skills.rest
kaminocorp
kaminocorpOFFICIAL
Explore all skills by this author →
Website𝕏@kaminocorpoGitHub

ocr-and-documents

Extract text from PDFs and scanned documents into Markdown.

228|35|Updated Mar 9, 2026
Search Tags:#ocr#pdf#markdown#pymupdf#document-processing#text-extraction#marker-pdf
One-click install
npx skills add https://github.com/kaminocorp/hermes-alpha --skill ocr-and-documents-kaminocorp
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ocr-and-documents
Source: https://github.com/kaminocorp/hermes-alpha/tree/main/hermes-agent/skills/productivity/ocr-and-documents
Command: npx skills add https://github.com/kaminocorp/hermes-alpha --skill ocr-and-documents-kaminocorp

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Extract text from PDFs and scanned documents to produce clean, searchable text suitable for AI processing.

Core Features & Use Cases

  • Remote URL extraction using web_extract to convert online PDFs to markdown or plain text.
  • Local text-based PDF extraction with pymupdf for fast, dependency-light processing.
  • OCR-enabled extraction with marker-pdf for scanned documents, including complex layouts, tables, and embedded content.
  • DOCX and PPTX support via related skills for broader document workflows.
  • Output in Markdown or plain text, with optional metadata extraction.

Quick Start

Provide a document path or URL to the extraction tool to obtain text, using web_extract for URLs and pymupdf or marker-pdf for local or OCR-processed content.

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?▼

Text extraction from scanned PDFs uses marker-pdf for OCR processing, handling complex layouts, tables, and embedded content to output clean, searchable Markdown text suitable for AI processing.

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

Yes, you can extract text from a remote PDF URL using the web_extract functionality, which fetches online documents directly and converts them to Markdown or plain text.

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 provides fast, dependency-light local extraction while outputting clean Markdown-formatted text.

Does marker-pdf require heavy disk usage for OCR extraction?▼

Yes, marker-pdf relies on optional disk-heavy OCR operations to process scanned documents, extracting text and optional metadata while converting complex layouts to Markdown.

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

You should use pymupdf for fast, dependency-light extraction of text-based PDFs, whereas marker-pdf is necessary for scanned documents requiring OCR and complex layout handling.

Can I extract metadata and images alongside text from PDF documents?▼

Yes, you can extract optional metadata and images alongside text from PDF documents, receiving outputs formatted in Markdown or plain text suitable for AI processing workflows.

Related Skills

Explore More Software Engineering Skills→
AissenLiuAissenLiu

ocr-and-documents

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

Community
Advanced
yut0takagiyut0takagi

PDF操作

Merge, split, convert, and extract text from PDFs using Python libraries.

Community
Intermediate
Open330Open330
1

processing-documents

Extract and convert content from PDF, DOCX, XLSX, PPTX, HWP, and HWPX documents.

Official
Intermediate
projectedanxprojectedanx
1

ocr-and-documents

Extract text, tables, and images from PDFs and office files.

Community
Intermediate