A library of skills for the Gemini API, SDK and model interactions.
$ npx -y skills add google-gemini/gemini-skills --agent claude-code
Run the curl in your terminal, the rest in Claude Code.
Repo: google-gemini/gemini-skills
What's inside
A library of skills for the Gemini API, SDK and model interactions.
LLMs have fixed knowledge, being trained at a specific point in time. Software dev is fast paced and changes often, where new libraries are launched every day and best practices evolve quickly.
This leaves a knowledge gap that language models can't solve on their own. For example, models don't know about themselves when they're trained, and they aren't necessarily aware of subtle changes in best practices (like thought circulation) or SDK changes.
Skills are a lightweight technique for adding relevant context to your agents. This repo contains skills related to building apps powered by the Gemini API.
Our evaluations found that adding this skill improved an agent's ability to generate correct API code following best practices to 87% with Gemini 3 Flash and 96% with Gemini 3.1 Pro. For more details, see our blog post: Closing the knowledge gap with agent skills.
[!IMPORTANT] The
vertex-ai-api-devskill has moved to skills/cloud/gemini-api.
| Skill | Description |
|---|---|
gemini-api-dev | Skill for developing Gemini-powered apps. Provides the best practices for building apps that use the Gemini API. |
gemini-live-api-dev | Skill for building real-time, bidirectional streaming apps with the Gemini Live API. Covers WebSocket-based audio/video/text streaming, voice activity detection, native audio features, function calling, and session management. |
gemini-interactions-api | Skill for building apps with the Gemini Interactions API. Covers text generation, multi-turn chat, streaming, function calling, structured output, image generation, Deep Research agents, deprecated model guardrails, and both Python and TypeScript SDKs. |
gemini-omni-flash-api | Specialized generative AI video skill focused on video editing, image-referenced generation, and first-frame-to-video capabilities using the Interactions API. |
You can browse and install skills using either the Vercel skills CLI or the Context7 skills CLI.
# Interactively browse and install skills.
npx skills add google-gemini/gemini-skills --list
# Install a specific skill (e.g., gemini-interactions-api).
npx skills add google-gemini/gemini-skills --skill gemini-interactions-api
# Interactively browse and install skills.
npx ctx7 skills install /google-gemini/gemini-skills
# Install a specific skill (e.g., gemini-interactions-api).
npx ctx7 skills install /google-gemini/gemini-skills gemini-interactions-api
You can find additional information about setting up your coding assistant with Gemini API MCP and Skills in the docs.
This is not an officially supported Google product. This project is not eligible for the Google Open Source Software Vulnerability Rewards Program.
.gitignore
LICENSE
plugin.json
README.md
skills/
gemini-api-dev/
SKILL.md
gemini-interactions-api/
references/
migration.md
SKILL.md
gemini-live-api-dev/
SKILL.md
gemini-omni-flash-api/
scripts/
upload_file.py
video/
generate_video.py
inspect_video.py
prep_video.py
SKILL.mdGemini CLI is an open-source AI agent that brings the power of Gemini directly into your terminal. It provides lightweight access to Gemini, giving you the most direct path from your prompt to our model. Learn all about Gemini CLI in our documentation.
@google-geminiFAQ
gemini-skills is a Claude Code plugin with 4 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes gemini-api-dev, gemini-interactions-api, gemini-live-api-dev. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.