ocr-and-documents

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

1|Updated Apr 13, 2026
One-click install
npx skills add https://github.com/tangzheng202202/hermes-skills --skill ocr-and-documents-tangzheng202202
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/tangzheng202202/hermes-skills/tree/main/06-productivity/productivity/ocr-and-documents
Command: npx skills add https://github.com/tangzheng202202/hermes-skills --skill ocr-and-documents-tangzheng202202

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Extract text from PDFs and scanned documents to convert non-searchable content into editable, searchable text.

Core Features & Use Cases

  • OCR-based extraction: OCR on scanned PDFs and images to recover text.
  • Text extraction for documents: Use pymupdf for text-based PDFs; marker-pdf for OCR/advanced parsing; DOCX for Word, PPTX for PowerPoint notes (references to powerpoint skill).
  • Use Case: Researchers processing large archives of PDFs and scanned documents can convert content into searchable formats for quick analysis.

Quick Start

Ask me to extract text from a local PDF or scanned document to begin the process.

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 and images?

To extract text from scanned PDFs, this Skill uses marker-pdf for OCR-based extraction, converting non-searchable content into editable, searchable text. It handles layout-aware results for research and archival workflows.

What's the best way to convert non-searchable PDFs into editable text?

The best way to convert non-searchable PDFs into editable text is using pymupdf for text-based PDFs or marker-pdf for OCR-heavy documents, ensuring layout-aware results for reliable data collection.

Does this tool support remote URL extraction for PDF documents?

Yes, remote URL extraction for PDF documents is supported via the web_extract function, allowing you to pull and process non-searchable content directly from online sources into editable text.

Can I use this to process large archives of PDFs for research?

Yes, you can use this to process large archives of PDFs for research. It converts content into searchable formats for quick analysis, making it ideal for archival and data-collection workflows.

Do I need pymupdf and marker-pdf to extract text from local PDFs?

Yes, you need the pymupdf and marker-pdf Python libraries to extract text from local PDFs. PyMuPDF handles text-based PDFs while marker-pdf manages OCR-heavy and scanned document extraction.

Why use marker-pdf instead of pymupdf for text extraction?

Use marker-pdf instead of pymupdf when dealing with OCR-heavy or scanned documents that lack embedded text. PyMuPDF is suitable for text-based PDFs, while marker-pdf recovers text from images using layout-aware parsing.