skills.rest
ChangZhou-xj
ChangZhou-xjCOMMUNITY
Explore all skills by this author →
GitHub

ocr-and-documents

Extract text from PDFs and scans using pymupdf with marker-pdf OCR.

1|Updated Apr 21, 2026
Search Tags:#ocr#pdf#tables#pymupdf#document-processing#text-extraction#marker-pdf
One-click install
npx skills add https://github.com/ChangZhou-xj/zxj_skill --skill ocr-and-documents-changzhou-xj
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/ChangZhou-xj/zxj_skill/tree/main/productivity/ocr-and-documents
Command: npx skills add https://github.com/ChangZhou-xj/zxj_skill --skill ocr-and-documents-changzhou-xj

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Manually extracting text from PDFs, scanned documents, or other file formats is time-consuming and error-prone. This skill provides reliable text extraction and basic structure from both digital PDFs and OCR-enabled scans using lightweight pymupdf by default, with marker-pdf available for advanced OCR needs.

Core Features & Use Cases

  • Extract plain text, markdown, and tables from PDFs (text-based and scanned) with options to include images.
  • Compare and switch between lightweight text extraction (pymupdf) and high-accuracy OCR (marker-pdf) for non-searchable documents.
  • Ideal for research papers, Arxiv PDFs, invoices, and archival documents requiring searchable text, metadata, or structured outputs.

Quick Start

Ask me to extract text from a PDF or scanned document using the default pymupdf extractor, with OCR via marker-pdf if needed.

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 and tables from a scanned PDF?▼

Text and tables from a scanned PDF are extracted using marker-pdf for high-accuracy OCR. This handles non-searchable documents, outputting structured markdown that preserves multi-language layouts and images from research papers or archival documents.

What is the best way to convert a research paper PDF to markdown?▼

Converting a research paper PDF to markdown is handled by pymupdf4llm for lightweight text extraction. It outputs structured markdown that preserves tables and layouts, switching to marker-pdf automatically if the document requires OCR.

Does pymupdf support extracting metadata and images from digital PDFs?▼

Pymupdf supports extracting metadata and images from digital PDFs during text extraction. It processes text-based documents to output plain text or markdown, including embedded images and document metadata for archival workflows.

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

Use marker-pdf instead of pymupdf for document text extraction when handling scanned documents or non-searchable PDFs requiring OCR. Pymupdf remains the default for lightweight extraction from digital, text-based PDFs.

Can I batch process multiple PDFs for text extraction?▼

Batch processing multiple PDFs for text extraction is supported across research papers and archival documents. It applies pymupdf by default for text-based files and marker-pdf for OCR, outputting markdown and tables.

Related Skills

Explore More Education & Research Skills→
nadicodeainadicodeai

ocr-and-documents

Extract and convert PDF, scanned document, and image text to plain text or Markdown using OCR and pymupdf/marker-pdf.

Official
Intermediate
Wike-CHIWike-CHI
2

document-pro

Extract text, tables, and images from PDFs, DOCX, PPTX, XLSX, and plain text.

Community
Intermediate
huidgehuidge
2

ocr-and-documents

Extract text from PDFs and scanned documents into Markdown.

Community
Advanced
kaminocorpkaminocorp
228

ocr-and-documents

Extract text from PDFs and scanned documents into Markdown.

Official
Intermediate