gemini-document-processing

Extract structured JSON data from PDFs using Google Gemini vision capabilities.

2.2k|422|Updated Oct 23, 2025
One-click install
npx skills add https://github.com/mrgoonie/claudekit-skills --skill gemini-document-processing
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-document-processing
Source: https://github.com/mrgoonie/claudekit-skills/tree/main/.claude/skills/gemini-document-processing
Command: npx skills add https://github.com/mrgoonie/claudekit-skills --skill gemini-document-processing

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, python-dotenv, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Extracting structured data, summarizing, or answering questions from complex PDF documents (especially those with images, charts, or tables) is often a manual and error-prone process. This skill leverages Google Gemini's native vision capabilities to automate deep document understanding, saving significant time and improving accuracy.

Core Features & Use Cases

  • Multimodal PDF Analysis: Understands text, images, diagrams, charts, and tables within PDFs up to 1,000 pages.
  • Structured Data Extraction: Extract specific information (e.g., invoice details, resume fields) into JSON format with schema validation.
  • Intelligent Summarization & Q&A: Generate concise summaries or get direct answers to questions based on document content.
  • Use Case: Automatically process a batch of legal contracts to extract key clauses, effective dates, and party names, then summarize each contract's obligations, all without manual review.

Quick Start

1. Get your Gemini API key: https://aistudio.google.com/apikey

2. Set API key as environment variable:

export GEMINI_API_KEY="your-api-key-here"

3. Install dependencies:

pip install google-genai python-dotenv

4. Use the provided script to summarize a PDF:

python .claude/skills/gemini-document-processing/scripts/process-document.py
--file your_document.pdf
--prompt "Provide a concise executive summary"