Sticker Factory

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.

• Action:
• Call generate_image with the constructed prompt.

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_image tool.
• OUTPUT_DIR: If user specified a custom path, use it. Otherwise, default to output/stickers_[theme].

• Metadata Auto-Population (CRITICAL):

Before moving to the next step, the Agent must:

• Automatically edit and fill in info.txt and meta.txt with 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.png or grid_image.png).

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:

1. Analyze IP: Extract visual features (hair, colors, outfit) from the generated grid image. 2. Generate Assets:

• Banner: Aspect ratio 15:8 (750x400 target). Rich story-rich scene, no text, no white/transparent background.
• Solicitation Image: Aspect ratio 4:3 (750x560 target). 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 (750x750 target). Celebratory pose, including text "感谢您的慷慨赞赏！", non-white background.

3. 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。

Step 4: Final Delivery

Report the complete production results to the user: 1. Preview: Show the generated grid sheet and the matching promotional assets (Banner, Solicitation, Acknowledgment). 2. 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 the assets/ subfolder).

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'."

Sticker Factory (表情包自动化工厂)

Sticker Factory 是一个全流程编排 (Orchestration) Skill。它充当“生产线经理”的角色，将生成 (grid-sticker-generator) 和 制作 (wechat-sticker-maker) 两个独立的 Skill 串联起来，实现从“一句话需求”到“最终上架素材包”的端到端自动化。

🏭 核心流程

工厂流水线包含四个自动化步骤：

1. 🎨 智能生成 (Design Phase):

• 调用 grid-sticker-generator。
• 根据用户描述（如“熬夜的猫头鹰”），构建符合 4x4 网格、透明背景、无文字规范的 Prompt。
• 调用绘图工具生成原始网格图。

2. ✂️ 自动加工 (Processing Phase):

• 监控生成结果，一旦拿到图片路径，立即触发加工程序。
• 调用 wechat-sticker-maker 的脚本：
• Auto Crop: 按 4x4 布局自动切图。
• Auto Resize: 统一缩放至 240x240 (主图) 和 50x50 (图标)。
• Meta Gen: 自动修改填充详情页所需的 info.txt 和 meta.txt。

3. 🖼️ 配套设计 (Assets Phase):

• 调用 wechat-sticker-assets-designer 技能。
• 分析已生成的 IP 角色视觉特征，分别生成横幅 (Banner, 750x400)、赞赏引导图 (750x560, 融合指定文案)、赞赏致谢图 (750x750, 融合指定文案)。
• 自动运行 run.sh 脚本执行条件化裁剪，得到精确官方尺寸的成品。

4. 📦 最终交付 (Delivery Phase):

• 向用户交付整合后的表情包输出目录的绝对路径（配套素材包含在内部的 assets/ 子目录中），并呈报图片预览。

📂 目录结构

skills/sticker-factory/
├── README.md               # 本说明文档
└── SKILL.md                # 流水线编排逻辑

注意：本 Skill 不包含具体代码脚本，它主要负责调度以下三个 Skill：

• ../grid-sticker-generator (负责画)
• ../wechat-sticker-maker (负责切)
• ../wechat-sticker-assets-designer (负责画微信配套 Banner、赞赏图及裁剪)

🗣️ 自然语言调用示例

这是最高效的使用方式，您只需关注结果：

场景一：标准生产（打工人主题 + 配套素材）

User: "工厂模式启动：帮我生产一套 '不想上班的树懒' 表情包。"

>

Factory: (生成树懒的 16 种摸鱼姿态 -> 自动切图 -> 自动生成配套横幅与赞赏图并裁剪到 assets/ 子目录 -> 返回整合后的输出目录)

场景二：自定义生产

User: "/sticker-factory 角色是'赛博朋克风格的兔子'，生成一套用于聊天的通用表情及相关发布素材。"

>

Factory: (生成赛博兔子 16 宫格 -> 自动切图 -> 自动生成配套横幅与赞赏图并裁剪到 assets/ 子目录 -> 返回整合后的输出目录)

💡 常见问题

• Q: 想要更高清的图？
• A: 您可以结合 ai-image-upscaler Skill，在生成原图后先将原图放大，然后再进行切图与后续处理。