Repolode
Submit
google-gemini

google-gemini/gemini-skills

A collection of agent skills that give AI coding assistants up-to-date context for building apps with the Gemini API and SDKs.

View on GitHubWebsite
Stars
4,414
Forks
485
Open issues
14
Last commit
2 days ago

What is it?

LLMs are trained at a fixed point in time, so they often miss new SDK releases, API changes and current best practices for the Gemini API. This repository provides skills, a lightweight way to add relevant context to coding agents, so they generate more accurate Gemini API code.

The repo includes four skills: gemini-api-dev for building apps with the Interactions API across Python and TypeScript SDKs, gemini-api-cli for calling Gemini from the shell, gemini-live-api-dev for real-time bidirectional audio, video and text streaming over WebSockets, and gemini-omni-flash-api for video generation and editing. Skills can be installed through the Vercel skills CLI, Context7, Claude Code, Cursor, OpenAI Codex and Antigravity.

The project is not an officially supported Google product.

Key features

  • 01Covers text generation, chat, streaming and function calling with the Gemini API
  • 02Includes image, speech (TTS) and video generation skills
  • 03Provides a real-time Live API skill for audio, video and text streaming
  • 04Offers a shell CLI skill for calling Gemini from scripts
  • 05Installs into Claude Code, Cursor, OpenAI Codex, Antigravity and other agent tools

Use cases

  • Helping a coding agent write correct Gemini API calls in Python or TypeScript
  • Building a real-time voice or video assistant on the Gemini Live API
  • Calling Gemini image, audio or video generation from shell scripts
  • Generating or editing short videos with the Gemini Omni Flash model

Quick start

  1. 1

    Browse and install skills interactively with the Vercel skills CLI

    npx skills add google-gemini/gemini-skills --list
  2. 2

    Or install the gemini-api-dev skill directly

    npx skills add google-gemini/gemini-skills --skill gemini-api-dev

Things to know

  • This is not an officially supported Google product.
  • The vertex-ai-api-dev skill has moved to a different repository.

In collections

Open-source AI agent frameworks & appsAI agent skill librariesStreaming tools

Topics

#gemini#llm#ai-agents#coding-assistant#sdk#speech-synthesis#function-calling#streaming#gemini-api#skills

FAQ

What is gemini-skills?
A collection of agent skills that give AI coding assistants up-to-date context for building apps with the Gemini API and SDKs. LLMs are trained at a fixed point in time, so they often miss new SDK releases, API changes and current best practices for the Gemini API. This repository provides skills, a lightweight way to add relevant context to coding agents, so they generate more accurate Gemini API code.
Is gemini-skills free to use? What license does it have?
gemini-skills is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
Is gemini-skills still maintained?
Actively maintained. The last commit to gemini-skills was on Nov 5, 2026.
What can I use gemini-skills for?
Helping a coding agent write correct Gemini API calls in Python or TypeScript Building a real-time voice or video assistant on the Gemini Live API Calling Gemini image, audio or video generation from shell scripts Generating or editing short videos with the Gemini Omni Flash model
How do I install gemini-skills?
Browse and install skills interactively with the Vercel skills CLI: npx skills add google-gemini/gemini-skills --list Or install the gemini-api-dev skill directly: npx skills add google-gemini/gemini-skills --skill gemini-api-dev
Where can I get gemini-skills?
The source code and installation instructions are on GitHub: https://github.com/google-gemini/gemini-skills

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects