skills.rest
arslan9024
arslan9024COMMUNITY
Explore all skills by this author →
GitHub

gemini-api-dev

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

Updated Jan 8, 2026
Search Tags:#image generation#multimodal#gemini api#llm integration#function calling#structured outputs#google-genai
One-click install
npx skills add https://github.com/arslan9024/White-Caves --skill gemini-api-dev-arslan9024
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-api-dev
Source: https://github.com/arslan9024/White-Caves/tree/main/.agents/skills/gemini-api-dev
Command: npx skills add https://github.com/arslan9024/White-Caves --skill gemini-api-dev-arslan9024

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Developers often rely on outdated training data when building with the Gemini API, leading to deprecated model names, legacy SDKs, and broken code. This Skill provides current model identifiers, correct SDK packages, and up-to-date documentation lookup paths for Gemini and Gemma development. ## Core Features & Use Cases - Current Model & SDK Reference: Lists active models (gemini-3.7-flash, gemini-3.1-pro-preview, gemma-4, embedding models) and correct SDKs (google-genai for Python, @google/genai for JS/TS, plus Go and Java packages), while flagging deprecated ones. - Multimodal Development Guidance: Covers text generation, function calling, structured outputs, image generation and editing, video generation, audio transcription, and embeddings. - Documentation Lookup: Directs agents to MCP-based doc search when available, or to the official llms.txt index and .md.txt documentation pages as a fallback. - Use Case: When asked to add image generation to an app, the Skill ensures you use gemini-3-pro-image-preview with the @google/genai SDK instead of a deprecated model or legacy package. ## Quick Start Ask the agent to write a Python script using the Gemini API that generates text with function calling, and it will use the current google-genai SDK and a supported 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 get started with the Gemini API in Python?▼

Install the google-genai package with pip, create a client using genai.Client(), and call client.models.generate_content with a current model like gemini-3.7-flash. The legacy google-generativeai package is deprecated and should not be used.

Which Gemini model should I use for my application?▼

Use gemini-3.7-flash for fast balanced multimodal tasks, gemini-3.1-pro-preview for complex reasoning and coding, and gemini-3.5-flash-lite for high-throughput low-cost execution. Image generation uses the Nano Banana preview models, and embeddings use gemini-embedding-2.

What is the correct JavaScript SDK for the Gemini API?▼

Use the @google/genai npm package and import GoogleGenAI from it. The older @google/generative-ai package is deprecated and must not be used for new development.

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

Yes, the Gemini API supports function calling and structured outputs through the current google-genai SDKs. Detailed guidance is available via the MCP documentation search tool or the official function-calling and structured-output documentation pages.

Why should I avoid gemini-1.5 and gemini-2.0 models?▼

Models in the gemini-2.0-* and gemini-1.5-* families are legacy and deprecated. Current development should use the gemini-3.x series, gemini-2.5-pro, gemini-2.5-flash, or gemma-4 models listed in the Skill.

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

Real-time bidirectional audio, video, and text streaming uses the Gemini Live API over WebSockets. Install the separate google-gemini/gemini-live-api-dev skill, which covers voice activity detection, session management, and ephemeral tokens.

Related Skills

Explore More Software Engineering Skills→
chetanreddyvchetanreddyv

onboarding

Guide users through AI assistant API setup and configuration.

Community
Basic
Probably-GroupProbably-Group
3

cloud-api-integration

Integrate cloud LLM APIs with prompt injection prevention and secret protection.

Official
Advanced
arakitakashiarakitakashi
1

google-adk-live

Enable bidirectional voice and video interactions via the Gemini Live API and ADK.

Community
Advanced
ax-llmax-llm
2.9k

ax-java-ai

Generate Java provider clients and normalized model connection code for Ax AI integrations.

Official
Intermediate