Provides text and image generation capabilities via the Gemini Web API for advanced AI-driven workflows.
The Gemini Web Client skill empowers Claude with the ability to interface directly with the Gemini Web API to perform complex tasks including high-fidelity image generation, vision-based analysis, and multi-turn conversations. By leveraging various models like Gemini 1.5 Pro and Flash-Thinking, this skill serves as a powerful backend for developers needing multimodal capabilities, such as creating visual assets from prompts or processing reference images. It includes automated browser-based authentication and session management to ensure a seamless integration within the Claude Code environment.
主な機能
010 GitHub stars
02Automated browser authentication and cookie caching
03Access to Gemini 1.5 Pro, Flash, and Thinking models
04Text and image generation via reverse-engineered Gemini Web API
05Multi-turn conversation state and session management
06Support for vision inputs using reference images
ユースケース
01Analyzing local design mockups or screenshots using Gemini's vision capabilities
02Generating production-ready images and UI assets directly from the CLI
03Utilizing Gemini's reasoning models for complex logic tasks that require 'thinking' phases
