skills.rest
AlexiosBluffMara
AlexiosBluffMaraCOMMUNITY
Explore all skills by this author →
GitHub

ocr-and-documents

Extract text and structure from PDFs and scanned documents into Markdown.

2|Updated Apr 25, 2026
Search Tags:#ocr#pdf#document-processing#text-extraction#markdown-output#web_extract
One-click install
npx skills add https://github.com/AlexiosBluffMara/mercury --skill ocr-and-documents-alexiosbluffmara
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/AlexiosBluffMara/mercury/tree/main/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/AlexiosBluffMara/mercury --skill ocr-and-documents-alexiosbluffmara

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Extract text from PDFs and scanned documents using OCR and parsing tools, enabling quick ingestion and downstream processing.

Core Features & Use Cases

  • Remote URL extraction with web_extract for PDFs
  • Local extraction using pymupdf for text-based PDFs
  • OCR-based extraction using marker-pdf for scanned documents
  • Guidance for DOCX (python-docx) and PPTX (python-pptx) processing
  • Markdown output and image extraction to support analysis and archiving

Quick Start

Process a local or remote document to extract text with pymupdf for text PDFs and marker-pdf for OCR.

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 skill utilizes marker-pdf to process images and tables, outputting the extracted content as structured Markdown for downstream analysis.

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

Yes, you can extract text from a remote PDF URL directly using the web_extract feature, which retrieves the document remotely and parses its contents without requiring a manual local download.

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

The best way to convert a text-based PDF to Markdown is using pymupdf, which parses text and basic document structure efficiently, while marker-pdf handles scanned documents requiring OCR.

Does this document processing approach support EPUB files?▼

Yes, this document processing approach supports EPUB files alongside PDFs, extracting text and basic structure to provide Markdown output and supporting image extraction for archiving and analysis.

Do I need pymupdf and marker installed to process local PDF files?▼

Yes, you need pymupdf installed for parsing text-based local PDFs and marker installed for performing OCR on scanned documents, ensuring both text and image-based inputs are processed correctly.

Related Skills

Explore More Data & Analytics Skills→
kaminocorpkaminocorp
228

ocr-and-documents

Extract text from PDFs and scanned documents into Markdown.

Official
Intermediate
sixscripts-aisixscripts-ai

vector-database-engineer

Configure vector retrieval pipelines with embedding models and HNSW indexes.

Community
Advanced
NateBJones-ProjectsNateBJones-Projects
4.4k

heavy-file-ingestion

Convert heavyweight files into markdown, CSV, and an index.

Official
Intermediate
jmaglyjmagly
175

pdf-extractor

Extracts text, tables, and images from PDFs into structured outputs with OCR support.

Community
Advanced