skills.rest
musical-basics
musical-basicsCOMMUNITY
Explore all skills by this author →
GitHub

ocr-and-documents

Extract text and data from PDFs, scanned documents, and images.

Updated Apr 11, 2026
Search Tags:#ocr#pdf#extraction#text#pymupdf#document#marker-pdf
One-click install
npx skills add https://github.com/musical-basics/hermes-build-2 --skill ocr-and-documents-musical-basics
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/musical-basics/hermes-build-2/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/musical-basics/hermes-build-2 --skill ocr-and-documents-musical-basics

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Extracting readable text from PDFs, scanned documents, images, and similar file formats is time‑consuming and often requires multiple tools. This skill automates the process, handling both native PDFs and scanned PDFs that need OCR, as well as DOCX and other document types.

Core Features & Use Cases

  • Web extraction: Uses web_extract for remote URLs, converting PDFs to markdown without local dependencies.
  • Lightweight local extraction: pymupdf handles text‑based PDFs, tables, images, and EPUBs with minimal installation size.
  • High‑quality OCR and layout analysis: marker-pdf provides OCR for scanned documents, equations, forms, and complex layouts when advanced extraction is required.
  • Document formats: Supports DOCX via python-docx and references the powerpoint skill for PPTX files.
  • Utility functions: Split, merge, and search PDFs using simple Python snippets.

Quick Start

Extract all text from the PDF file 'report.pdf' using the OCR-and-documents skill.

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 for research?▼

To extract text from scanned PDFs or images, you use OCR processing. This skill uses marker-pdf for high-quality OCR and layout analysis, handling complex layouts, equations, and forms to digitize content accurately.

What is the best way to convert a text-based PDF to markdown?▼

Converting a text-based PDF to markdown is done using lightweight local extraction. The skill uses pymupdf to handle text, tables, and images from PDFs and EPUBs with minimal installation overhead.

Does marker-pdf work better than pymupdf for complex document layouts?▼

Yes, marker-pdf handles complex layouts, equations, and forms better than pymupdf. While pymupdf is for lightweight extraction from text-based PDFs, marker-pdf provides advanced OCR and layout analysis for scanned documents.

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

You can extract text from remote PDF URLs using web extraction. The skill uses web_extract to convert remote PDFs to markdown directly without needing local dependencies or downloads.

Do I need Python libraries to split and merge PDF files for document analysis?▼

Yes, you need Python libraries like pymupdf to split, merge, and search PDFs. The skill provides utility functions using simple Python snippets to manipulate document files for analysis tasks.

Related Skills

Explore More Education & Research Skills→
automatedigitalautomatedigital
1

ocr-and-documents

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

Official
Intermediate
cas-bigdatalabcas-bigdatalab
541

docx_text_extract

Extract text from DOCX files to plain text using Python's zipfile and xml libraries.

Official
Basic
shuyu-labsshuyu-labs
288

office-to-md

Convert Word, Excel, PowerPoint, and PDF documents to Markdown with preserved headings, tables, and images.

Official
Advanced
89jobrien89jobrien
4

PDF Processing

Extract text and tables from native and scanned PDFs using pdfplumber.

Community
Advanced