#407 · Primary category： AI Agents & Automation
gemini-skills
Skills for the Gemini API, SDK and model/agent interactions
Project last updated：08/27/26
GitHub Stars
4.0K
Forks
411
Contributors
13
License
Apache-2.0
Why we included this project
Models only know what they were trained on, so an agent built against the Gemini API can be working from API and SDK details that have since changed. This repo packages that missing context as installable skills, small bundles of best-practice guidance that cover the core Gemini API, the real-time Live API, the Interactions API, and the Omni Flash video capabilities. If you are writing agent code for Gemini, you drop a skill into the agent's context rather than maintaining your own notes. The maintainers' evaluations put correct API code generation at 87 percent with Gemini 3 Flash and 96 percent with Gemini 3.1 Pro, which is a concrete reason to try it before building your own. It is a low-effort way to keep agent behavior in line with current Gemini documentation and SDK patterns.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
hermes-agent
The agent that grows with you
n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
deepseek-harness
DeepSeek Harness: Everything is a Plugin.
AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.