skills.rest
nimdvir
nimdvirCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

gemini-api-dev

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

1|Updated May 26, 2026
Search Tags:#multimodal#llm development#gemini api#function calling#structured outputs#google-genai#sdk migration
One-click install
npx skills add https://github.com/nimdvir/dima-publishing --skill gemini-api-dev-nimdvir
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-api-dev
Source: https://github.com/nimdvir/dima-publishing/tree/main/.agents/skills/gemini-api-dev
Command: npx skills add https://github.com/nimdvir/dima-publishing --skill gemini-api-dev-nimdvir

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 Developers building with the Gemini API often rely on outdated training data, using deprecated models like gemini-1.5 or legacy SDKs like google-generativeai.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 window sizes, plus the correct google-genai SDKs for Python, JavaScript/TypeScript, Go, and Java. - Quick Start Code Patterns: Provides working generate_content examples in four languages covering text generation, multimodal input, function calling, and structured outputs. - Documentation Lookup Strategy: Directs the agent to the Google MCP search_docs tool when available, or to the official llms.txt documentation index as a fallback. - Use Case: You ask an agent to build a Python script that summarizes images with Gemini. The Skill ensures it uses google-genai with gemini-3.5-flash instead of a deprecated SDK and model. ## Quick Start Ask the agent to write a Python script using the Gemini API that generates text with the gemini-3.5-flash 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 the google-genai package with pip, create a client via genai.Client(), and call client.models.generate_content with a model like gemini-3.5-flash and your prompt. The response text is available on the response.text attribute.

Which Gemini model should I use for my application?▼

Use gemini-3.5-flash for fast balanced multimodal tasks, gemini-3.1-pro-preview for complex reasoning and coding, and gemini-3.1-flash-lite-preview for high-frequency lightweight calls. Image generation uses the gemini-3-pro-image-preview or gemini-3.1-flash-image-preview models.

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

google-genai is the current supported Python SDK for the Gemini API, while google-generativeai is the legacy deprecated package that should no longer be used. The same applies to @google/genai replacing @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. Official documentation pages for both features are available at ai.google.dev in markdown format for detailed implementation guidance.

How do I get real-time audio streaming with Gemini?▼

Real-time bidirectional audio, video, and text streaming is handled by the Gemini Live API over WebSockets. This Skill directs you to install the separate gemini-live-api-dev skill for session management, voice activity detection, and ephemeral tokens.

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
gke-labsgke-labs
42

kube-agents-observability

Audit logs, metrics, and traces for Platform Agent on GKE.

Official
Advanced
JetBrainsJetBrains
302

gemini-live-api-dev

Stream audio, video, and text bidirectionally over WebSockets with Gemini Live API.

Official
Advanced
pydanticpydantic
19.6k

add-new-model

Wire newly released LLM model identifiers into pydantic-ai profiles, literals, and tests.

Official
Advanced