ocr-and-documents

Extract text and data from PDFs and scanned documents.

Updated May 21, 2026
One-click install
npx skills add https://github.com/samlaggz/hermes-agent-sam --skill ocr-and-documents-samlaggz
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/samlaggz/hermes-agent-sam/tree/main/backup/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/samlaggz/hermes-agent-sam --skill ocr-and-documents-samlaggz

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires marker, marker-pdf, pymupdf, pymupdf4llm, and includes scripts (resource) components.

What problem does it solve?

Extract text from PDFs, scanned documents, and other file formats to streamline data capture and digitization.

Core Features & Use Cases

  • Lightweight extraction with pymupdf for quick text capture from PDFs.
  • OCR-enabled parsing with marker-pdf for scanned documents and complex layouts.
  • Optional outputs (Markdown/text), page-range selection, and image extraction.

Quick Start

Run a basic extraction on document.pdf using the pymupdf workflow.

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 a scanned PDF using OCR?

You can extract text from scanned PDFs using the marker-pdf workflow, which applies OCR to convert document content into searchable, editable markdown or text formats.

What is the best way to convert a PDF to markdown?

The best way to convert a PDF to markdown is using this Skill, which leverages pymupdf for fast text capture and marker-pdf to output markdown while handling complex document layouts and image extraction.

Can I extract text from specific pages of a PDF?

Yes, you can extract text from specific pages of a PDF using the page-range selection feature, allowing you to filter and capture text or data only from the exact pages you need.

Does this PDF extraction method work with complex layouts?

Yes, this PDF extraction method works with complex layouts by using marker-pdf, which applies OCR specifically designed to parse scanned documents and intricate page structures into markdown output.

Do I need pymupdf or marker-pdf for text extraction?

You need both: pymupdf handles lightweight, fast text capture from native PDFs, while marker-pdf is required for OCR on scanned documents and complex layouts to generate markdown output.

Can I extract images from a PDF along with the text?

Yes, you can extract images from a PDF along with the text, as the Skill includes an image extraction option to capture visual content alongside the parsed markdown or text data.