pdf-extractor

Extract text, tables, images, and form fields from PDF documents.

Updated Feb 18, 2026
One-click install
npx skills add https://github.com/Greenmamba29/skillsdotmd_web --skill pdf-extractor-greenmamba29
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf-extractor
Source: https://github.com/Greenmamba29/skillsdotmd_web/tree/main/.agents/skills/pdf-extractor
Command: npx skills add https://github.com/Greenmamba29/skillsdotmd_web --skill pdf-extractor-greenmamba29

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires tesseract, google-cloud-vision, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the extraction of structured information, text, tables, images, and form data from PDF documents, including scanned ones requiring OCR.

Core Features & Use Cases

  • Content Extraction: Extracts text, tables, images, and form field data.
  • OCR Support: Processes scanned PDFs using OCR engines like Tesseract or Google Vision API.
  • Batch Processing: Handles large sets of documents efficiently.
  • Use Case: Extracting invoice data from a batch of supplier PDFs for accounting.

Quick Start

Use the pdf-extractor skill to extract tables from the file './invoices/lithium_supplier_inv_2026.pdf' and save the output as a CSV file.

Frequently Asked Questions about pdf-extractor

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

FAQPage Schema
How do I extract tables and text from scanned PDF documents?

You can extract structured text, tables, and form fields from scanned PDFs using OCR engines like Tesseract or Google Cloud Vision, handling multi-column layouts and outputting data in JSON, CSV, or Markdown formats.

Can I batch process a large set of PDF files to extract invoice data?

Yes, you can batch process large document sets to extract structured invoice data efficiently, handling multi-column layouts and saving the extracted information into your specified JSON, CSV, or Markdown output formats.

Does the pdf-extractor Skill support multi-column layouts and form fields?

Yes, pdf-extractor supports extracting structured data from multi-column layouts and form fields, delivering the extracted text, tables, and images in specified formats like JSON, CSV, or Markdown for downstream processing.

Do I need Tesseract or Google Cloud Vision to extract data from PDFs?

You need Tesseract or Google Cloud Vision dependencies specifically for processing scanned PDF documents via OCR; standard digital PDF text, table, and image extraction can proceed without these OCR engines.

What is the best way to convert PDF documents into structured JSON or CSV files?

The best way to convert PDFs into structured JSON or CSV is to use an extraction tool that parses multi-column layouts and form fields, applying OCR for scanned files to ensure accurate data output.

What are the limitations when processing large sets of PDF documents for data extraction?

When processing large PDF document sets, limitations depend on your chosen OCR engine, as Tesseract or Google Cloud Vision are required for scanned files, and batch processing efficiency varies with multi-column layout complexity.