Integrates Google Gemini's web-based text and image generation capabilities directly into Claude workflows.
A robust utility skill that enables Claude to leverage the web-based version of Google Gemini for advanced text generation, high-quality image creation, and visual analysis. It functions as a versatile backend for creative tasks, supporting multi-turn conversations through persistent session management and vision-based inputs for processing local images, effectively bridging the gap between Claude and Gemini's creative suite.
Key Features
01High-fidelity image generation from descriptive text prompts
02Vision input processing for analyzing and referencing local images
03Automated cookie-based authentication and session caching
04Persistent multi-turn conversation support using unique session IDs
0511 GitHub stars
06Support for multiple model tiers including Gemini Pro and Flash
Use Cases
01Generating custom illustrations and cover images for articles and social media
02Maintaining context-aware AI dialogues for multi-step creative workflows
03Performing complex visual-to-text analysis on local image files
