skills.rest
DaddyElonMusk69
DaddyElonMusk69COMMUNITY
Explore all skills by this author →
GitHub

ocr-and-documents

Extract text, tables, and images from PDFs and scanned documents into Markdown.

Updated Apr 12, 2026
Search Tags:#ocr#pdf#pymupdf#text-extraction#document-extraction#marker-pdf#web_extract
One-click install
npx skills add https://github.com/DaddyElonMusk69/motis-agent --skill ocr-and-documents-daddyelonmusk69
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/DaddyElonMusk69/motis-agent/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/DaddyElonMusk69/motis-agent --skill ocr-and-documents-daddyelonmusk69

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Many important documents are locked in PDFs, scanned images, or complex layouts that block search, extraction, and downstream analysis; this skill converts those sources into searchable, editable, and structured text so you can read, analyze, or repurpose content quickly.

Core Features & Use Cases

  • Remote URL extraction using web_extract for fast PDF-to-markdown conversion without local dependencies.
  • Lightweight local parsing with pymupdf for plain text extraction, basic tables, split/merge operations, image extraction, and metadata inspection.
  • High-quality OCR and layout analysis with marker-pdf for scanned documents, equations, forms, and complex layouts, including a disk space check and optional LLM-boosted post-processing.
  • Recommendations for DOCX parsing via python-docx and guidance to use the powerpoint skill for PPTX files.
  • Typical use cases include extracting arXiv papers, batch-processing reports and invoices, pulling tables for financial analysis, and saving embedded images for review.

Quick Start

Extract the full text and any tables from the provided document (URL or local PDF) and return the output in Markdown.

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 for markdown output?▼

To extract text and tables from a scanned PDF into markdown, this skill uses marker-pdf for OCR and layout analysis, handling complex layouts, equations, and forms while returning structured markdown output.

What is the best way to convert a remote PDF URL to markdown without downloading the file?▼

Converting a remote PDF URL to markdown is done using the web_extract feature, which fetches the document and performs PDF-to-markdown conversion directly without needing local file dependencies.

Does pymupdf support image extraction and metadata inspection from local PDFs?▼

Yes, pymupdf supports lightweight local parsing for plain text extraction, basic tables, split and merge operations, image extraction, and metadata inspection from text-based PDFs.

When do I need to use marker-pdf instead of pymupdf for document extraction?▼

You need marker-pdf instead of pymupdf when processing scanned documents, equations, or complex layouts, as it provides high-quality OCR and layout analysis rather than just lightweight text extraction.

Are there disk space requirements for installing OCR models to process scanned documents?▼

Yes, the skill includes local disk-space checks before installing large OCR models required by marker-pdf, ensuring your system has sufficient storage for high-quality scanned document processing.

Can I batch process research papers and invoices to pull tables for financial analysis?▼

Yes, you can batch process research papers, reports, and invoices to pull tables for financial analysis and save embedded images, using either pymupdf or marker-pdf based on the document type.

Related Skills

Explore More Education & Research Skills→
AissenLiuAissenLiu

ocr-and-documents

Extract text from PDFs and scanned documents via web_extract, pymupdf, or marker-pdf.

Community
Advanced
smilebank7smilebank7
2

Extract Materials

Extract text, tables, and equations from PDFs, PPTX, DOCX, and images into Markdown.

Community
Intermediate
photonics-dhlphotonics-dhl

ocr-and-documents

Extract text and structured data from PDFs and documents using OCR and parsing tools.

Community
Intermediate
89jobrien89jobrien
4

PDF Processing

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

Community
Advanced