gemini-pdf-analyzer

Extract text, tables, and insights from PDFs and images via Gemini.

Updated Dec 2, 2025
One-click install
npx skills add https://github.com/matixlol/monitoreo-panama --skill gemini-pdf-analyzer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-pdf-analyzer
Source: https://github.com/matixlol/monitoreo-panama/tree/main/.agents/skills/gemini-pdf-analyzer
Command: npx skills add https://github.com/matixlol/monitoreo-panama --skill gemini-pdf-analyzer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill enables rapid analysis of PDFs and images using Gemini via OpenRouter to extract actionable insights, reducing manual review time and enabling scalable document understanding.

Core Features & Use Cases

  • Extract text and tables from PDFs to structured data.
  • Analyze diagrams and images to summarize visuals.
  • Answer questions about document content and compare multiple documents for consistency.
  • Handle large PDFs by streaming or sending pages to Gemini's vision capabilities.

Quick Start

Use the Gemini PDF Analyzer to process a prompt and one or more files: bun run .agents/skills/gemini-pdf-analyzer/scripts/analyze.ts "What are the main findings in this report?" report.pdf

Frequently Asked Questions about gemini-pdf-analyzer

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

FAQPage Schema
How do I extract text and tables from a PDF using Gemini?

You can extract text and tables from a PDF using Gemini by running the analyze.ts script with your document and a prompt. It processes single or multiple files to output structured data.

Can I analyze multiple PDFs and compare their content with Gemini?

Yes, you can analyze multiple PDFs with Gemini to compare document content for consistency. The analyzer script accepts multiple files, enabling cross-document review and research workflows.

Do I need an OpenRouter API key to analyze PDFs and images?

Yes, you need an OPENROUTER_API_KEY to analyze PDFs and images. The Skill operates by routing requests through OpenRouter to access Gemini's vision capabilities for document and image analysis.

What is the best way to handle large PDFs for data extraction?

The best way to handle large PDFs for data extraction is by streaming or sending pages directly to Gemini's vision capabilities. This approach allows the analyzer to process extensive documents effectively.

Can Gemini analyze images and diagrams inside PDF documents?

Yes, Gemini can analyze images and diagrams inside PDF documents. The Skill uses Gemini's vision capabilities to summarize visuals and extract insights from images during document review.