sketch-illustration
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、知识图和手绘信息图等场景。支持四种风格：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）；D) Doodle Infographic 白纸手绘知识图风（白纸背景、拟人角色、高信息密度、手账/课堂板书感，适合概念对比、方法论、拖延机制、知识卡片）。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、知识图、信息图、手绘知识海报时触发此技能。
Why use this skill?
Generate professional hand-drawn illustrations, flowcharts, and infographic knowledge maps with the OpenClaw sketch-illustration skill. Supports four styles and automatic Feishu delivery.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/dadaniya99/sketch-illustrationWhat This Skill Does
The sketch-illustration skill is a powerful generative AI tool for OpenClaw that enables users to create high-quality, stylistically consistent illustrations using the Imagen 3 model via ZenMux API. This skill is specifically designed for professional and academic contexts, offering four distinct artistic styles: Sketch (minimalist), Watercolor (warm/textural), Flat Vector Retro (structured), and Doodle Infographic (hand-drawn knowledge mapping). The skill automates the entire pipeline: from intelligent prompt construction based on predefined templates to high-fidelity image generation and automated delivery to Feishu, ensuring a seamless workflow for creators, developers, and educators.
Installation
To install this skill, use the following command in your OpenClaw terminal:
clawhub install openclaw/skills/skills/dadaniya99/sketch-illustration
Ensure that your ZenMux API key is correctly configured in your ~/.openclaw/openclaw.json file as the script will dynamically pull this key for authentication during the generation process.
Use Cases
- Technical Documentation: Use the Sketch style to create Notion-like minimalist flowcharts or system architecture diagrams.
- Educational Materials: Use the Watercolor style for warm, engaging PPT presentation slides or course handouts.
- Content Creation: Use the Flat Vector Retro style for NotebookLM-style course covers or blog thumbnails.
- Complex Concept Visualization: Use the Doodle Infographic style to convert abstract ideas or methodology into hand-drawn, high-information-density knowledge posters that are perfect for sharing on team communication platforms.
Example Prompts
- "帮我画一张极简风格的流程图，展示用户注册到登录的数据验证逻辑，用Notion风格。"
- "生成一张关于延迟满足的知识图，风格要用白纸手绘风，包含一个拟人的小蜗牛形象，并展示大脑如何控制冲动。"
- "为我的PPT制作一张配图，主题是团队协作，风格选择奶油彩铅水彩风，暖色调，看起来要温馨一些。"
Tips & Limitations
- Style Selection: When unsure, the system defaults to Style A. If you need complex data visualization, prioritize Style D and specify the chart type (mechanism, comparison, or flow).
- Information Density: For Style D, avoid dense text paragraphs. Use titles, bullet points, arrows, and metaphors with cute characters to maintain clarity and aesthetic appeal.
- API Stability: The skill utilizes
google/gemini-3-pro-image-preview. If you encounter a 403 error during generation, it is usually a transient issue; please retry the operation. - File Management: Generated assets are saved to
/root/myfiles/. Regularly clean up this directory to maintain workspace performance.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-dadaniya99-sketch-illustration": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, external-api, code-execution
Related Skills
evomap-gep
Connect any OpenClaw agent to the EvoMap collaborative evolution marketplace via the GEP-A2A protocol — no evolver required. Activate when the user or agent mentions EvoMap, wants to search for capsules or genes from other agents, publish a solution, or learn the GEP protocol. sender_id is auto-detected from MEMORY.md — each agent just saves their node ID once and the scripts handle the rest.
feishu-card
飞书互动卡片发送技能（国际版 Feishu 兼容）。当需要发送格式丰富的飞书卡片消息时使用。支持标题、Markdown 内容、颜色主题。关键：必须使用 schema 2.0 格式 + 双重 JSON stringify，否则国际版飞书（Feishu）无法渲染。
pdf-ocr
PDF扫描件转Word文档。支持中文OCR识别，自动裁掉页眉页脚，保留插图，彩色章节封面页保留为图片。使用百度OCR API（免费额度1000次/月）。当用户要求把扫描PDF转成文字/Word时触发。
cn-video-gen
国产AI视频生成技能。支持通义万相（Wan2.6文生视频/图生视频）和可灵（Kling V2）。适合创意视频制作、图生视频、动态内容生成等场景。当用户要求生成视频、将图片生成动态视频、或基于描述生成视频片段时触发。
eudic-vocab
欧路词典生词本管理与每日测试技能。支持自动从欧路词典收藏夹出题、管理单词、删除已掌握词汇。适合每日背单词使用。