mulerouter
Generates images and videos using MuleRouter or MuleRun multimodal APIs. Text-to-Image, Image-to-Image, Text-to-Video, Image-to-Video, video editing (VACE, keyframe interpolation). Use when the user wants to generate, edit, or transform images and videos using AI models like Wan2.6, Veo3, Nano Banana Pro, Sora2, Midjourney.
Why use this skill?
Use the MuleRouter skill to generate, edit, and transform images and videos with advanced models like Wan2.6 and Veo3 directly through OpenClaw.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/misaka43fd/mulerouter-skillsWhat This Skill Does
The mulerouter skill for OpenClaw provides a unified interface for interacting with high-end multimodal AI models. It acts as a routing agent to connect your environment with powerful inference APIs like MuleRouter and MuleRun. Whether you need to generate high-fidelity images via Midjourney, create cinematic videos using Wan2.6 or Veo3, or perform complex video transformations like keyframe interpolation and VACE, this skill handles the heavy lifting. It includes built-in support for image preprocessing, automatically handling the conversion of local file paths to base64 to ensure API compatibility and avoid command-line character limitations.
Installation
To integrate this skill into your OpenClaw environment, execute the following command: clawhub install openclaw/skills/skills/misaka43fd/mulerouter-skills. Ensure you have the uv package manager installed as it is required for dependency synchronization. Once installed, navigate to the skills/mulerouter-skills/ directory, create a .env file for your MULEROUTER_API_KEY, and run uv sync to install all necessary Python dependencies.
Use Cases
- Creative Content Production: Generate professional-grade promotional imagery or short-form video clips from text descriptions.
- Multimedia Enhancement: Use Image-to-Video capabilities to animate static photography, perfect for digital marketing or social media assets.
- Automated Media Pipelines: Streamline repetitive generation tasks by integrating model scripts into larger automation workflows.
- Model Experimentation: Quickly switch between different backbone models like Nano Banana Pro or Sora2 to compare output quality for specific stylistic requirements.
Example Prompts
- "Generate a 10-second cinematic video of a futuristic cyberpunk city at sunset using the Wan2.6 model."
- "Transform this local image /tmp/input_sketch.png into a detailed oil painting using the Midjourney integration."
- "Create a gentle zoom-in video effect using this image: https://example.com/mountain.jpg and keep the original landscape aesthetic."
Tips & Limitations
- Pathing: Always prefer absolute local file paths over remote URLs when processing sensitive data to ensure high-speed, reliable uploads.
- Environment Variables: Remember that
MULEROUTER_BASE_URLtakes precedence overMULEROUTER_SITE. If your API calls fail, verify your environment configuration withechocommands provided in the documentation. - Efficiency: The skill is designed to run from the root directory; attempting to execute generation scripts from outside the specific model folders may result in relative path resolution errors.
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-misaka43fd-mulerouter-skills": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-read, external-api, code-execution