name: animated-sticker-studio description: Turn a character image (mascot, OC, pet photo, 3D render, or just a text description) into a full pack of animated chat stickers — real keyframe animation plus motion, captions and effects — exported to the exact spec of WeChat 表情开放平台, Telegram, LINE, Discord, Slack, WhatsApp or plain GIF, auto-compressed under each size limit, visually verified and zipped. Use for 表情包/动态表情/贴纸/sticker pack requests of any size (8 to 100+), for redoing single stickers, or for converting an existing pack to another platform.

Animated Sticker Studio · 动态表情包工坊

Pipeline: plan → reference → atlases → cut → build → look → fix → deliver. Scripts live in scripts/ (Python 3 + Pillow; ffmpeg for Telegram/MP4). Run every script with --help before first use.

1. Plan (manifest.json)

Ask only what you cannot default. Defaults: 16 stickers, Simplified Chinese captions, generic GIF; add wechat if they mention 微信表情开放平台/上架, telegram/line/discord/slack/whatsapp if named. WeChat albums take any 8–24 stickers; LINE packs must be 8, 16 or 24.

Write manifest.json next to the work (format: references/manifest.md). Pick captions from references/phrases.md unless the user gave their own, and give every entry:

• pose — what the body does, in English, concrete enough to draw (arms, props, expression). Two entries may never share the same pose with only new text.
• motion + icon + optional caption_fx — chosen to match the line (table in phrases.md).
• For the 4–8 stickers where the gesture IS the joke (挥手, 鼓掌, 打字, 干饭, 点赞, 哭, 打哈欠, 比心…) put them in a group with "keys": 4 and write four key_poses. These become real frame-by-frame animation. Single poses get procedural motion only.

Show the user the plan as a short table (编号 / 文案 / 动作) before spending on generation when the pack is ≥24 or the user seems picky; otherwise go.

2. Reference

• User image → copy into ref/, set character.reference. Write character.anchors: one English sentence listing what must never change (shape, colours, markings, accessories).
• 3D model → render a front/three-quarter view with the face visible, use that.
• Only a description → gen_atlas.py manifest.json --provider hiapi --make-reference "<description>", show the result, get a yes.
• Use only art the user owns or may adapt. Do not recreate a third party's character from memory.

3. Atlases

One sheet per group (≤16 cells). Either:

• Your own image tool (Codex image_gen, etc.): gen_atlas.py manifest.json --print-prompts, generate each sheet with the reference attached, save as the printed path, then set the group's atlas and grid.
• Bundled providers: gen_atlas.py manifest.json --provider hiapi|openai (keys only from env: HIAPI_API_KEY, or OPENAI_API_KEY + optional OPENAI_BASE_URL/OPENAI_IMAGE_MODEL). Skips groups that already have an atlas; --group N redraws one. Never print or echo a key.

Open every sheet at full size. Reject and redraw (--group N) when the identity drifts, a cell is missing or doubled, limbs are clipped, or two poses are the same.

4. Cut

cut_atlas.py manifest.json — removes solid or fake-checkerboard backgrounds, finds each sprite by its pixels (not by a rigid grid), writes sprites/ and fills every entry's sprites list. Open each atlases/*.index.png and confirm number N shows the pose written for entry N. If the model swapped cells, fix by editing sprites paths in the manifest — never by renaming captions to fit wrong art.

5. Build

python3 scripts/build_pack.py manifest.json out --mp4          # platforms from manifest
python3 scripts/build_pack.py manifest.json out --only 3,7-9   # quick re-render of a few while iterating

Fonts are found automatically (PingFang/Hiragino/Noto CJK/YaHei); --font overrides. Each platform file is re-encoded until it fits that platform's byte limit; report.json records the setting used.

6. Look (required — you cannot watch a GIF, so look at these)

• out/review/motion-XX.png: every sticker as 4 frames side by side on alternating white/dark rows. Check: the motion reads as the caption's emotion, keyframes don't jitter sideways, nothing clipped, no white halo on dark rows, captions legible, accents not covering the face.
• out/review/contact.png: whole pack at once — check variety and that no two look alike.
• The build's JSON summary: failing (per-platform spec failures) and pack_issues (near-duplicate poses, wrong pack size, stickers that barely move). Fix all of them or tell the user exactly which remain and why.

Fix loop: wrong motion/icon/caption → edit manifest, --only; bad art → redraw that group or cell; then rebuild everything once at the end.

