Geomotion logo

Geomotion

Community
hacimertgokhan
geomotion

Create hand-drawn, morphing line animations (boiling ink, riso-style fills) from simple shapes and export them as animated SVG, Lottie JSON, HTML or shareable links. Use when the user wants an animated icon, loader, illustration, explainer motion, logo sting, empty-state or success animation, "hand-drawn" / "sketchy" / "doodle" animation, or asks for geomotion.

Overview

Publisherhacimertgokhan
Repositorygeomotion
Skill namegeomotion
Stars
6
Forks
0
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 hacimertgokhan on GitHub. Read the source before you install it.

Installation

Install the Geomotion 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/hacimertgokhan/geomotion/tree/main/skills/geomotion
  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/hacimertgokhan/geomotion.git /tmp/geomotion
mkdir -p .claude/skills
cp -r /tmp/geomotion/skills/geomotion .claude/skills/geomotion
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Geomotion 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 Geomotion 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 Geomotion 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.

geomotion

geomotion turns a JSON spec — a list of keyframes, each a list of shapes — into a hand-drawn animation. Shapes with the same id morph into each other between keyframes; lines keep "boiling" (re-inked ~12×/s) so the result feels traced by hand.

Site & studio: https://hacimertgokhan.github.io/geomotion · Repo: https://github.com/hacimertgokhan/geomotion

Workflow

  1. Pick a route (use the first that is available):
    • MCP tools (geomotion_guide, geomotion_get_preset, geomotion_render, geomotion_share_link): call geomotion_guide once, then render.
    • CLI (Node 18+ with network): npx -y github:hacimertgokhan/geomotion render spec.json --both --formats svg,lottie,html
    • No tooling: write the spec, then run python scripts/link.py spec.json (in this skill folder) to get a player/studio link the user can open, edit and export from.
  2. Start from a preset when one is close (see catalog below) and adapt ids, positions, colours.
  3. Write the spec following the rules below. Validate (MCP geomotion_validate or geomotion check spec.json).
  4. Deliver: file paths and/or the player link. Mention the studio link so they can tweak it. Offer a transparent version (transparent: true or "both") when the animation will sit on a website.

Spec essentials

json
{
  "name": "idea",
  "size": [1200, 1200],
  "fps": 24, "boil": 12, "loop": true,
  "background": "ivory",
  "hold": 0.7, "duration": 0.9, "ease": "inOutCubic",
  "style": { "width": 24, "wobble": 1, "misregister": [-14, 10] },
  "keyframes": [
    { "shapes": [ { "id": "bulb", "type": "circle", "cx": 600, "cy": 520, "r": 220, "fill": "oat" } ] },
    { "hold": 1.2, "shapes": [
      { "id": "bulb", "type": "circle", "cx": 600, "cy": 520, "r": 240, "fill": "sun" },
      { "id": "ray", "type": "line", "from": [600, 200], "to": [600, 110], "enter": "draw", "delay": 0.3 }
    ] }
  ]
}
  • Keyframe: hold (seconds shown), duration (morph to the next keyframe), ease.
  • Shape types: circle {cx,cy,r}, ellipse {cx,cy,rx,ry}, rect {x,y,w,h,radius?} or {cx,cy,w,h}, line {from,to}, polyline {points,closed?}, polygon {points}, regular {cx,cy,r,sides}, triangle {cx,cy,r}, star {cx,cy,r,inner?,points?}, heart {cx,cy,size}, blob {cx,cy,r,seed?}, crescent {cx,cy,r,thickness?,angle?}, wave {from,to,amplitude?,waves?,phase?}, spiral {cx,cy,r,turns?}, arc {cx,cy,r,start,end} (degrees, 0 = right, clockwise), path {d} (any SVG path).
  • Shape options: id (match across keyframes — always set it), fill, stroke (colour or false), width, opacity, enter/exit (grow | pop | draw | fade | cut), delay (0–0.95, stagger), ease, transform {translate, rotate, scale, origin}, misregister: false for tiny solid dots.
  • Palette names: ink, slate, ivory, paper, oat, kraft, clay, coral, fig, sky, cactus, olive, heather, sun, white (or any hex).
  • Easings: linear, in/out/inOut Quad·Cubic·Sine, inOutQuart, outExpo, inOutExpo, outBack, inOutBack, outElastic, outBounce.

Design rules that make it look good

  1. 1200×1200 canvas, ~120 px margin, 2–5 bold shapes per pose. Small details read badly.
  2. Ink for every outline, one or two accent fills per pose (oat, clay, sun, sky, cactus, coral).
  3. Tell a story through ids: the same element transforms (sun → moon, envelope → paper plane, dot → heart).
  4. Stagger with delay 0 / 0.15 / 0.3; use "enter": "draw" for lines that should feel written, "pop" for playful arrivals.
  5. Holds 0.5–1.2 s, morphs 0.5–1.2 s. inOutCubic = calm, inOutBack/outBack = playful, outElastic = jelly.
  6. Rotations > 30° between two keyframes make lines cut corners — split big rotations into several keyframes (see the spinner, gears, orbit presets).
  7. Solid dots (eyes, typing dots): "stroke": false, "fill": "ink", "misregister": false.

Preset catalog (start points)

  • interface: loader, spinner, success, error, toggle, bell, search
  • nature: sunrise, sprout, rain, night, sea
  • communication: chat, send, like, connect
  • ideas: idea, growth, target, gears, house
  • characters: smile, ghost, sparkle
  • abstract: drift, orbit, kaleido, pebbles
  • motion: bounce, pendulum, jelly

Any preset opens directly: https://hacimertgokhan.github.io/geomotion/play/#preset=<name> (add &bg=0 for a transparent background) or in the studio: /studio/#preset=<name>.

Embedding on a website

html
<script type="module" src="https://hacimertgokhan.github.io/geomotion/src/embed.js"></script>
<geo-motion preset="success" transparent style="width:160px"></geo-motion>
<geo-motion code="z…"></geo-motion>   <!-- the #s=… part of a share link -->

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 Geomotion AI skill do?

Create hand-drawn, morphing line animations (boiling ink, riso-style fills) from simple shapes and export them as animated SVG, Lottie JSON, HTML or shareable links. Use when the user wants an animated icon, loader, illustration, explainer motion, logo sting, empty-state or success animation, "hand-drawn" / "sketchy" / "doodle" animation, or asks for geomotion.

Why use Geomotion on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hacimertgokhan/geomotion/tree/main/skills/geomotion. 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 Geomotion?

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 Geomotion?

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

Is the Geomotion AI skill free?

Yes. It is published on GitHub by hacimertgokhan 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 👇