StickerLoopv1.0.0

Writes a consistent GPT Image 2.6 prompt for each expression, to make on GifBake with no key (two free GIFs) or with the OpenAI Images API, which it calls with GIF output and never pays for twice.

See what you can make

Made with this SkillA sticker pack exported and checked for each chat app

4 stickers, 32 files within limits

Open full example

What you get

A sticker pack exported and checked for each chat app

What you can make

  • Writes a consistent GPT Image 2.6 prompt for each expression, to make on GifBake with no key (two free GIFs) or with the OpenAI Images API, which it calls with GIF output and never pays for twice.
  • Removes a plain background by flood fill so similar colours in the character stay, softens the shadow, adds outlined captions in any language and checks that each loop is seamless.
  • Exports every sticker for WeChat, Telegram, WhatsApp, LINE, Discord and Slack, compressing until each fits, measuring it again, and adding tray, main and tab icons.
Explore delivered files6 groups
  • A GPT Image 2.6 prompt per expression, for GifBake or the API
  • wechat/, discord/, slack/: GIFs at each size limit
  • telegram/: 512 px WEBM VP9 with transparency
  • whatsapp/: 512 px animated WebP and tray icon
  • line/: APNG with main and tab images
  • index.html preview on chat backgrounds, and report.md

Good fit

Creators, brands, communities and teams making reaction stickers, mascot packs and custom emoji.

Know the limits

Prepares and checks the files; it does not submit packs or pass platform reviews. Works best with a plain one-colour background, and GIF drops soft shadows.

About this skill

Your agent plans the character and the expressions people send most, and writes one GPT Image 2.6 prompt per animation that describes the character the same way each time, on a plain background, with a seamless loop and no text. Make each GIF on GifBake with no key (two free, then credits) or with the OpenAI Images API using GIF output, frame count and frame duration; existing GIFs are never requested again and each request's token cost is recorded. StickerLoop then removes the background colour by flood fill from the edges, so a cream character on mint keeps its body, turns the ground shadow soft, draws outlined captions in any language, lets one animation carry several captions, and checks that the last frame flows back into the first. Every sticker is exported for each app and compressed step by step until it fits: a 240 px WeChat GIF, a 512 px Telegram WEBM with transparency under 256 KB and 3 seconds, a 512 px WhatsApp animated WebP with tray icon, a LINE APNG with loops within 4 seconds plus main and tab images, and Discord and Slack emoji. Each file is measured again, limits not confirmed by the platform are flagged, and a preview shows the pack on chat backgrounds. Requires Node.js 20+ and FFmpeg.

FROM PACKAGE TO FIRST RESULT

Your first result, with your agent

Choose a starting point, add the content you already have, then let your agent check the setup and create one result.

View example result

Purchase access is required. Unzip the package into the project folder below, or let your agent follow the installation guide. .agents/skills/stickerloop

Your project name, audience and the content or images you already have are enough to start. Your agent will ask for anything essential that is missing.

3. Let your agent guide the first result

Package location: .agents/skills/stickerloop

Use StickerLoop to make a 16-sticker WeChat pack of my cat with Chinese captions. Start from examples/pack.json.

Use a new output folder and preserve existing files. Inspect the actual deliverables (A GPT Image 2.6 prompt per expression, for GifBake or the API, wechat/, discord/, slack/: GIFs at each size limit, telegram/: 512 px WEBM VP9 with transparency), open the visual result and explain failed checks. An incomplete dependency check is not a successful result. Ask before paid services and do not publish automatically.
Before calling it done
  • Dependencies checked before rendering
  • Actual files open and work with your content
  • Editable source saved in a new folder
Made your first result? Share your experience →
Installation options & technical requirements

Start with your agent

Give this request to Claude Code, Codex or Cursor. Your agent can collect the missing details and guide your first result.

Use StickerLoop to make a 16-sticker WeChat pack of my cat with Chinese captions. Start from examples/pack.json.

Purchase access is required to install the package. Technical commands are available below when you need them.

US$4.99 · MIT licenseNode.js 20+ · FFmpeg · GifBake (no key) or an OpenAI API keyNo API key or paid provider
  1. 01

    Choose your agent

    These steps use a project folder. Open the project in your agent and run terminal commands from its root.

    Codex directory guide

    Package folder .agents/skills/stickerloop

  2. 02

    Add the package

    Download and unzip the package into the folder above. Keep all its files together, with SKILL.md directly inside that folder.

    Downloads require a verified account and purchase access. Choose a new folder if this Skill is already installed.

  3. 03

    Run the included sample

    Manual sample commands and technical details

    Read SKILL.md, review the generator and check its runtime requirements before running:

    cd .agents/skills/stickerloop
    No installation needed
    node scripts/build.mjs --input examples/pack.json --output ./stickers
    Your first result

    Review index.html on light and dark chat backgrounds, then upload each folder to its app.

    Mochi is an original character; the two animations were generated with GPT Image 2.6 on GifBake. WeChat, Discord and Slack limits are flagged for checking on their upload pages.

    If stickers already exists, change the output to ./stickers-2. Existing files are never overwritten.

    Prefer to ask your agent?

    Use StickerLoop to make an animated sticker pack: plan my character and expressions, write a GPT Image 2.6 prompt for each animation to make on GifBake or with the API, then add captions, remove the background and export every sticker for the apps I use.

Reviews

Share your first result

Tried this workflow? Help others decide with an honest review.

Before you choose this Skill

How do I get StickerLoop?

The listed individual package price is USD 4.99. Premium downloads require a confirmed purchase or active membership. Your agent subscription, model access and external provider credits are separate.

Which agents can use this skill?

This release lists Codex, Claude Code, Cursor as intended installation hosts. Check the package’s dependencies and permissions before running it. These labels do not certify that every workflow has been tested in every agent.

What files can this workflow generate?

The documented 1.0.0 workflow lists: A GPT Image 2.6 prompt per expression, for GifBake or the API; wechat/, discord/, slack/: GIFs at each size limit; telegram/: 512 px WEBM VP9 with transparency; whatsapp/: 512 px animated WebP and tray icon; line/: APNG with main and tab images; index.html preview on chat backgrounds, and report.md. Some files or exports are optional; follow the package’s setup and inspect the delivered result.

What should I check before using the result?

Mochi is an original character; the two animations were generated with GPT Image 2.6 on GifBake. WeChat, Discord and Slack limits are flagged for checking on their upload pages.

$4.99One-time purchase