Turn a character image into a full pack of animated chat

Animated Sticker Studio · 动态表情包工坊

by fantuan-lab · MIT license · ★ 26 on GitHub

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,…

---
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](references/manifest.md)). Pick captions from [references/phrases.md](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.

Overview

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.

Manual install (npx, ZIP)

Claude Codenpx skills add fantuan-lab/animated-sticker-studio -g -a claude-code

Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

SKILL.md5.4 KB

Read SKILL.md here

fantuan-lab/main1 file

SKILL.md5.4 KB

SKILL.md

Show the full text64 lines

animated-sticker-studio/SKILL.md64 lines · 5.4 KB

PreviewCode

Outline

RawView on GitHub

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.

1	---
2	name: animated-sticker-studio
3	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.
4	---
5
6	# Animated Sticker Studio · 动态表情包工坊
7
8	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.
9
10	## 1. Plan (manifest.json)
11
12	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.
13
14	Write `manifest.json` next to the work (format: [references/manifest.md](references/manifest.md)). Pick captions from [references/phrases.md](references/phrases.md) unless the user gave their own, and give every entry:
15
16	- `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.
17	- `motion` + `icon` + optional `caption_fx` — chosen to match the line (table in phrases.md).
18	- 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.
19
20	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.
21
22	## 2. Reference
23
24	- User image → copy into `ref/`, set `character.reference`. Write `character.anchors`: one English sentence listing what must never change (shape, colours, markings, accessories).
25	- 3D model → render a front/three-quarter view with the face visible, use that.
26	- Only a description → `gen_atlas.py manifest.json --provider hiapi --make-reference "<description>"`, show the result, get a yes.
27	- Use only art the user owns or may adapt. Do not recreate a third party's character from memory.
28
29	## 3. Atlases
30
31	One sheet per group (≤16 cells). Either:
32
33	- 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`.
34	- 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.
35
36	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.
37
38	## 4. Cut
39
40	`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.
41
42	## 5. Build
43
44	```sh
45	python3 scripts/build_pack.py manifest.json out --mp4 # platforms from manifest
46	python3 scripts/build_pack.py manifest.json out --only 3,7-9 # quick re-render of a few while iterating
47	```
48
49	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.
50
51	## 6. Look (required — you cannot watch a GIF, so look at these)
52
53	- `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.
54	- `out/review/contact.png`: whole pack at once — check variety and that no two look alike.
55	- 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.
56
57	Fix loop: wrong motion/icon/caption → edit manifest, `--only`; bad art → redraw that group or cell; then rebuild everything once at the end.
58
59	## 7. Deliver
60
61	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](references/platforms.md); say they are as of 2026-11 and the platform console wins.
62
63	Keep the original reference and atlases out of the ZIP unless asked.
64