7. Deliver

Give the user: the ZIP path, 预览.html (opens offline; light/dark/checker backgrounds and a chat mock-up), the MP4 if made, and a one-line pass/fail per platform from the summary. Mention platform limits that still need a human: WeChat needs a 750×400 banner and copyright paperwork, LINE/Telegram need account-side upload. Specs are in references/platforms.md; say they are as of 2026-11 and the platform console wins.

Keep the original reference and atlases out of the ZIP unless asked.

Animated Sticker Studio

Give your AI coding agent one character image (or just a description) and get back a full pack of chat stickers that actually animate: it writes the captions and poses, draws every keyframe, adds text and effects, exports to each platform's exact upload spec, compresses every file under the size limit, checks its own work, and zips it up.

Works in Claude Code, Codex, and any agent that can run Python.

Example: Onigiri Cat · 24 stickers

An original character, made in one run: 1 character sheet + 3 pose sheets = 4 image-generation calls, no manual retouching. Shown below is the WeChat Sticker Platform export (240×240, ≤500 KB each), submitted for WeChat review on 2026-11-05.

#1–16: one pose each, plus procedural motion. #17–24: real frame-by-frame animation — the paw waves, the tears stream, the yawn opens.

What it does

• Characters really move. Gesture stickers get 2–4 drawn keyframes (wave, clap, type, eat, cry, yawn…), layered with procedural motion. Most AI sticker tools only slide and squash one still image.
• 22 seamless motion presets, 5 caption animations (pop, typewriter, wave, shake, static), 17 vector effect icons that stay sharp at any size.
• Smooth illustration or pixel-art rendering.
• Platform presets: generic GIF, WeChat Sticker Platform, Telegram, LINE, Discord, Slack, WhatsApp — size, format, frame count, duration and byte limits. Files are re-encoded until they fit, and the setting used is recorded.
• Companion images each platform asks for: WeChat thumbnails / cover / chat icon, LINE main + tab, Telegram and WhatsApp pack icons.
• Robust cutting: removes solid backgrounds and the fake "transparent" checkerboard image models often paint; finds each sprite by its pixels, so uneven grids still cut cleanly; writes a numbered index sheet per atlas.
• Self-review the agent can actually see: agents can't watch a GIF, so every sticker is laid out as 4 frames on alternating light/dark rows. Clipping, halos on dark mode, wrong motion and near-duplicate poses (perceptual hash) are flagged; stickers that jump off the canvas are auto-shrunk.
• Offline preview page with light / dark / checker / pixel backgrounds and a chat mock-up.
• CJK fonts found automatically, with a glyph-coverage check.

Quick start

Install

• Claude Code: put this folder at ~/.claude/skills/animated-sticker-studio/, or tell Claude: "Install this skill: https://github.com/fantuan-lab/animated-sticker-studio"
• Codex: put it at ~/.codex/skills/animated-sticker-studio/ (agents/openai.yaml is included).

Requires Python 3 + Pillow (pip install Pillow). Telegram export and the MP4 preview also need ffmpeg.

Make a pack

Send your agent a character image and say:

Use animated-sticker-studio to make 16 animated stickers of this character for the WeChat Sticker Platform.

Or: "24 office-worker stickers", "use my own captions", "pixel style", "also export a Telegram version". No image? Describe the character and it will draw a reference sheet for you to approve first.

Image generation: you only need ONE of these

# 1. write manifest.json (format: references/manifest.md, captions: references/phrases.md)
# 2. generate pose sheets
python3 scripts/gen_atlas.py manifest.json --provider hiapi
# 3. cut sprites, then check atlases/*.index.png
python3 scripts/cut_atlas.py manifest.json
# 4. render, export, verify, zip
python3 scripts/build_pack.py manifest.json out --platform wechat,telegram --mp4

Rebuild the example without spending anything (the cut sprites are in the repo):

cd examples/onigiri-cat
python3 ../../scripts/build_pack.py manifest.json out --platform generic,wechat

Repository layout

SKILL.md                workflow the agent follows
scripts/gen_atlas.py    prompts + image-generation providers
scripts/cut_atlas.py    background removal, sprite cutting, index sheets
scripts/build_pack.py   render, per-platform export, compression, checks, preview, zip
scripts/sticker_core.py motion, icons, captions, die-cut outline
references/             manifest format, platform specs, caption library (Chinese)
examples/onigiri-cat/   Onigiri Cat: reference, atlases, sprites, finished GIFs

Notes

• Platform specs reflect public requirements as of November 2026; the platform's own console is the final word. Store listings (banners, copyright paperwork, account setup) are still up to you.
• Your reference image is sent to the image provider you choose. Use only characters you own or are licensed to adapt.
• Built after studying WoYun520/pixel-gif-sticker-pack; the Chinese README has a point-by-point comparison.

License

MIT