gemini-api-dev

This skill enables developers to build applications leveraging Google's Gemini models and the Gemini API. It provides guidance on working with multimodal content (text, images, audio, video), implementing function calling, utilizing structured outputs, and understanding current model specifications.

The skill covers the use of official SDKs (google-genai for Python, @google/genai for JavaScript/TypeScript, google.golang.org/genai for Go), model selection strategies, and understanding the API's capabilities. It also highlights the importance of staying updated with the latest API specifications and migrating from deprecated SDKs.

What It Does

Provides the AI agent with the ability to develop applications using the Gemini API, including text generation, multimodal understanding, function calling, structured outputs, and more. It also provides access to current model specifications and SDK usage.

When To Use

When the user needs to build applications that leverage the Gemini API's features, such as generating text, processing multimodal content, implementing function calling, or working with structured outputs. Also useful for tasks requiring current model specifications or SDK guidance.

Installation

Copy SKILL.md to your skills directory