菜单
插画图片生成技能，支持多种手绘风格。使用 Imagen 3（ZenMux API）生成插图，适合流程图、功能说明、PPT配图、教程配图等场景。支持三种风格：A) Sketch 极简手绘风（Notion/Linear 风格，简笔人物，冷淡低饱和）；B) Watercolor 奶油彩铅水彩风（暖色调，纸纹彩铅，适合PPT讲义）；C) Flat Vector Retro 扁平矢量复古风（黑色轮廓线，几何简化，复古配色，适合NotebookLM PPT/课程封面）。生成后自动上传发送到飞书。当用户要求生成插画、配图、手绘风格图、流程示意图、产品插图、PPT配图时触发此技能。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Bloom Mission Discovery — find missions matched to your taste, submit content, and track rewards. Powered by Bloom Protocol.
DESCRIPTION of what this skill does. Include specific trigger keywords and scenarios. Use when: scenario1, scenario2, scenario3.
First-time setup for the Durable Agents stack (Mastra + Trigger.dev). Run once before using the main skill.
Read/search Gmail via gog CLI. Inbox check, email search, content retrieval.
One-sentence description. Use when [trigger scenarios].
Use cheap, TEE-verified AI models from the 0G Compute Network as OpenClaw providers. Discover available models and compare pricing vs OpenRouter, verify provider integrity via hardware attestation (Intel TDX), manage your 0G wallet and sub-accounts, and configure models in OpenClaw with one workflow. Supports DeepSeek, GLM-5, Qwen, and other models available on the 0G marketplace.
| name | sketch-illustration |
| description | 插画图片生成技能，支持多种手绘风格。使用 Imagen 3（ZenMux API）生成插图，适合流程图、功能说明、PPT配图、教程配图等场景。支持三种风格：A) Sketch 极简手绘风（Notion/Linear 风格，简笔人物，冷淡低饱和）；B) Watercolor 奶油彩铅水彩风（暖色调，纸纹彩铅，适合PPT讲义）；C) Flat Vector Retro 扁平矢量复古风（黑色轮廓线，几何简化，复古配色，适合NotebookLM PPT/课程封面）。生成后自动上传发送到飞书。当用户要求生成插画、配图、手绘风格图、流程示意图、产品插图、PPT配图时触发此技能。 |
支持两种手绘插画风格，按需选择，用 Imagen 3 生成并发送到飞书。
查看 references/styles.md 了解三种风格的详细说明和使用场景：
用户未指定时默认用风格 A。
references/styles.md 取对应风格块references/image-assistant-templates/基础结构：
[风格块（从 styles.md 复制）]
顶部居中标题：'[中文标题]'
[内容描述：人物、场景、元素、布局]
[负面约束]
详细提示词模板见 references/prompt-guide.md。
cd /root/.openclaw/workspace/skills/zenmux-image-generation
ZENMUX_API_KEY="<key>" python3 scripts/generate.py \
--output /root/myfiles/<filename>.png \
--prompt "<完整prompt>"
API Key 读取：
cat ~/.openclaw/openclaw.json | python3 -c "import json,sys; d=json.load(sys.stdin); print(d['models']['providers']['ZenMux']['apiKey'])"
bash scripts/send_to_feishu.sh /root/myfiles/<filename>.png <open_id>
猫南北的 open_id：ou_22f2eefd5abe63e0cd67f4882cec06d4
google/gemini-3-pro-image-preview（需要 ZenMux Pro+）/root/myfiles/references/image-assistant-workflow.md