image-prompt-generator
基于五层拆解法的AI图片提示词生成器。将模糊的创意想法转化为结构严谨、可执行的图像生成规格书,支持多种风格预设和目标工具适配。
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/349840432m-dev/image-prompt-generatorWhat This Skill Does
The image-prompt-generator is a specialized OpenClaw agent skill designed to bridge the gap between abstract creative ideas and concrete AI image generation. By leveraging the proprietary "Five-Layer Decomposition Method," the skill systematically deconstructs user requests into structured image specifications covering the scene, mood, texture, brushwork, and layout. It eliminates the guesswork often associated with complex AI art tools by providing optimized prompts tailored specifically for Midjourney, DALL-E, and Stable Diffusion, ensuring that users get high-quality, professional results regardless of their experience level.
Installation
To install this skill, use the OpenClaw CLI in your terminal:
clawhub install openclaw/skills/skills/349840432m-dev/image-prompt-generator
Once installed, the skill integrates directly with your local OpenClaw Gateway to process prompts through your configured AI models.
Use Cases
This skill is ideal for digital artists, content creators, and marketers. Use it to:
- Generate professional-grade visual assets from simple sketches or text descriptions.
- Maintain consistent art styles across a series of images using the provided presets.
- Create complex infographics by specifying data visualization requirements.
- Accelerate workflows for professional illustrators who need to iterate on character designs or concept art quickly.
Example Prompts
- "生成图片提示词:一张介绍深度学习的信息图,面向初学者"
- "用童趣涂鸦风格生成:一只可爱的小猫在看书"
- "生成提示词:赛博朋克风格的未来东京街头,霓虹灯雨夜"
Tips & Limitations
- Be Specific: The quality of the output depends on the clarity of your input. Include details about lighting, camera angles, and subject matter for the best results.
- Use Presets: If you are unsure about the aesthetic direction, start with one of the built-in styles (e.g., minimalist, retro film, or cyberpunk) to see how the AI interprets your request.
- Tool Selection: Remember that Midjourney, DALL-E, and Stable Diffusion interpret prompts differently. The skill automatically optimizes the output for the selected tool, so always specify your target platform if you have one.
- Local Execution: Note that all processing occurs through your local OpenClaw Gateway; ensure your system is online and configured properly for the Gateway endpoint at http://127.0.0.1:18789.
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-349840432m-dev-image-prompt-generator": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access
Related Skills
context-management
Agent 上下文管理方法论:通过分层文件体系实现跨 session 记忆延续、职责分离和高效上下文恢复。Use when: (1) 搭建新 agent 工作区, (2) 优化 agent 记忆和上下文管理, (3) 长期运行 agent 的记忆维护。
feishu-user-md
飞书端读取USER.md任务清单。当用户说"查看任务"、"我的任务"时触发,实时解析并返回格式化的分类任务列表,让用户快速了解当前所有可用任务和技能。
multi-agent-workshop
七阶段(含阶段0任务澄清)多角色工作坊;角色种类与人数均由任务决定。触发词:"多角色研讨"、"需求工作坊"、"需求评审"、"圆桌"、"定方案再执行"。