ocr-and-documents

Extract text from PDFs and scanned documents via OCR and parsing tools.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Extracts text from PDFs, scanned documents, and other file formats by combining OCR and document-parsing tools to turn non-editable content into searchable, editable text.

Core Features & Use Cases

  • OCR-based extraction for scanned documents to produce editable text and searchable content.
  • PDF and document parsing using pymupdf and related tools to deliver clean text or Markdown outputs.
  • Use case: convert a scanned research paper into digital notes and extract figures and tables for analysis.

Quick Start

Provide a document path or URL and extract text using the appropriate 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 using OCR?

To extract text from a scanned PDF, the Skill applies OCR using marker-pdf to recognize text and complex layouts. This process turns non-editable scanned documents into clean, searchable digital text for research and analysis.

What is the best way to convert a research paper PDF into Markdown?

The best way to convert a research paper PDF into Markdown is using pymupdf and pymupdf4llm. These dependencies parse text-based PDFs and complex layouts to output clean, editable Markdown text for digital notes.

Can I extract text from a document URL or do I need a local file?

You can extract text from a document URL without needing a local file. The Skill uses the web_extract tool to fetch and process remote URLs, while pymupdf and marker-pdf handle local text-based PDFs and scanned documents respectively.

Does this PDF text extraction tool work with DOCX and PPTX files?

Yes, the PDF text extraction tool includes optional DOCX and PPTX support via respective parsing tools. It extracts editable text and structured data from these mixed-source file formats alongside standard PDFs and scans.

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

Use pymupdf for local text-based PDFs where text is already digital and selectable. Use marker-pdf when you need OCR for scanned documents or when parsing complex layouts that require advanced structure and figure recognition.