Gemini AI Image Generator
Automates high-quality AI image generation via Google Gemini with advanced style matching and browser-based automation.
This skill empowers Claude to create visual content by orchestrating Google Gemini's image generation capabilities through browser automation. It streamlines the creative workflow by managing persistent authentication and environment setup, allowing users to generate graphics directly from text prompts. Most notably, it features a reference image mode that analyzes existing visuals to extract style, lighting, and composition parameters, ensuring newly generated images maintain a consistent aesthetic across projects.
Características Principales
01Automated browser-based image generation via Google Gemini
02Persistent authentication management for multi-session use
03Meta-prompt optimization using YAML-based visual element extraction
04Shared session state with other Gemini-based productivity skills
05Reference image analysis for style-matching and aesthetic consistency
060 GitHub stars
Casos de Uso
01Automating visual content creation for sales letters and presentations
02Creating placeholder or production-ready assets for web development
03Generating brand-consistent graphics using reference style images