This is a wrapper around Google's Gemini 3 Pro image model that lets you generate, edit, and compose images through Python scripts. You get single image generation with text prompts, editing of existing images with instructions, and multi-image composition supporting up to 14 inputs. The resolution options are practical (1K, 2K) and it uses uv for fast Python execution. It's hosted in steipete's clawdis repo, which has solid traction at 376K stars and has passed security audits from Gen Agent Trust Hub, Socket, and Snyk. If you need AI image generation in your workflow without dealing with API boilerplate, this does the job cleanly.
npx skills add https://github.com/steipete/clawdis --skill nano-banana-pro