skills.rest
diskd-ai
diskd-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

gemini-api

Integrate Google Gemini API across Python and TypeScript SDKs.

6|1|Updated Jan 23, 2026
Search Tags:#documentation#embeddings#multimodal#function-calling#gemini-api#genai#google-genai
One-click install
npx skills add https://github.com/diskd-ai/gemini-api --skill gemini-api
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-api
Source: https://github.com/diskd-ai/gemini-api/tree/main
Command: npx skills add https://github.com/diskd-ai/gemini-api --skill gemini-api

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill consolidates patterns, examples, and references for building AI-powered applications with Google's Gemini API, enabling rapid adoption across models, multimodal inputs, embeddings, and tooling.

Core Features & Use Cases

  • Broad model coverage: Work with Gemini 3 Pro, Gemini 3 Flash, Gemini 2.5 Pro/Flash, Nano Banana, Veo, and Lyria for text, image, video, and audio generation.
  • Multimodal workflows: Process text, images, PDFs, and other media with structured outputs, function calling, and embedded JSON schemas.
  • Developer ergonomics: Includes Python and TypeScript SDK patterns, streaming responses, and built-in tooling integration.
  • Document processing & embeddings: Leverage document processing (PDFs) and embeddings for retrieval and RAG tasks.

Quick Start

Install the skill into your workspace and start exploring Gemini API capabilities. For example: install with npx skills add diskd-ai/gemini-api, then reference the SKILL.md and the references folder for model guides (gemini-3.md, image-generation.md, veo.md, lyria.md, etc.) to implement end-to-end tasks.

Frequently Asked Questions about gemini-api

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

FAQPage Schema
How do I integrate Google's Gemini API for multimodal inputs in my app?▼

You can integrate the Gemini API using provided Python and TypeScript SDK patterns to process multimodal inputs like text, images, and PDFs. The skill offers centralized references for structured outputs and streaming responses to handle diverse media types effectively.

Can I use the Gemini API for function calling with structured JSON outputs?▼

Yes, the Gemini API supports function calling with embedded JSON schemas for structured outputs. The skill provides specific implementation patterns to define and enforce these schemas within your generation workflows.

What's the best way to generate text and media using Google GenAI models?▼

The best way to generate text and media with Google GenAI models is by leveraging the skill's broad model coverage, including Gemini 3 Pro, Veo for video, and Lyria for audio. It provides dedicated guides for each model's specific generation workflow.

Does this Gemini API integration skill support Python and TypeScript SDKs?▼

Yes, this Gemini API integration skill fully supports both Python and TypeScript SDKs. It includes developer ergonomic patterns and examples for streaming responses and complex workflows across both development environments.

How do I create embeddings for document processing with the Gemini API?▼

To create embeddings for document processing with the Gemini API, the skill provides patterns for leveraging PDF processing and embeddings. This enables retrieval and RAG tasks directly within your AI-powered applications.

Related Skills

Explore More Software Engineering Skills→
JetBrainsJetBrains
302

gemini-interactions-api

Orchestrate Gemini model interactions, state, and tools via a single API.

Official
Advanced
rubbypinkrubbypink

firebase-ai-logic

Integrate Firebase AI Logic with Gemini API for multimodal generation and structured JSON output.

Community
Advanced
jackjin1997jackjin1997
11

LangChain RAG Pipeline

Build end-to-end RAG pipelines with document loading, chunking, and vector storage.

Community
Intermediate
lengo0951lengo0951

ai-multimodal

Process images, audio, and video with the Gemini API.

Community
Advanced