ocr-document-processor

Extract text and structured data from images and scanned PDFs using Tesseract OCR.

3|Updated Apr 2, 2026

Search Tags:#ocr #document processing #pdf #text extraction #computer vision #receipt parsing

Ready to run

npx skills add https://github.com/legout/pi-config --skill ocr-document-processor-legout

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ocr-document-processor
Source: https://github.com/legout/pi-config/tree/main/installed-skills/ocr-document-processor
Command: npx skills add https://github.com/legout/pi-config --skill ocr-document-processor-legout

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires Pillow, PyMuPDF, numpy, opencv-python, pandas, pytesseract, and includes scripts (resource) components.

What problem does it solve?

This skill solves the challenge of digitizing physical or image-based documents, converting unreadable scans into structured, searchable, and editable digital formats.

Core Features & Use Cases

Advanced OCR: High-accuracy text recovery from images, scanned PDFs, and photos.
Structured Extraction: Automatically parse business cards and receipts into clean JSON data.
Batch Processing: Process entire directories of documents at once to generate searchable PDFs or markdown files.

Quick Start

Use the ocr-document-processor skill to extract text from the image file named scan.png and save the output as a markdown file.

Frequently Asked Questions about ocr-document-processor

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

FAQPage Schema

How do I extract text from scanned PDF documents and images?▼

You can extract text from scanned PDFs and images using this skill, which applies Tesseract OCR and computer vision techniques to convert scans into searchable markdown or JSON data.

Can I parse receipts and business cards into structured data?▼

Yes, you can parse receipts and business cards into structured data, as the skill automatically extracts text and formats it into clean JSON data for automated data entry and archival.

Do I need to install Tesseract and OpenCV to process multi-page reports?▼

Yes, you need Tesseract, OpenCV, and PyMuPDF installed to process multi-page reports, because these dependencies perform the necessary image preprocessing and text recognition tasks.

What's the best way to batch process a directory of scanned documents?▼

The best way to batch process a directory of scanned documents is using this skill, which processes entire directories at once to automatically generate searchable PDFs or markdown files.

Why does OCR text extraction fail on low quality images?▼

OCR text extraction can fail on low quality images due to poor scan resolution or noise, but this skill uses OpenCV and Pillow for image preprocessing to improve recognition accuracy before applying Tesseract.