creative-toolkit
Generate images from text with multi-provider routing — supports Nanobanana Pro, GPT Image, Seedream, and local ComfyUI workflows. Includes 1,300+ curated prompts and style-aware prompt enhancement. Use when users want to create images, design assets, enhance prompts, or manage AI art workflows.
Why use this skill?
Generate professional AI images, enhance prompts, and manage local ComfyUI workflows effortlessly with this unified OpenClaw Creative Toolkit.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/jau123/creative-toolkitWhat This Skill Does
The Creative Toolkit is a comprehensive MCP-powered interface for AI image generation, designed to streamline artistic workflows by routing requests through high-performance providers like Nanobanana Pro, GPT Image, Seedream, or local ComfyUI instances. It eliminates the friction of jumping between different platforms by providing a unified command-line and agentic interface. Beyond simple generation, the toolkit features a massive library of over 1,300 curated prompts and a style-aware enhancement engine that transforms simple user inputs into highly detailed, production-ready prompts that exploit the full capabilities of modern diffusion models.
Installation
To install, use the OpenClaw hub CLI: clawhub install openclaw/skills/skills/jau123/creative-toolkit. Once installed, add the server configuration to your ~/.config/mcporter/config.json file. Ensure you have the MEIGEN_API_TOKEN environment variable set if you intend to use the premium cloud-based generation features. For local workflows, simply point the configuration to your ComfyUI URL, and the skill will automatically discover your node parameters, making your local art pipeline accessible via natural language commands.
Use Cases
This skill is perfect for digital artists, social media managers, and developers looking to integrate AI assets into their applications. Use it to generate consistent brand imagery, enhance rough sketches via prompt-to-prompt workflows, or automate your local ComfyUI generation batches without manual UI interaction. It is particularly effective for users who want to compare output styles across different models simultaneously.
Example Prompts
- "Enhance this: a cat in space, then generate it using the FLUX.1 model."
- "Search the gallery for cyberpunk aesthetics and save a few as inspiration for a new logo design."
- "Generate a minimalist perfume bottle on white marble with soft lighting, and use my local ComfyUI workflow for the render."
Tips & Limitations
To get the best results, use the enhance_prompt tool before sending your request to the image generator; the model works best when given descriptive sensory details (lighting, texture, mood). Note that while many features work in local/stdio modes without keys, the premium cloud providers require a valid token to function. Always ensure your ComfyUI instance is running and accessible via the specified port before triggering local generation workflows. For complex character consistency, consider using the local ComfyUI routing to maintain control over seeds and LoRA injections.
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-jau123-creative-toolkit": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: external-api, file-read, network-access