ocr-and-documents

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

Extract text from PDFs and scanned documents into Markdown.

2|2|Updated Apr 16, 2026

Search Tags:#ocr #pdf #pymupdf #document-processing #text-extraction #python-docx #web-extract

Ready to run

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

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps you quickly convert text from PDFs and scanned documents into editable, searchable content, reducing manual copy-paste and data-entry tasks.

Core Features & Use Cases

Remote URL extraction: Always try web_extract first to convert online PDFs to Markdown text.
Local text-based PDFs: Use pymupdf for fast, accurate text extraction from standard PDFs.
OCR/Scanned documents: Use marker-pdf for OCR-enabled extraction of text, equations, tables, and images.
Office docs support: For DOCX use python-docx; PPTX is covered by the powerpoint skill.
Use Case: Convert a batch of arXiv PDFs to Markdown for analysis and indexing.

Quick Start

Extract the full text from the provided PDF or scanned document, preferring web_extract for URLs and pymupdf for local documents.

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 using OCR, this tool utilizes marker-pdf to accurately recognize text, equations, tables, and images, converting the document into editable Markdown output for downstream processing.

Can I extract text directly from a remote PDF URL without downloading it first?▼

Yes, you can extract text directly from a remote PDF URL by using the web_extract component, which fetches the online document and converts it into Markdown text for immediate downstream analysis.

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

The best way to convert text-based PDFs to Markdown is using pymupdf, which provides fast and accurate text extraction from standard local documents without requiring heavy OCR processing.

Does this text extraction approach support DOCX and PPTX files?▼

Yes, the text extraction approach supports DOCX files via the python-docx library, while PPTX files are handled by a separate powerpoint skill to ensure accurate document processing.

How do I process a batch of arXiv PDFs for indexing?▼

To process a batch of arXiv PDFs for indexing, the Skill extracts full text from each document, favoring web_extract for remote URLs and pymupdf for local files, outputting Markdown.

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

You should use marker-pdf instead of pymupdf when dealing with scanned documents or image-heavy PDFs that require OCR-enabled extraction, as pymupdf is optimized for fast text-based PDFs.