Last commit on September 2, 2026·Created on February 6, 2026
google-gemini/gemini-skills
“Technical guidance for building multimodal applications with the Gemini API and Live API”
Combined rank
#94
across all skills
Stars
4k
7d change unavailable
Forks
414
Watchers
40
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of real attention, adoption, and active maintenance.
TL;DR
This collection provides implementation patterns for developers integrating Gemini models into Python and TypeScript applications. It covers the transition from legacy APIs to current standards for text generation, structured output, and background research tasks.
The repository includes specific guidance for real-time, bidirectional streaming via the Gemini Live API, focusing on WebSocket management, voice activity detection, and ephemeral token authentication for client-side security.
WHO IT'S FOR
AI agent / automation builders
implementing function calling and structured output
Real-time application developers
building bidirectional audio and video streaming
Generative video engineers
creating text-to-video and generative editing workflows
Full-stack AI engineers
integrating multimodal LLM capabilities into apps
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Want to install it?
Claude Marketplace · Claude Plugin · NPX Skills AddRepository instructions