Last commit on October 13, 2026·Created on February 6, 2026
google-gemini/gemini-skills
“A technical guide for implementing multimodal generation and structured outputs via the Gemini API”
Combined rank
#118
across all skills
Stars
4.3k
+0.8% in last 7d
Forks
461
+2.0% in last 7d
Watchers
44
0.0% in last 7d
Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
TL;DR
This skill provides developers with the patterns and best practices needed to integrate Gemini models into Python and TypeScript applications. It focuses on the transition from basic text generation to complex multimodal workflows involving image, video, and speech synthesis.
Engineers can use these resources to implement multi-turn chat, function calling, and bidirectional streaming responses while ensuring structured output for reliable data parsing.
WHO IT'S FOR
AI application developers
implementing multimodal text, image, and speech generation
Real-time AI engineers
building bidirectional streaming audio and video apps
Generative video creators
automating text-to-video and generative video editing
AI agent architects
designing function calling and background research workflows
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.
Claude
Codex
Cursor
Gemini CLI
AntigravityWant to install it?
Claude Marketplace · Claude Plugin · NPX Skills AddRepository instructions