skills.rest
arfaomar
arfaomarCOMMUNITY
Explore all skills by this author →
GitHub

gemini-api-dev

Implements Gemini API integrations with current models, SDKs, and multimodal capabilities.

Updated Aug 3, 2026
Search Tags:#llm#sdk#multimodal#gemini api#function calling#structured outputs#google-genai
One-click install
npx skills add https://github.com/arfaomar/NotebookLM-Clone --skill gemini-api-dev-arfaomar
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-api-dev
Source: https://github.com/arfaomar/NotebookLM-Clone/tree/main/.agents/skills/gemini-api-dev
Command: npx skills add https://github.com/arfaomar/NotebookLM-Clone --skill gemini-api-dev-arfaomar

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Developers building with the Gemini API often rely on outdated training data, using deprecated models like gemini-1.5 or legacy SDKs like google-generativeai. This Skill provides current model names, correct SDK packages, and working code patterns so generated code runs against the live API. ## Core Features & Use Cases - Current Model & SDK Reference: Lists supported Gemini and Gemma 4 models with context windows, plus the correct google-genai SDKs for Python, JavaScript/TypeScript, Go, and Java. - Quick Start Code: Provides working generate_content examples in four languages using the current client libraries. - Documentation Lookup: Directs the agent to the Google MCP search_docs tool when available, or to the official ai.google.dev llms.txt index as a fallback. - Use Case: When asked to add function calling or structured output to a TypeScript app, the agent uses @google/genai with gemini-3.6-flash instead of hallucinating deprecated APIs. ## Quick Start Ask the agent to write a Python script that sends a prompt to the Gemini API using the current SDK and model.

Frequently Asked Questions about gemini-api-dev

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I call the Gemini API from Python?▼

Install google-genai with pip, create a client via genai.Client(), and call client.models.generate_content with a model like gemini-3.6-flash and your prompt. The response text is available on response.text.

Which Gemini model should I use for my application?▼

Use gemini-3.6-flash for balanced agentic and multimodal tasks, gemini-3.5-flash-lite for high-throughput low-cost work, and gemini-3.1-pro-preview or gemini-2.5-pro for complex reasoning and coding. Image generation uses the Nano Banana preview models.

What is the difference between google-genai and google-generativeai?▼

google-genai is the current official Python SDK for the Gemini API, while google-generativeai is the legacy package and is deprecated. The same applies to @google/genai versus @google/generative-ai in JavaScript.

Does the Gemini API support function calling and structured outputs?▼

Yes, the Gemini API supports function calling and structured outputs through the google-genai SDKs. Detailed usage is documented on the official ai.google.dev pages for function-calling and structured-output.

How do I get up-to-date Gemini API documentation?▼

If the Google MCP server is installed, use its search_docs tool as the sole documentation source. Otherwise fetch the llms.txt index at ai.google.dev/gemini-api/docs and retrieve specific pages in .md.txt format.

Related Skills

Explore More Software Engineering Skills→
alon3153alon3153

agent-platform-migrate-from-ai-studio

Migrates Gemini API applications from Google AI Studio to Gemini Enterprise Agent Platform.

Community
Intermediate
kiurakkukiurakku
15

llm-integration

Integrate LLM APIs into production applications with streaming, cost control, and fallbacks.

Community
Advanced
amoai-techamoai-tech
1

gemini-live-api-dev

Build real-time bidirectional audio and video streaming applications with the Gemini Live API over WebSockets.

Community
Advanced
choice5346choice5346

chroma

Manage vector embeddings and metadata for semantic search applications.

Community
Intermediate