Published by nahid-sparktales on GitHub. Read the source before you install it.

Installation

Install the Motion Design 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/nahid-sparktales/agent-dispatcher/tree/main/skills/design/motion-design
  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/nahid-sparktales/agent-dispatcher.git /tmp/agent-dispatcher
mkdir -p .claude/skills
cp -r /tmp/agent-dispatcher/skills/design/motion-design .claude/skills/motion-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Motion Design 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 Design 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 Design 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 design

Motion is a sentence about what just changed. An animation that does not say where something came from, that input registered, or that work is under way is decoration the user waits through.

When this fires

Transitions, animated state changes, gesture-driven movement or loading indicators are being added, changed or reviewed — or an interface reads as janky, slow, or unexplained.

Procedure

  1. Give each motion a job, in one sentence. The honest jobs are: continuity (this came from there), feedback (your input registered), status (something is still happening), and attention (this changed and you would have missed it). Motion with no job gets cut — that is the cheapest improvement available here.
  2. Set duration from the size of the change, not from taste. Small local feedback is nearly instant (around a tenth of a second); ordinary component transitions sit in the low hundreds of milliseconds; large or full-screen surfaces take somewhat longer. Past roughly half a second the user is waiting on you, and it must buy something. Shorter is the safer error.
  3. Choose easing from the direction of travel. Elements entering the screen decelerate into place; elements leaving accelerate out; elements moving between two on-screen positions ease both ends. Reserve linear for continuous or indeterminate loops, where easing would read as a pulse.
  4. Anchor the movement to its trigger. A panel opens from the control that opened it; a row expands in place; a dismissed item leaves the way a user pushed it. Movement that starts somewhere unrelated to the tap breaks the continuity it was meant to provide.
  5. Make it interruptible. A second input during an animation must be honoured immediately and the motion must reverse or retarget from where it currently is, not restart from the beginning and not queue. A transition that swallows input, or that must finish before the UI responds, is a defect regardless of how it looks.
  6. Implement the reduced-motion path deliberately. Respect the OS-level reduced-motion preference, and treat it as a substitution rather than a deletion: a cross-fade or an immediate state change, so the change is still legible. Never carry information only in the movement — if the animation is the only thing saying an item was added or removed, the still frame must say it too.
  7. Keep stagger small and bounded. A short per-item delay across the first few items, then nothing. A list that ripples for a second is slower than a list that appears.
  8. Prefer properties the compositor can animate — transform and opacity — over animating layout geometry, which recomputes layout every frame. When a property's cost is not obvious, measure rather than assume.
  9. Watch it run, repeatedly, on the slowest target you have. Loop it; play it with the CPU throttled; play it on a device, not only a desktop browser. Motion is the thing that reads correct in the source and wrong on screen, and what you notice on the tenth viewing the user notices on the second. Reading the CSS is not watching the animation.

Checklist

  • Each animation's job stated, or the animation removed
  • Durations scaled to the size of the moving element, nothing gratuitously long
  • Easing matches enter / exit / move-between; linear only for continuous loops
  • Motion originates at its trigger
  • Interrupting mid-flight reverses or retargets, and input is never blocked
  • Reduced-motion path substitutes rather than strips, and no meaning lives only in movement
  • Observed running, at least once on a slow path, not only inferred from code
  • Loading and indeterminate states still readable at their slowest

Failure handling

  • "It feels slow" — separate the animation from the wait behind it. Shortening a transition that is covering a two-second fetch fixes nothing; the fix is a status motion plus a faster fetch, and those are two different findings.
  • Stutter or dropped frames — profile before tuning. Guessing at duration when the cause is a layout-thrashing property produces a shorter bad animation.
  • It looks right in the browser and wrong on device — trust the device. Say which one you observed on; never generalize one smooth desktop run to "animation verified".
  • No way to observe it running — say motion was not observed, report what the code specifies, and do not describe it as checked. Reduced-motion behaviour in particular is only confirmed by running with the preference set.
  • A motion carries meaning nothing else carries — that is an accessibility defect, not a tuning question. Raise it rather than quietly shortening the animation.

Evidence to report

Each animation, its stated job, its duration and easing, and the property it animates; what you saw when you interrupted it; what the reduced-motion path does and whether you actually ran with the preference set; the device or throttling conditions you observed under; and any motion you changed the timing of without being able to watch it.

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 Design AI skill do?

Decide what an animation is communicating, then give it a duration, an easing curve, an interruption behaviour and a reduced-motion fallback. Use when adding or reviewing transitions, when a screen feels sluggish or jumpy, when implementing motion specified in a design, or when animation needs to survive users who ask for less of it. Not for static visual design, and not for general performance profiling of code that has no animation.

Why use Motion Design on TypingMind?

Because you install it once and use it with any model. Motion Design 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 Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/nahid-sparktales/agent-dispatcher/tree/main/skills/design/motion-design. 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 Design?

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 Design?

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

Is the Motion Design AI skill free?

Yes. It is published on GitHub by nahid-sparktales under the MIT license. 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 👇