ocr-and-documents

Extract text and data from PDFs and scanned documents using Python OCR tools.

Updated Jun 19, 2026
One-click install
npx skills add https://github.com/AnandaAnugrahHandyanto/savarez_agent --skill ocr-and-documents-anandaanugrahhandyanto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/AnandaAnugrahHandyanto/savarez_agent/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/AnandaAnugrahHandyanto/savarez_agent --skill ocr-and-documents-anandaanugrahhandyanto

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Extract text and data from PDFs and scanned documents is time-consuming when done manually. This Skill combines lightweight text extraction with OCR-powered parsing to convert content into searchable, editable outputs.

Core Features & Use Cases

  • Text extraction from standard PDFs and images using pymupdf for fast, dependency-free workflows.
  • OCR-enabled extraction for scanned documents via marker-pdf to recover text, tables, code blocks, and layout.
  • Output formats include Markdown and structured data; useful for archiving, research, and content processing.
  • Use Case: A researcher downloads dozens of research PDFs and needs to pull out abstracts, tables, and figures for meta-analysis.

Quick Start

Run the provided scripts on a PDF to extract plain text with pymupdf or Markdown with pymupdf4llm.

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 and tables from scanned PDFs for research analysis?

To extract text and tables from scanned PDFs, apply OCR-enabled parsing via marker-pdf to recover content, code blocks, and layout, outputting structured Markdown or JSON for research meta-analysis. This handles archival materials where standard text extraction fails.

What is the best way to convert standard PDFs to Markdown without losing layout?

Converting standard PDFs to Markdown is best handled by pymupdf4llm, which extracts text while preserving document layout. This yields dependency-free, fast output suitable for archiving and content processing workflows.

Does marker-pdf support extracting figures and images alongside text extraction?

Yes, marker-pdf supports extracting figures and images alongside text extraction. It recovers tables, code blocks, and layout from scanned documents, providing optional image and table extraction for comprehensive document parsing.

Can I use pymupdf for fast text extraction from large batches of research papers?

Yes, you can use pymupdf for fast text extraction from large batches of research papers. It provides lightweight, dependency-free parsing to quickly pull abstracts and text from standard PDFs without OCR overhead.

When should I not use standard PDF text extraction and switch to OCR instead?

You should switch to OCR when processing scanned documents or images where standard text extraction fails. If your PDFs are image-based archival materials without embedded text layers, marker-pdf is required to recover the content.