gemini-api-dev

Overview

A development skill for building applications with Google's Gemini models and the Gemini API. It provides comprehensive guidance on SDK usage across Python, JavaScript/TypeScript, Go, and Java, covering text generation, multimodal understanding, function calling, structured output, code execution, context caching, and embeddings.

Key Features

• Multi-SDK Support — Covers the latest SDKs for Python (google-genai), JavaScript (@google/genai), Go (google.golang.org/genai), and Java (com.google.genai), with migration guidance from deprecated legacy SDKs
• Current Model Specifications — Includes up-to-date model information for Gemini 3 Pro Preview, Flash Preview, and Pro Image Preview with token limits and capabilities
• Full API Coverage — Guides on text generation, multimodal content processing (images, audio, video, documents), function calling, structured JSON output, sandboxed code execution, context caching, and embedding generation

Who is this for?

Developers building applications that leverage Google's Gemini AI models. Especially helpful for those integrating Gemini capabilities into their apps and needing accurate, current SDK references and API usage patterns across multiple programming languages.