Gemini Skill

•
833
•

Automate Gemini web operations for AI image generation, text conversations, and content extraction via Chrome DevTools Protocol.

This tool leverages the Chrome DevTools Protocol (CDP) to programmatically interact with the Gemini web interface (gemini.google.com). It enables advanced automation for AI image generation, including high-resolution downloads and watermark removal, multi-turn text conversations, image uploads for reference, and the extraction of generated images. Designed as an MCP Server, it seamlessly integrates with any MCP client like Claude or CodeBuddy, providing a robust set of functionalities for AI agents to control Gemini. Its architecture includes a daemon mode for efficient browser management and stealth features to avoid detection, ensuring reliable operation.

Key Features

01Engage in multi-turn text conversations with Gemini.
02Standard MCP protocol interface for seamless AI client integration.
03Upload reference images to guide new image generation.
04Extract and download generated images from chat sessions.
051 GitHub stars
06Automated AI image generation with high-resolution download and watermark removal.

Use Cases

01Programmatically managing Gemini sessions for advanced image queries and content extraction.
02Integrating Gemini's conversational AI capabilities into AI agents for dynamic interactions.
03Automating the creation of AI-generated images, such as game assets or social media content.