image-gen

Generate images using Gemini via ZenMux

⭐2stars🔀0forks📁View on GitHub🕐Updated Dec 19, 2025⬇️1downloads

When & Why to Use This Skill

This Claude skill enables seamless AI image generation by leveraging Google's Gemini models through the ZenMux API. It allows users to programmatically create high-quality visual assets directly within their workflow using natural language prompts, offering customizable quality settings and output options to streamline creative production.

Use Cases

  • Automated Content Creation: Generate relevant blog post headers or social media graphics directly from text descriptions.
  • Rapid Prototyping: Quickly visualize UI/UX concepts or product ideas during the design phase without leaving the terminal or chat interface.
  • Marketing Asset Generation: Create diverse variations of visual content for A/B testing and digital advertising campaigns.
  • Enhanced AI Communication: Allow the agent to provide visual representations of complex concepts, artistic ideas, or data visualizations discussed in a session.
nameimage-gen
descriptionGenerate images using Gemini via ZenMux
allowed-tools[Bash, Read]

Usage

python3 ~/.claude/skills/image-gen/gen_image.py "PROMPT" [-o output.png] [-q low|medium|high] [--ascii]

Display result with Read tool after generation.