ocr-and-documents

Extract text, tables, and equations from PDFs and scanned documents using OCR.

Updated Jun 4, 2026

Search Tags:#ocr #text extraction #document automation #pdf processing #document extraction

Ready to run

npx skills add https://github.com/kngender5/hermes --skill ocr-and-documents-kngender5

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/kngender5/hermes/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/kngender5/hermes --skill ocr-and-documents-kngender5

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pymupdf, marker-pdf, python-docx, python-pptx, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill simplifies the process of extracting text from PDFs, scanned documents, and images, making it easier to convert documents into usable data.

Core Features & Use Cases

PDF and Scan Extraction: Extract text from PDFs and scanned documents with high accuracy.
Text-based PDFs: Use pdftotext for fast text extraction from text-based PDFs.
Scanned PDFs: Utilize marker-pdf for OCR on scanned PDFs, supporting 90+ languages.
Table Extraction: Extract tables from PDFs for better data organization.
Equation Extraction: Support for extracting equations and LaTeX from PDFs.
Use Case: If you have a stack of scanned invoices and need to extract the text for processing, this skill can do it efficiently.

Quick Start

Use the ocr-and-documents skill to extract text from a scanned invoice 'invoice.pdf'.

Frequently Asked Questions about ocr-and-documents

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

FAQPage Schema

How do I extract text from scanned PDFs using OCR?▼

To extract text from scanned PDFs, this Skill applies OCR via marker-pdf, supporting 90+ languages for high accuracy. It handles scanned documents and images, converting them into usable text data efficiently for administrative tasks like invoice processing.

What is the best way to extract tables and equations from PDFs?▼

The best way to extract tables and equations from PDFs is using this Skill's document parsing tools. It supports table extraction for better data organization and can extract equations and LaTeX directly from your PDF files.

Does this PDF text extraction tool support text-based PDFs as well as scans?▼

Yes, this PDF text extraction tool supports both text-based PDFs and scanned documents. It uses pymupdf for fast text extraction from text-based PDFs, while utilizing marker-pdf for OCR on scanned documents.

Do I need Python libraries for document extraction and processing?▼

Yes, you need Python libraries for document extraction and processing. This Skill requires pymupdf, marker-pdf, python-docx, and python-pptx to perform OCR, parse documents, and extract text from PDFs and scans.

Can I use this for invoice processing and form digitization?▼

Yes, you can use this Skill for invoice processing and form digitization. It is specifically suited for administrative tasks, efficiently extracting text from stacks of scanned invoices and converting forms into usable data.