pdf-to-markdown

Convert PDFs into structured Markdown using .NET-native parsing in PowerShell.

11|1|Updated Mar 27, 2026

Search Tags:#ocr #pdf #markdown #dotnet #text-extraction #powershell #german

Ready to run

npx skills add https://github.com/raandree/CopilotAtelier --skill pdf-to-markdown-raandree

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf-to-markdown
Source: https://github.com/raandree/CopilotAtelier/tree/main/Skills/pdf-to-markdown
Command: npx skills add https://github.com/raandree/CopilotAtelier --skill pdf-to-markdown-raandree

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Converting PDFs into editable, well-structured Markdown without external tooling, enabling offline documentation workflows and easier content reuse.

Core Features & Use Cases

NET-native PDF parsing in PowerShell for text extraction without Python, pdftotext, or Word
Decodes hex-encoded text operators and reconstructs lines by Y-coordinate positioning to preserve layout
German locale support (ISO-8859-1) and handling of umlauts, ß, and special chars
OCR fallback using pymupdf + Tesseract for image-only PDFs with a Windows-friendly installation guide
Produces clean Markdown including tables and formatting, suitable for payslips, invoices, and reports
On-demand use as a slash-command-style workflow within Copilot Atelier

Quick Start

Run the pdf-to-markdown workflow on a sample.pdf to generate a Markdown document.

Frequently Asked Questions about pdf-to-markdown

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

FAQPage Schema

How do I convert PDF to Markdown offline without installing external tools?▼

You can convert PDF to Markdown offline using .NET-native PDF parsing in PowerShell, which extracts text and reconstructs lines by Y-coordinate without needing Python, pdftotext, or Word.

Can I extract text from German-language PDFs with umlauts and special characters?▼

Yes, PDF text extraction supports German locale ISO-8859-1, correctly decoding hex-encoded text operators to preserve umlauts, ß, and special characters in the final Markdown output.

Does PDF to Markdown conversion work with image-only PDFs?▼

Image-only PDFs require an OCR fallback using pymupdf and Tesseract, which extracts text from images and includes a Windows-friendly installation guide to complete the Markdown conversion.

What is the best way to extract structured tables from PDF invoices into Markdown?▼

The best way to extract tables from PDF invoices is using .NET-native parsing that decodes hex-encoded text and reconstructs lines by Y-coordinate positioning, producing clean Markdown formatting.

Do I need Python to parse PDF files in PowerShell?▼

No, you do not need Python for standard PDF text extraction in PowerShell. .NET-native parsing handles the conversion directly, though Python is only required for the optional OCR fallback on image-based PDFs.