What multimodal formats are supported?

The integration supports text, images, video, audio, and PDF documents within the same request for comprehensive multimodal understanding.

Which Node.js SDK should I use for Google Gemini?

You must use @google/genai. The older @google/generative-ai package was deprecated as of November 30, 2025.

How many tokens does the Gemini 2.5 context window support?

Gemini 2.5 models support up to 1,048,576 input tokens and 65,536 output tokens.

Does this skill support Gemini's Thinking Mode?

Yes, it provides specific configurations for Thinking Mode, which is enabled by default in the Gemini 2.5 and 3 series for complex reasoning.

Can I use this with edge runtimes like Cloudflare Workers?

Yes, the skill includes a Fetch-based direct REST API approach specifically for environments where the Node.js SDK may not be compatible.

Google Gemini API Integration

Name: Google Gemini API Integration
Author: brendadeeznuts1111

bybrendadeeznuts1111

API 개발

Integrates the latest Google Gemini API using the current @google/genai SDK for multimodal processing, reasoning, and real-time grounding.

소개

This Claude Code Skill provides a comprehensive framework for implementing Google's Gemini 3 and 2.5 models while strictly avoiding deprecated SDKs. It offers standardized patterns for text generation, streaming, and complex multimodal inputs involving video, audio, and PDFs. Designed for production readiness, the skill includes error prevention for 14 known issues, context caching strategies to optimize costs, and configuration guides for 'Thinking Mode' and parallel function calling, ensuring high-performance AI integration within the Claude environment.

주요 기능

Implementation patterns for parallel function calling and Google Search grounding
Context caching and TTL management for efficient 1M+ token window handling
Full migration guide from deprecated @google/generative-ai to @google/genai SDK
Advanced configuration for Gemini Thinking Mode and reasoning tasks
Support for multimodal inputs including video, audio, and multi-page PDFs
0 GitHub stars

사용 사례

Creating reasoning-intensive applications leveraging Gemini 3 Pro's thinking capabilities
Developing high-throughput agents using cost-optimized context caching
Building multimodal RAG systems that analyze video and audio documentation

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add brendadeeznuts1111/tier-1380-omega google-gemini-api

For use in Claude.ai and ChatGPT

Download Skill

GitHub

소개