prompt-bozo

What This Skill Does

Prompt Bozo is an advanced AI assistant tailored for the systematic generation of prompts for AI image and video creation. It acts as a bridge between user requirements and high-quality AI generation models such as Midjourney, Stable Diffusion, and Jimo AI. The skill utilizes a modular architecture to ensure that every aspect of a scene—from character design and cinematic camera movements to intricate traditional Chinese aesthetics—is captured with precision. By following a structured parameterization framework, it allows users to specify subjects, environments, lighting, and technical details to achieve professional-grade results.

Installation

To install this skill, run the following command in your terminal: clawhub install openclaw/skills/skills/bozoyan/prompt-bozo

Use Cases

• Professional Photography: Generate detailed prompts for portrait or landscape photography with specific camera angles and lens settings.
• Cinematic Video Production: Create complex prompts for text-to-video or image-to-video tasks, incorporating dynamic camera movement and motion descriptors.
• Traditional Chinese Aesthetics: Access a deep library of cultural elements, including detailed descriptions of historical garments like Hanfu, traditional architecture, and period-specific stylistic choices.
• Creative Character Design: Rapidly generate consistent character prompts across various poses and scenarios for digital storytelling.

Example Prompts

1. "帮我生成一张在故宫红墙前穿着宋制汉服的少女，背景有桃花，要唯美古风质感。"
2. "我要制作一个图生视频，人物是参考图中这位穿着旗袍的女性，加上镜头运镜，表现出她在雨中漫步的感觉。"
3. "生成一个赛博朋克风格的城市街道，广角镜头，霓虹灯光影，要极具电影质感的文生图提示词。"

Tips & Limitations

• Specificity Matters: Always provide as much detail about the subject as possible. The more specific your description (e.g., specific hairstyle, fabric type, or time of day), the better the output quality.
• Use the Framework: The skill relies on the [Subject], [Environment], [Style], [Composition], [Lighting], [Camera], [Technical] framework. Try to keep your requests mapped to these categories for the best results.
• Language Support: While the skill is optimized for high-quality Chinese prompts, it handles complex descriptors well.
• Limitations: Note that this skill generates text-based prompt instructions. It does not interface directly with the GPU rendering process of your chosen AI tool, so you will still need to copy these prompts into your specific generation interface (e.g., Stable Diffusion or Midjourney).