skills.rest
KarlinskyS
KarlinskySCOMMUNITY
Explore all skills by this author →
GitHub

ocr-and-documents

Extract text from PDFs, scanned documents, images, and related files.

Updated Apr 10, 2026
Search Tags:#ocr#pdf#pymupdf#document#text-extraction#marker-pdf#web-extract
One-click install
npx skills add https://github.com/KarlinskyS/hermesSkills --skill ocr-and-documents-karlinskys
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/KarlinskyS/hermesSkills/tree/main/productivity/ocr-and-documents
Command: npx skills add https://github.com/KarlinskyS/hermesSkills --skill ocr-and-documents-karlinskys

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Users need to extract readable text from PDFs, scanned documents, images, and related file formats without manual copying or error‑prone OCR setups.

Core Features & Use Cases

  • Remote extraction: Uses web_extract to pull text from online PDFs and arXiv links instantly.
  • Local lightweight extraction: Employs pymupdf for fast text‑based PDFs and basic tables.
  • High‑quality OCR & layout analysis: Leverages marker-pdf for scanned PDFs, equations, forms, and complex layouts.
  • Office document support: Handles DOCX via python-docx and refers to the PowerPoint skill for PPTX files.
  • Use case: A researcher can pull the full text of an arXiv paper, or a business can batch‑process scanned invoices to retrieve key data.

Quick Start

Extract all text from the file 'report.pdf' and receive it as 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 or image?▼

To extract text from scanned PDFs or images, this tool uses marker-pdf for high-quality OCR and layout analysis, handling complex structures like equations and forms. It processes local files directly to retrieve readable text.

What is the best way to pull text from an online PDF or arXiv link?▼

The best way to pull text from online PDFs or arXiv links is using the web_extract service, which fetches remote URLs instantly for immediate text extraction without manual downloading.

Does pymupdf support extracting tables from text-based PDFs?▼

Yes, pymupdf supports extracting basic tables from text-based PDFs. It provides fast, lightweight text extraction for local files without requiring heavy OCR processing.

Can I process DOCX files for text extraction with this setup?▼

Yes, you can process DOCX files for text extraction using the python-docx library. The setup handles office documents alongside PDFs and scanned images for research and archival tasks.

When do I need OCR for PDF text extraction?▼

You need OCR for PDF text extraction when handling scanned documents, images, or complex layouts containing equations and forms where standard text parsing fails to retrieve readable content.

Why does marker-pdf take longer than pymupdf for document processing?▼

Marker-pdf takes longer because it performs deep OCR and layout analysis for scanned documents and complex structures, whereas pymupdf provides fast extraction for text-based PDFs without OCR overhead.

Related Skills

Explore More Education & Research Skills→
quiznatquiznat

ocr-and-documents

Extract text from PDFs and scanned documents using pymupdf and marker-pdf.

Community
Intermediate
alibabaalibaba
10.5k

pdf-extractor

Extract text, tables, and metadata from PDF documents into JSON.

Official
Intermediate
photonics-dhlphotonics-dhl

ocr-and-documents

Extract text and structured data from PDFs and documents using OCR and parsing tools.

Community
Intermediate
LeighAtkinsLeighAtkins

PDF Processing Pro

Extract tables, fill forms, and OCR scanned PDF documents.

Community
Advanced