sticker-factory
Skill32 starsChanged 4 months agoMITView on GitHub
Automated factory workflow: Generates grid-based sticker sheets and auto-packages them for WeChat using wechat-sticker-maker. Use when the user wants to create a complete custom sticker pack from scratch (e.g., '帮我做一套表情包', '批量生产表情').
In this repository9 other files it gives its agents.
- excalidraw-visual-designerSkill
- gif-makerSkill
- grid-sticker-generatorSkill
- toutiao-publisherSkill
- video-tutorial-makerSkill
- wechat-post-publisherSkill
- wechat-sticker-assets-designerSkill
- wechat-sticker-makerSkill
- template-skillSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Custom: If user specifies a different theme, generate 16 varied actions relevant to that theme satisfying the grid constraints.
- Very specific: line 24
Call generate_image with the constructed prompt.
- Distinctive: line 37
Before moving to the next step, the Agent must:
- Distinctive: line 51
Run the conditional crop and resize wrapper script on each generated asset to achieve the exact WeChat specification sizes:
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Sticker Factory (Auto-Generator & Packer)
This skill serves as an Automated Production Line that orchestrates the entire lifecycle of sticker creation: from AI generation to WeChat-compliant asset packaging.
Execution Workflow
Step 1: Generate Sticker Grid
Adhere to the Universal Grid Logic defined in skills/grid-sticker-generator/SKILL.md.
- Prompt Construction:
- Core: User's described character/theme.
- Format Constraints (CRITICAL): Inherit all Visual Design Standards from
grid-sticker-generator(4x4 Grid, No Text, Flat Vector). - Content Logic:
- Default: Load the Office Worker Template (
references/office_worker_template.md) from the generator skill to fill slots with office memes. - Custom: If user specifies a different theme, generate 16 varied actions relevant to that theme satisfying the grid constraints.
- Default: Load the Office Worker Template (
- Action:
- Call
generate_imagewith the constructed prompt.
- Call
Step 2: Auto-Process with Sticker Maker
Once the image is successfully generated, immediately trigger the packaging robot.
- Command:
./skills/wechat-sticker-maker/scripts/run.sh "PATH_TO_GENERATED_IMAGE" --output "OUTPUT_DIR" --layout 4x4- PATH_TO_GENERATED_IMAGE: The absolute path returned by the
generate_imagetool. - OUTPUT_DIR: If user specified a custom path, use it. Otherwise, default to
output/stickers_[theme].
- PATH_TO_GENERATED_IMAGE: The absolute path returned by the
- Metadata Auto-Population (CRITICAL):
Before moving to the next step, the Agent must:
- Automatically edit and fill in
info.txtandmeta.txtwith actual names, descriptions, and sticker meaning words, replacing the template placeholders, based on the theme generated. - Copy the original generated grid image into the output folder (e.g. as
source.pngorgrid_image.png).
- Automatically edit and fill in
Step 3: Generate Matching WeChat Sticker Assets
Orchestrate the design of matching promotional materials based on the generated IP character using skills/wechat-sticker-assets-designer/SKILL.md.
- Action:
- Analyze IP: Extract visual features (hair, colors, outfit) from the generated grid image.
- Generate Assets:
- Banner: Aspect ratio 15:8 (
750x400target). Rich story-rich scene, no text, no white/transparent background. - Solicitation Image: Aspect ratio 4:3 (
750x560target). Begging pose, including text "您的赞赏是我们最大的动力!", non-white background. - Acknowledgment Image: Aspect ratio 1:1 (
750x750target). Celebratory pose, including text "感谢您的慷慨赞赏!", non-white background.
- Banner: Aspect ratio 15:8 (
- Crop & Resize:
Run the conditional crop and resize wrapper script on each generated asset to achieve the exact WeChat specification sizes:
./skills/wechat-sticker-assets-designer/scripts/run.sh "PATH_TO_BANNER" --width 750 --height 400 --anchor center ./skills/wechat-sticker-assets-designer/scripts/run.sh "PATH_TO_SOLICITATION" --width 750 --height 560 --anchor top ./skills/wechat-sticker-assets-designer/scripts/run.sh "PATH_TO_ACKNOWLEDGMENT" --width 750 --height 750 --anchor center- 保存路径 (CRITICAL): 将裁剪缩放后的三张配套图保存到该表情包输出目录下的
assets/子目录中(即OUTPUT_DIR/assets/),严禁零散放置在外部。
- 保存路径 (CRITICAL): 将裁剪缩放后的三张配套图保存到该表情包输出目录下的
Step 4: Final Delivery
Report the complete production results to the user:
- Preview: Show the generated grid sheet and the matching promotional assets (Banner, Solicitation, Acknowledgment).
- Asset Package: Provide the absolute clickable link to the consolidated output directory:
- Stickers & Assets Project Folder:
OUTPUT_DIR(Stickers inside the root folder, and Banner/Solicitation/Acknowledgment assets inside theassets/subfolder).
- Stickers & Assets Project Folder:
Example Command
"Generate a set of generic 'Cute Robot' stickers and assets under a single folder." "Production line: Make me an office worker set and matching assets for a 'Tired T-Rex'."
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

