skills.rest
antonyfmunoz
antonyfmunozCOMMUNITY
Explore all skills by this author →
GitHub

google_gemini

Call Google Gemini to generate text and structured outputs via the google.genai Python SDK.

1|Updated Mar 11, 2026
Search Tags:#embeddings#llm#structured output#function calling#google genai#multimodal analysis
One-click install
npx skills add https://github.com/antonyfmunoz/OS --skill google-gemini-antonyfmunoz
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: google_gemini
Source: https://github.com/antonyfmunoz/OS/tree/main/skills/tools/google_gemini
Command: npx skills add https://github.com/antonyfmunoz/OS --skill google-gemini-antonyfmunoz

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps the EOS runtime reliably generate high-quality text, analyze multimodal inputs, and produce embeddings or structured outputs using Google Gemini when you need a production-ready LLM provider.

Core Features & Use Cases

  • Multimodal text generation: Use Gemini to generate answers from text plus images/audio/video/PDFs for tasks like screenshot analysis and document understanding.
  • Embeddings for semantic search: Create semantic vectors (e.g., gemini-embedding-001) to power retrieval, classification, and memory lookups.
  • Function calling and structured outputs: Use JSON/enum-style outputs and tool-ready function calling patterns to integrate Gemini with EOS modules that require strict schemas.

Quick Start

Use google_gemini to analyze the attached image and generate a structured business assessment for the current EOS stage.

Frequently Asked Questions about google_gemini

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

FAQPage Schema
How do I generate structured outputs from a multimodal image and text prompt?▼

You can generate structured outputs from multimodal inputs by passing images, audio, video, or PDFs alongside text prompts to Google Gemini, which returns JSON or enum-style responses adhering to strict schemas for direct system integration.

What is the best way to create embeddings for semantic search using Google Gemini?▼

Creating embeddings for semantic search involves sending text to the Gemini embedding model, which generates semantic vectors to power retrieval, classification, and memory lookups within your application.

Does Google Gemini support function calling with JSON schemas?▼

Google Gemini supports function calling by using JSON schemas to define tool-ready patterns, allowing the LLM to output structured data that integrates directly with external modules requiring strict formats.

Can I use Google Gemini for document understanding and PDF analysis?▼

Google Gemini handles document understanding by accepting PDFs and images as multimodal inputs, analyzing the visual and textual content to generate accurate text answers and structured business assessments.

What do I need to authenticate Google Gemini API requests in Python?▼

Authenticating Google Gemini API requests requires setting the GEMINI_API_KEY environment variable and using the google.genai Python SDK to access models like gemini-2.5-flash and gemini-embedding-001.

Why use Google Gemini over other LLM providers for multimodal analysis?▼

Google Gemini provides a production-ready LLM provider that natively processes text, images, audio, and video within a single call, streamlining multimodal document analysis and structured output generation without chaining multiple models.

Related Skills

Explore More Software Engineering Skills→
BoraPerusicBoraPerusic

gemini-api-integration

Integrate Google Gemini API for multimodal inputs, streaming, and function calling.

Community
Advanced
danilonovaisvdanilonovaisv
1

AgentDB Vector Search

Enable fast semantic search over document collections using AgentDB.

Community
Advanced
ArieGoldkinArieGoldkin
10

ai-native-development

Integrate LLMs, RAG pipelines, vector databases, and agentic workflows.

Community
Advanced
involvexinvolvex

gemini-api-dev

Develop applications using Google's Gemini API for text, multimodal, and structured outputs.

Community
Advanced