Prompt Bozo for Openclaw

A professional modular prompt generator for high-fidelity AI image and video production supporting diverse generation modes.

bozoyan
v1.0.0
Mar 18, 2026
0
923
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install prompt-bozo

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install prompt-bozo using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Prompt Bozo?

Prompt Bozo is a specialized AI coding agent tool designed to streamline the creation of complex prompts for AI art and video platforms like Midjourney, Stable Diffusion, and Jimeng AI. By utilizing a modular framework, it translates simple user intent into highly detailed, parameter-driven descriptions that cover everything from character design and hairstyles to camera movement and lighting.

This skill excels at maintaining consistency across different generation modes, such as Text-to-Image (T2I) and Image-to-Video (I2V). As a key component of the Openclaw Skills library, it integrates deep cultural knowledge, offering specific modules for traditional Chinese aesthetics, Hanfu details, and cinematic camera language to ensure professional-grade outputs every time.

Prompt Bozo Use Cases

  • Creating high-fidelity character concepts with specific hairstyles and poses.
  • Generating consistent video sequences from static reference images (I2V).
  • Designing culturally accurate traditional Chinese or ancient-style artwork.
  • Automating the inclusion of cinematic technical details like focal length and lighting styles.
  • Developing transition videos using start-and-end frame interpolation.

How Prompt Bozo Works

  1. The agent identifies the generation mode (T2I, I2I, T2V, I2V, or First-Last Frame) based on user input and available reference assets.
  2. It collects core parameters including subject characteristics, environment, and specific aesthetic requirements.
  3. The skill loads relevant reference modules such as camera.md, poses.md, or chinese-style.md to enrich the prompt with technical terminology.
  4. It assembles the final prompt using a precise control framework: [Subject], [Environment], [Style], [Composition], [Lighting], [Camera], and [Technical Details].
  5. The agent outputs a seamless, natural language paragraph optimized for the target AI model without any explanatory meta-text.

Prompt Bozo Setup

To integrate Prompt Bozo into your environment, ensure your agent has access to the reference directory and the Openclaw Skills configuration.

# Clone the skill repository into your agent's skills folder
git clone https://github.com/openclaw/prompt-bozo.git

# Ensure reference documents are linked
ln -s ./prompt-bozo/references ./your-agent/references

Prompt Bozo Data Schema & Taxonomy

Prompt Bozo organizes its creative intelligence through a structured directory of Markdown reference files:

File Content Type
framework.md Core prompt structure and composition rules
camera.md Cinematic lens movements and angles
chinese-style.md Traditional aesthetics, architecture, and Hanfu details
poses.md / character-design.md Subject postures and character archetypes
hairstyles.md Detailed hair design parameters
locations.md Geographic and environmental scene settings

Prompt Bozo Advanced Features

  • Multi-mode adaptation: Automatically shifts prompt weighting for video vs. static image generation.
  • Cultural Engine: Specialized triggers for dynasties (Han, Tang, Ming) and specific garment construction (Mamian skirt, Ruqun).
  • Dynamic Reference Loading: Only loads the contextually necessary Markdown files to keep the agent's context window efficient.
  • Technical Detail Injection: Automatically appends quality boosters like "Ultra-high definition" and "Professional Photography" based on the selected framework.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*