ocr-and-documents

Extract text, markdown, and metadata from PDFs and scanned documents.

Updated Jun 25, 2026
One-click install
npx skills add https://github.com/davpatel605-beep/hermusagent --skill ocr-and-documents-davpatel605-beep
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/davpatel605-beep/hermusagent/tree/main/backend/vendor/hermes/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/davpatel605-beep/hermusagent --skill ocr-and-documents-davpatel605-beep

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill solves the challenge of extracting usable text and structured information from PDFs, scanned documents, and complex files that are difficult to search or process manually.

Core Features & Use Cases

  • PDF Text Extraction: Extract text, markdown, metadata, tables, and images from text-based PDF documents using lightweight parsing tools.
  • OCR and Layout Analysis: Process scanned PDFs and complex documents with high-quality OCR, equation handling, and layout-aware conversion.
  • Use Case: Researchers can convert academic papers, scanned archives, and reports into searchable markdown for analysis and knowledge workflows.

Quick Start

Use the ocr-and-documents skill to extract all readable text from the attached PDF file and return it in a structured format.

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 for research analysis?

To extract text from scanned PDF documents, this Skill applies OCR processing and layout-aware conversion to generate searchable markdown. It handles complex layouts and equations, converting scanned archives into structured text for research workflows.

Can I convert a text-based PDF to markdown while preserving tables and metadata?

Yes, you can convert text-based PDFs to markdown while preserving tables and metadata. This Skill uses lightweight parsing tools like pymupdf to extract text, images, and structured information into a searchable markdown format.

Does pymupdf4llm work with complex document layouts for markdown conversion?

Yes, pymupdf4llm works with complex document layouts for markdown conversion. This Skill leverages it alongside pymupdf and marker-pdf to handle high-quality OCR, equation parsing, and layout-aware text extraction from difficult documents.

What is the best way to parse academic papers into searchable text?

The best way to parse academic papers into searchable text is using OCR and layout analysis tools. This Skill converts reports and academic papers into structured markdown, supporting metadata retrieval and complex layout handling for knowledge workflows.

Why does text extraction fail on scanned documents without OCR?

Text extraction fails on scanned documents without OCR because they contain images rather than embedded text layers. This Skill applies layout-aware OCR processing to interpret these images, extracting usable text and structured information from archival files.