google-gemini/gemini-skills▌

Real-time bidirectional streaming with Gemini over WebSockets for audio, video, and text conversations. \n \n Supports audio input/output (16 kHz PCM), video frames, text, and automatic transcriptions with voice activity detection for interruption handling \n Includes native audio features: affective dialog, proactive audio, and thinking mode; function calling for synchronous and asynchronous tool use; and Google Search grounding \n Offers session management with context compression, resumption,

Access Google's most advanced AI models built for enterprise use cases using the Gemini API in Vertex AI.

Unified interface for Gemini models and agents with server-side state, streaming, and tool orchestration. \n \n Supports multiple current models (gemini-3-flash-preview, gemini-3-pro-preview, gemini-2.5-flash/pro) and the Deep Research agent; automatically substitute deprecated model IDs with current alternatives \n Offload conversation history to the server via previous_interaction_id for stateful multi-turn interactions without manual history management \n Built-in tool orchestration including

Build applications with Google's Gemini models, supporting multimodal content, function calling, and structured outputs across Python, JavaScript, Go, and Java. \n \n Access current Gemini 3 models (Pro, Flash, Pro Image) with 1M token context; legacy Gemini 2.x and 1.5 models are deprecated \n Supports text generation, image/audio/video understanding, function calling, structured JSON output, code execution, context caching, and embeddings \n Official SDKs available: google-genai (Python), @goo