ocr-and-documents

Extract text from PDFs and scanned documents into Markdown or plain text.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/shiftrepo/aws --skill ocr-and-documents-shiftrepo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/shiftrepo/aws/tree/main/HermesAgent/skills/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/shiftrepo/aws --skill ocr-and-documents-shiftrepo

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

PDFs and scanned documents often exist as images or binary data. This skill extracts text to make documents searchable, editable, and easy to analyze.

Core Features & Use Cases

  • Remote URL extraction via web_extract for online PDFs.
  • Local text-based PDF extraction using pymupdf for fast results.
  • OCR-based extraction via marker-pdf for scanned papers, preserving layout, tables, and multi-language support.
  • DOCX and PPTX notes are supported through recommended complementary skills.
  • Real-world use case: convert a batch of archival PDFs into searchable Markdown or plain text for literature reviews.

Quick Start

Process a local PDF or scanned document by selecting the lightweight pymupdf path for text extraction or the marker-pdf OCR path to convert images to editable 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 a literature review?▼

To extract text from a scanned PDF, use the marker-pdf OCR path to convert document images into searchable Markdown or plain text while preserving layout and tables. This method supports multi-language extraction for archival research workflows.

What is the best way to extract text from a local text-based PDF?▼

The best way to extract text from a local text-based PDF is using the lightweight pymupdf path, which delivers fast results. It processes local files directly to output searchable Markdown or plain text without requiring OCR.

Can I extract text from online PDFs using a remote URL?▼

Yes, you can extract text from online PDFs by providing a remote URL. The skill processes online files via the web_extract functionality, converting remote documents into searchable and editable content for analysis.

Does marker-pdf preserve tables and layout during OCR extraction?▼

Yes, marker-pdf preserves document layout and tables during OCR extraction. It processes scanned documents to maintain structural formatting, converting them into searchable Markdown or plain text suitable for admin and knowledge-work workflows.

Do I need pymupdf and marker-pdf to extract text from documents?▼

Yes, the skill requires and validates the use of pymupdf and marker-pdf libraries for text extraction. Pymupdf handles text-based PDFs while marker-pdf provides OCR capabilities for scanned documents.

What formats can I convert PDFs into besides DOCX and PPTX?▼

You can convert PDFs into searchable Markdown or plain text formats. While DOCX and PPTX handling is supported through recommended complementary skills, the core extraction outputs Markdown or plain text for editable content.

Related Skills