document-processor

Name: document-processor
Availability: InStock
Author: adnanmueller

Extract content from PDFs and DOCX into Markdown-ready text.

2|Updated Dec 24, 2025

Search Tags:#ocr #pdf #markdown #obsidian #docx #extraction #document-processing

Ready to run

npx skills add https://github.com/adnanmueller/am-dev-plugins --skill document-processor-adnanmueller

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: document-processor
Source: https://github.com/adnanmueller/am-dev-plugins/tree/main/plugins/document-processor
Command: npx skills add https://github.com/adnanmueller/am-dev-plugins --skill document-processor-adnanmueller

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, python-docx, pdf2image, pytesseract, Pillow, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a robust toolchain to extract content from PDFs and DOCX files, enabling you to convert and integrate documents into note-taking and knowledge bases with consistent formatting.

Core Features & Use Cases

Extract text and content from PDFs and DOCX while preserving structure
Convert DOCX to Markdown with headings, lists, tables, and emphasis
Split large documents into manageable chunks and enable OCR for scanned documents
Seamlessly integrate with Obsidian or other markdown note workflows

Quick Start

Process a sample PDF or DOCX to verify extraction and Markdown conversion.

Frequently Asked Questions about document-processor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I convert PDF and DOCX files to Markdown for Obsidian?▼

To convert PDF and DOCX files to Markdown for Obsidian, this tool extracts text and content while preserving structural elements like headings, lists, and tables. It outputs clean Markdown-ready text for seamless integration into your note-taking workflows.

Can I extract text from scanned PDFs using OCR?▼

Yes, you can extract text from scanned PDFs using OCR. The tool leverages Tesseract OCR and pdf2image to process scanned documents, converting image-based pages into clean, Markdown-ready text for archival workflows.

Does this approach preserve headings and tables when converting DOCX to Markdown?▼

Yes, converting DOCX to Markdown preserves headings, lists, tables, and emphasis. The extraction process uses python-docx to maintain original document structure, ensuring structured Markdown output for documentation and research.

What is the best way to split large PDFs into manageable Markdown chunks?▼

The best way to split large PDFs into manageable chunks is using the built-in page-splitting feature. It divides large documents during extraction, outputting structured Markdown text that is easier to manage in note-taking bases.

Do I need Python libraries installed to process documents into Markdown?▼

Yes, you need Python libraries installed to process documents into Markdown. The toolchain relies on pypdf, python-docx, pytesseract, pdf2image, and Pillow to extract content and format it into Markdown-ready text.