About this project

Gemini API skills is a library of skills for the Gemini API, SDK and model interactions. It addresses the knowledge gap that arises because LLMs are trained at a fixed point in time, while software development changes quickly: new libraries appear and best practices evolve, so models may not know about themselves or about subtle changes such as thought circulation or SDK updates. Skills are described as a lightweight technique for adding relevant context to agents, and this repository collects skills related to building apps powered by the Gemini API. The README reports internal evaluations in which adding the 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, with further details in a linked blog post. Skills included: - gemini-api-dev: building apps with the Gemini API (Interactions API). Covers text generation, multi-turn chat, streaming, function calling, structured output, image generation, managed agents, Deep Research, deprecated model guardrails, and both Python and TypeScript SDKs. - gemini-live-api-dev: 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-omni-flash-api: a specialized generative AI video skill focused on Gemini Omni 1.1 Flash, video editing, image and video referenced generation, first and last frame transitions, and video extensions using the Interactions API. The README notes that the vertex-ai-api-dev skill has moved to a separate google/skills repository under skills/cloud/gemini-api. Installation options documented include the Vercel skills CLI (npx skills add google-gemini/gemini-skills, with --list to browse and --skill to install a specific skill), the Context7 skills CLI (npx ctx7 skills install), Antigravity (bundled under Customizations → Build with Google Plugins, or via agy plugin install), Claude Code (plugin marketplace add and plugin install commands), Cursor (from the plugin directory or /add-plugin), and OpenAI Codex (codex plugin marketplace add and codex plugin add). Additional setup information for coding assistants with Gemini API MCP and Skills is linked in the Gemini API docs. The README includes a disclaimer that this is not an officially supported Google product and is not eligible for the Google Open Source Software Vulnerability Rewards Program.