ocr-and-documents

Extract text from PDFs and scanned documents into Markdown.

97|8|Updated Mar 20, 2026
One-click install
npx skills add https://github.com/peteromallet/megaplan --skill ocr-and-documents-peteromallet
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/peteromallet/megaplan/tree/main/megaplan/agent/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/peteromallet/megaplan --skill ocr-and-documents-peteromallet

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Extracts text from PDFs and scanned documents to enable search, indexing, and content reuse across research, data collection, and document-management workflows.

Core Features & Use Cases

  • Remote extraction for URLs using web_extract to fetch PDFs and convert to text or Markdown.
  • Local extraction using pymupdf for text-based PDFs; marker-pdf for OCR-heavy or complex layouts, including markdown output.
  • DOCX/PPTX support via python-docx and python-pptx to broaden document compatibility.

Quick Start

Use this skill to extract text from a document by specifying the path or URL and choosing a local or OCR-based extractor.

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 search and indexing?

To extract text from a scanned PDF for search and indexing, the Skill uses marker-pdf for OCR-heavy or complex layouts, converting the document content into editable text or Markdown format.

Can I extract text from remote PDF URLs without downloading files locally?

Yes, you can extract text from remote PDF URLs without downloading files locally by using the web_extract feature, which fetches documents directly and converts them to text or Markdown output.

What is the best way to convert text-based PDFs to Markdown?

The best way to convert text-based PDFs to Markdown is using pymupdf, which handles text extraction from local files efficiently, while marker-pdf is reserved for OCR-heavy or complex document layouts.

Does this PDF text extraction method support DOCX and PPTX files?

Yes, this PDF text extraction method supports DOCX and PPTX files by utilizing python-docx and python-pptx, broadening document compatibility for text extraction and content reuse workflows.

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

You should use marker-pdf instead of pymupdf for document text extraction when dealing with OCR-heavy, scanned documents, or complex layouts, as pymupdf is optimized for text-based PDFs.

Do I need Python to extract text from PDFs and convert them to Markdown?

Yes, you need Python to extract text from PDFs and convert them to Markdown, as the Skill requires Python tools pymupdf and marker-pdf for extraction and OCR processing.