ocr-and-documents

Extract text, tables, and images from PDFs and scanned documents using pymupdf or marker-pdf.

Updated Aug 21, 2026
One-click install
npx skills add https://github.com/TylerSimons1127/vibe --skill ocr-and-documents-tylersimons1127
Or copy as Structured Prompt for Agentâ–¼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/TylerSimons1127/vibe/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/TylerSimons1127/vibe --skill ocr-and-documents-tylersimons1127

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Getting usable text out of PDFs, scanned documents, and research papers is often blocked by missing text layers, complex layouts, equations, or tables that simple copy-paste cannot handle. ## Core Features & Use Cases - Lightweight extraction with pymupdf: Pull plain text, markdown, tables, embedded images, and metadata from text-based PDFs with a ~25MB install. - High-quality OCR with marker-pdf: Process scanned PDFs, equations, forms, and complex layouts in 90+ languages, with optional LLM-boosted accuracy. - Remote URL extraction: Use web_extract via Firecrawl to convert hosted PDFs (including arXiv papers) to markdown with no local dependencies. - Use Case: You have a scanned 50-page report and an arXiv paper URL. Use web_extract for the paper, then run the marker script on the scanned report to get clean markdown with tables and equations preserved. ## Quick Start Extract the text from my local file report.pdf, using OCR if it turns out to be a scanned document.

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 PDF in Python?â–¼

Use pymupdf to open the PDF and call get_text() on each page, or run the extract_pymupdf.py script for plain text, markdown, tables, or metadata. It installs in about 25MB and works instantly on text-based PDFs.

pymupdf vs marker-pdf for PDF extraction?â–¼

pymupdf is lightweight (~25MB) and instant, handling text-based PDFs, basic tables, and embedded images. marker-pdf (~3-5GB with PyTorch) adds OCR for scanned documents, equations, forms, and reading-order detection.

How do I OCR a scanned PDF document?â–¼

Use marker-pdf, which performs OCR in over 90 languages and outputs markdown. Run the extract_marker.py script on the scanned file, optionally with --use_llm for higher accuracy, after confirming about 5GB of free disk space.

Can I extract text from a PDF hosted at a URL?â–¼

Yes, web_extract handles remote PDFs via Firecrawl and converts them to markdown with no local dependencies. It is the recommended first choice for URLs, including arXiv abstract and PDF links.

Why does PDF text extraction return empty output?â–¼

Empty output usually means the PDF is scanned and has no text layer, which pymupdf cannot read. Switch to marker-pdf for OCR, or provide a URL so web_extract can process the document instead.

What are the limitations of pymupdf for documents?â–¼

pymupdf cannot perform OCR on scanned pages, recognize equations or forms, or detect reading order and headers. For those cases use marker-pdf, which requires roughly 5GB of disk for PyTorch and models.