This skill equips Claude with specialized knowledge for developing and integrating Google's Gemini API, focusing on the latest Gemini 3 Pro and Flash models. It provides domain-specific guidance on implementing text generation, multimodal processing, function calling, and structured JSON outputs while ensuring developers use the most current SDKs. By referencing live API discovery specs and official documentation, the skill helps automate the migration from legacy libraries and enables advanced features like context caching and sandboxed code execution for robust AI-driven applications.
主要功能
01128 GitHub stars
02Comprehensive support for Gemini 3 Pro and Flash model integration
03Context caching and text embedding implementation for semantic search
04Structured output and function calling schema design
05Expert implementation guidance for Python, JavaScript, and Go GenAI SDKs
06Multimodal understanding patterns for image, audio, and video processing
使用场景
01Developing automated agents that utilize function calling and sandboxed Python execution
02Building high-performance AI chatbots and multimodal content analyzers
03Migrating legacy Google AI Studio integrations to the modern Gemini 3 architecture