Loop Cover logo

Loop Cover

Community
charlie947
loop-cover

Turn a newsletter or blog cover into a seamless looping GIF at 896 x 640, 180 frames at 20fps. Only the one element you name moves, the loop is rotated so frame 1 shows the finished picture, and the seam is measured, not eyeballed. Use when someone says "animated cover", "make my cover move", "looping GIF cover", "newsletter cover GIF", "animate my thumbnail" or wants a cover that moves in the inbox without looking busy.

Overview

Publishercharlie947
Repositorymotion-graphics-skills
Skill nameloop-cover
Stars
428
Forks
62
Bundled files
Instructions only
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.

  • Self-contained

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

  • Open source

    Published by charlie947 on GitHub. Read the source before you install it.

Installation

Install the Loop Cover 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/loop-cover
  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/loop-cover .claude/skills/loop-cover
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Loop Cover 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 Loop Cover 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 Loop Cover 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.

Looping cover GIF

A cover that moves gets noticed in a feed full of stills. It only works if the move is small, the loop never jumps and the first frame still makes sense on its own.

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 three things, then wait

  1. The cover. A finished still (PNG) or a cover built in HTML. 896 x 640, or a larger image with the same 7:5 shape.
  2. The one element that moves, named plainly. "The lighthouse beam." "The orange line drawing itself." "The lines between the cells."
  3. How it moves. A pulse, a draw-on, a slow drift or a glow. One move, not three.

Step 2: Build it

If the cover is HTML: animate only the named element as a pure function of time, add window.seek(seconds), and capture 180 frames at 20fps (9 seconds).

If the cover is an image: animate the still in code. Make a mask of the named element by colour (for example every pixel where blue is much stronger than red), soften its edge a few pixels, and change only those pixels, frame by frame. Nothing outside the mask moves.

For both, use one clean sine cycle or one draw-on, hold and fade across the 9 seconds, so the last frame flows into the first.

Rotate the loop so frame 1 is the finished picture. Inboxes and link previews show frame 1 as a still. Frame i draws the moment ((i + offset) mod 180) / 20 seconds, where offset puts the fully drawn state first.

Encode with no dithering, because dither adds flicker to every frame of a flat image:

ffmpeg -y -framerate 20 -i f%03d.png -filter_complex "split[x][y];[x]palettegen=max_colors=128:stats_mode=full[p];[y][p]paletteuse=dither=none" -loop 0 cover.gif

Step 3: Measure it

ffmpeg -v error -y -i cover.gif -vf scale=216:154,format=gray -f rawvideo frames.raw
python3 -c "
n = 216 * 154
d = open('frames.raw', 'rb').read()
f = [d[i:i + n] for i in range(0, len(d), n)]
diff = lambda a, b: sum(abs(x - y) for x, y in zip(a, b)) / n
print('frames', len(f))
print('seam', round(diff(f[-1], f[0]), 2))
print('excursion', round(max(diff(x, f[0]) for x in f), 2))
"

Targets from covers I shipped: 180 frames, a seam of 0.0 to 0.3, an excursion of about 0.7 to 2.8, and a file between 0.6 and 2.3 MB. An excursion near zero means nothing visible moves.

What I learned the hard way

  • "You changed the image entirely." My first GIF swept a band across the whole frame. Animate only the thing that was named.
  • A video model adds a camera move. Told "camera holds completely still", it still pushed in. Animating the still in code is the only way to lock the camera.
  • Never measure motion at the halfway frame. A sine is back at zero there, so a working animation reports no motion. Measure the biggest change against frame 0.
  • In ffmpeg's eq filter, add eval=frame, or the expression runs once and nothing moves.
  • Shrink it to 240px wide and look again. That is the size in an inbox. If the moving element disappears, it is too small.
  • Upload the GIF itself. Some upload tools convert to PNG and the animation is silently gone. Check the uploaded link still ends in .gif.

Frequently asked questions

What does the Loop Cover AI skill do?

Turn a newsletter or blog cover into a seamless looping GIF at 896 x 640, 180 frames at 20fps. Only the one element you name moves, the loop is rotated so frame 1 shows the finished picture, and the seam is measured, not eyeballed. Use when someone says "animated cover", "make my cover move", "looping GIF cover", "newsletter cover GIF", "animate my thumbnail" or wants a cover that moves in the inbox without looking busy.

Why use Loop Cover on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/charlie947/motion-graphics-skills/tree/main/skills/loop-cover. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Loop Cover?

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 Loop Cover?

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

Is the Loop Cover 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 👇