skills.rest
jleechanorg
jleechanorgOFFICIAL
Explore all skills by this author →
GitHub

ocr-and-documents

Extract text, Markdown, tables, and images from PDFs and scans.

Updated Jun 28, 2026
Search Tags:#ocr#pdf#markdown#pymupdf#text-extraction#document-extraction#marker-pdf
One-click install
npx skills add https://github.com/jleechanorg/hermes-agent --skill ocr-and-documents-jleechanorg
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/jleechanorg/hermes-agent/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/jleechanorg/hermes-agent --skill ocr-and-documents-jleechanorg

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Extract text from PDFs, scanned documents, and other file formats using lightweight tools (pymupdf) or high-quality OCR (marker-pdf), enabling quick digitization and searchability.

Core Features & Use Cases

  • Text extraction: Convert text from native PDFs and scanned documents into plain text.
  • OCR for non-searchable docs: Use marker-pdf to perform OCR on images and multi-language documents with layout awareness.
  • Real-world workflow: Convert a batch of academic PDFs to Markdown for literature reviews or extract data tables for analysis.

Quick Start

Use the pymupdf extractor to convert document.pdf to plain text.

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 for analysis?▼

To extract text from a scanned PDF, you can use OCR-enabled tools like marker-pdf to recognize text and layout. This process digitizes non-searchable documents into plain text or Markdown for downstream analysis.

Can I convert native PDFs directly to Markdown format?▼

Yes, you can convert native PDFs to Markdown format using pymupdf4llm. This preserves document structure and tables, outputting searchable Markdown text suitable for literature reviews or data analysis.

Does this OCR text extraction approach work with both local files and URLs?▼

Yes, this OCR text extraction approach supports both local files and URLs. It handles text-based PDFs and OCR-enabled scans, allowing you to process documents from various sources for digitization.

What is the best way to extract tables and images from PDF documents?▼

The best way to extract tables and images from PDFs is using pymupdf and marker-pdf. These libraries provide scripts to export document elements, capturing structural data alongside plain text and Markdown output.

Do I need Python packages like pymupdf and marker to perform document extraction?▼

Yes, you need Python packages like pymupdf, pymupdf4llm, and marker to perform document extraction. These dependencies enable lightweight text extraction and high-quality, layout-aware OCR for non-searchable documents.

When should I use marker-pdf instead of pymupdf for text extraction?▼

You should use marker-pdf instead of pymupdf when handling scanned documents or images requiring OCR. Marker-pdf offers layout-aware, multi-language recognition, whereas pymupdf quickly extracts text from native, text-based PDFs.

Related Skills

Explore More Data & Analytics Skills→
attentiondotnetattentiondotnet

ocr-and-documents

Extract text from PDFs, DOCX, PPTX, and scanned documents via OCR.

Community
Intermediate
PancrePal-xiaoyibaoPancrePal-xiaoyibao
6

pdf-reader

Extract text from local PDF files into structured Markdown format.

Official
Intermediate
smilebank7smilebank7
2

Extract Materials

Extract text, tables, and equations from PDFs, PPTX, DOCX, and images into Markdown.

Community
Intermediate
paxlabs-incpaxlabs-inc
7

ocr-and-documents

Extract text, tables, and images from PDFs and scanned documents.

Community
Intermediate