Motion Effects logo

Motion Effects

Community
charlie947
motion-effects

Build any of 16 premium motion effects from scratch in your own brand, as one 8-second looping HTML file with window.seek(seconds) so it exports frame-exact to MP4 or GIF. Interfaces (button to player, search to results, card to workspace, tabs to panels), data (chart morph, dashboard zoom, spring stack, magnetic dock), type (masked type, elastic type, text to layout, image reveal) and systems (perspective shift, glass focus, flowing paths, particle logo). Use when someone says "build the chart morph", "make a button that turns into a video player", "animate my logo with particles", "motion effect", "UI animation", "product animation", "animated dashboard", "kinetic type" or names any of the 16 effects.

Overview

Publishercharlie947
Repositorymotion-graphics-skills
Skill namemotion-effects
Stars
428
Forks
62
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 charlie947 on GitHub. Read the source before you install it.

Installation

Install the Motion Effects 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/charlie947/motion-graphics-skills/tree/main/skills/motion-effects
  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/charlie947/motion-graphics-skills.git /tmp/motion-graphics-skills
mkdir -p .claude/skills
cp -r /tmp/motion-graphics-skills/skills/motion-effects .claude/skills/motion-effects
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Motion Effects 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 Effects 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 Effects 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 effects, built in your brand

Sixteen effects that make a product, a number or a word move like it was made by a motion designer. Each one is a recipe: what it is, where it starts, where it ends, when each part moves inside an 8-second loop, and the one detail that makes it look premium. You pick the effect, give it your real words, and it gets built from scratch in your colours and type.

Before you start: read brand.md and MOTION.md if they exist. If not, run brand-intake first, or ask for hex codes, a font and a logo file. Never call a result on-brand without them.

Step 1: Ask for four things, then wait

  1. The effect. One of the 16 by name or number. If they describe a job instead ("show our pricing", "reveal the launch name"), suggest the two effects from the table below that fit best and let them pick.
  2. The real content. The words, labels and numbers that go in it. Real figures, or say they are samples.
  3. The size. 1080 x 1080 (square), 1080 x 1350 (LinkedIn portrait), 1080 x 1920 (Reel) or 1920 x 1080 (YouTube).
  4. Loop or hold. Loop repeats forever (a post or a GIF). Hold plays once and stays on the finished frame (under a voiceover, so it never resets mid-sentence).
#EffectUse it when you
01Button → playeradd a "watch the demo" moment to a landing page or launch email
02Search → resultsshow what people find in your help centre or content library
03Card → workspaceannounce a feature, and one small card becomes the whole editor
04Tabs → panelscompare plans, packages or channels without a wall of text
05Chart morphdrop a weekly result into a client report or results post
06Dashboard zoompull the one KPI that matters out of a dashboard
07Spring stackshow three offers, case studies or testimonials in turn
08Magnetic dockshow the tools you use, or a product's integrations
09Masked typereveal a campaign name, issue number or launch headline
10Elastic typeopen an event, webinar or podcast with a title card
11Text → layoutturn a headline into a carousel cover or article teaser
12Image revealtease a product drop, then swap in your own photo
13Perspective shiftexplain the layers of a service, brand system or stack
14Glass focusmake people read the one line of a report that matters
15Flowing pathsshow one piece of content feeding several channels
16Particle logoclose a video, reel or post on your mark

Step 2: Read the recipe

Open references/effects.md and read the chosen effect in full: start state, end state, timing, the premium detail. The recipe is the spec. Swap the demo words for the user's real ones, and map every colour role (ground, surface, ink, muted, accent, second accent) to a colour in MOTION.md.

Step 3: Build it

Build one self-contained file, effect.html, to these rules:

  1. One clock. Every frame is worked out from the time alone. Add window.seek(seconds) that draws the exact frame for that moment, in any order, as often as it is called. No setTimeout, no CSS animations running on their own, no randomness that is not seeded.
  2. One loop, 8 seconds. Move from 0.0 to 2.2, hold to 6.6, return by 8.0. seek(0) and seek(8) must draw the same frame. In hold mode, play the move once and stay on the finished frame from 6.6 onwards.
  3. Back to the start. The return eases every element back to exactly where it began. Nothing snaps home.
  4. Real content, never lorem. The user's words and numbers. Sample numbers carry a visible "illustrative" or "example" label on every frame.
  5. Self-contained. Fonts embedded, images inlined, no network requests, so it opens offline and renders the same every time.
  6. Autoplay unless told not to. Play in real time when opened in a browser, and stop the clock when the URL ends in ?render, so an exporter drives window.seek() itself.
  7. Scale the effect up. It fills the frame at the chosen size, with margins from MOTION.md. It is not a small tile in a big empty canvas.

