ocr-and-documents

Extract text from PDFs and scanned documents using pymupdf and marker-pdf.

Updated Apr 24, 2026
One-click install
npx skills add https://github.com/Harries/hermes-agent --skill ocr-and-documents-harries
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/Harries/hermes-agent/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/Harries/hermes-agent --skill ocr-and-documents-harries

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Extracts text from PDFs and scanned documents to enable quick reuse, indexing, and analysis without manual transcription.

Core Features & Use Cases

  • Remote extraction from URLs using web_extract to convert PDFs to markdown.
  • Local extraction using pymupdf for text-based PDFs and marker-pdf for OCR-enabled documents.
  • DOCX/PPTX support through dedicated tools (python-docx for DOCX; see powerpoint skill for PPTX) and broader batch processing.
  • Outputs in Markdown with optional images/tables extraction and cross-file search readiness.

Quick Start

Provide a PDF or document path and I will extract text using pymupdf for text PDFs or marker-pdf for OCR-ready scans.

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 PDF documents?

To extract text from scanned PDFs, this solution uses marker-pdf for OCR-enabled documents, converting the scanned content into markdown format for quick reuse. It handles scanned documents by applying local extractors to transform images into text.

Can I use pymupdf for text extraction from text-based PDFs?

Yes, you can use pymupdf for text extraction from text-based PDFs. It serves as the local extractor for standard PDFs, while marker-pdf handles OCR for scanned documents, ensuring accurate text extraction across different document types.

What is the best way to batch process large document collections for text extraction?

The best way to batch process large document collections is using this automated text extraction workflow, which outputs markdown with optional images and tables extraction, making the results ready for indexing and cross-file search.

Does this OCR and document processing approach support remote URLs?

Yes, this OCR and document processing approach supports remote URLs by using web_extract as the preferred option to convert remote PDFs to markdown, allowing direct extraction from web links without local downloads.

How do I convert PDFs to markdown for archival digitization?

You can convert PDFs to markdown for archival digitization by applying pymupdf for text-based files and marker-pdf for scanned documents, outputting markdown with optional images and tables extraction for fast content indexing.

When should I not use pymupdf for document text extraction?

You should not use pymupdf alone for document text extraction when dealing with scanned documents or images, as it handles text-based PDFs; instead, marker-pdf is required for OCR-enabled documents to ensure accurate text capture.