ocr-and-documents

Name: ocr-and-documents
Availability: InStock
Author: rnben

Extract text from PDFs, scanned documents, DOCX, and PPTX files.

1|Updated Apr 18, 2026

Search Tags:#ocr #pdf #pymupdf #document-processing #text-extraction #marker-pdf #web_extract

Ready to run

npx skills add https://github.com/rnben/hermes-skills --skill ocr-and-documents-rnben

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/rnben/hermes-skills/tree/main/plugins/productivity-skills/skills/ocr-and-documents
Command: npx skills add https://github.com/rnben/hermes-skills --skill ocr-and-documents-rnben

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Extract text from PDFs and scanned documents to enable searchable, editable content and easier data reuse.

Core Features & Use Cases

Remote extraction: use web_extract for URLs to fetch and convert documents to text.
Local extraction: pymupdf handles text-based PDFs quickly and reliably.
OCR for scans: marker-pdf performs OCR on scanned documents with multi-language support and layout-aware output.
DOCX/PPTX support: uses python-docx for Word docs and references the powerpoint skill for PowerPoint files.

Quick Start

Provide a URL or file path to a document and I will extract its text using web_extract when possible, fallback to pymupdf for text PDFs, or marker-pdf for OCR on scans.

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?▼

To extract text from a scanned PDF, this Skill uses marker-pdf to perform OCR with multi-language support and layout-aware output. It processes scanned documents directly, converting images of text into searchable and editable content without manual transcription.

Can I extract text from a PDF using a remote URL?▼

Yes, you can extract text from a PDF using a remote URL. The Skill uses web_extract to fetch and convert documents from URLs to text automatically, supporting end-to-end document text extraction across multiple formats for automation pipelines.

What is the best way to extract text from DOCX and PPTX files?▼

The best way to extract text from DOCX and PPTX files is using python-docx for Word documents and the referenced powerpoint skill for PowerPoint files. This provides reliable text extraction from Office formats alongside its PDF processing capabilities.

Does pymupdf work for text extraction from text-based PDFs?▼

Yes, pymupdf works for extracting text from text-based PDFs quickly and reliably. It handles local text-based PDFs directly, providing a fast extraction method for documents that already contain embedded selectable text rather than scanned images.

When do I need OCR for PDF text extraction instead of pymupdf?▼

You need OCR for PDF text extraction when your document is a scanned image rather than a text-based PDF. The Skill uses marker-pdf for OCR on scans because pymupdf only extracts embedded text and cannot read text from images.