Step 4: Check it before you show it

Capture frames at 0, 1, 2.2, 4.4, 6.6, 7.9 and 8 seconds and look at every one.

  • The loop: frame 0 and frame 8 are identical.
  • The move: frames 0, 1 and 2.2 are all different. If two match, part of the effect is not running.
  • The fit: no text runs past its box, and nothing is cut off at any of the seven moments.
  • The still: pause on 4.4. The point of the effect reads from that single frame.
  • The brand: every colour and font on screen is in MOTION.md.

Fix what fails, capture again, and only then show the user the 2.2 and 4.4 frames with the file path.

Step 5: Export it

Now turn effect.html into a video and a GIF I can post. Use tools already on this computer. If you need something that is not installed, stop and tell me what it is before you install anything. Load the page with ?render, call window.seek() for every frame at 30 frames per second (240 frames for 8 seconds), and encode an MP4 in H.264 at [SIZE]. Then make a GIF that loops forever. Show me three frames from the finished GIF so I can check it came out right.

HyperFrames (npx skills add heygen-com/hyperframes) does this in one step if it is installed.

What I learned the hard way

  • "Make it premium" means one object changing shape. Every one of the 16 effects is a thing turning into another thing: a button into a player, bars into a line, a card into a window. A fade from one picture to another looks cheap every time.
  • The hold is where people actually look. 4.4 of the 8 seconds is the hold. If nothing moves in it, the loop feels dead. Each recipe keeps something small alive there: a progress bar, a cursor, a second wave of light.
  • A ghost of the start state sells the change. A faint outline left where the button or card began lets the eye follow the move. Without it the end state looks like it appeared from nowhere.
  • Stagger by a beat, not all at once. Rows, slats, letters and dots each start a fraction later than the last. Everything moving together reads as a slide transition.
  • Frame 0 drew in the wrong font. An embedded font does not load until something uses it, so the first frame can paint in a fallback. Load every font explicitly before the first seek(0).
  • Scale it up, do not redraw it. An effect drawn with fixed coordinates ends up in one corner when you just change the canvas size. Scale the whole drawing to fill the frame instead.
  • A blank page is usually a name declared twice. Copying helpers between files duplicated a colour constant and stopped the whole script. Declare each name once, and paste the red console error back to Claude if the page is empty.
  • Eight seconds is too slow for a Reel cut. A full loop dropped into Instagram B-roll failed a motion check. Cut the active move (about 1.4 seconds of it) and use hold mode under narration.
  • Pick one unit for time and keep it. The exporter and the page must agree on seconds or milliseconds. This pack uses seconds everywhere.
  • Label made-up numbers on the frame. I made up every figure on my own board for the demo, so every effect carries an "example" label until real numbers go in.

Hand off

Give the user effect.html, the MP4 and the GIF, with the three checked frames. Then offer the next step in one line: another effect from the same group, or reel-export to turn it into a vertical Reel with safe-zone text.

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 Effects AI skill do?

Build any of 16 premium motion effects from scratch in your own brand, as one 8-second looping HTML file with window.seek(seconds) so it exports frame-exact to MP4 or GIF. Interfaces (button to player, search to results, card to workspace, tabs to panels), data (chart morph, dashboard zoom, spring stack, magnetic dock), type (masked type, elastic type, text to layout, image reveal) and systems (perspective shift, glass focus, flowing paths, particle logo). Use when someone says "build the chart morph", "make a button that turns into a video player", "animate my logo with particles", "motion...

Why use Motion Effects on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/charlie947/motion-graphics-skills/tree/main/skills/motion-effects. 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 Effects?

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 Effects?

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

Is the Motion Effects AI skill free?

Yes. It is published on GitHub by charlie947 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 👇