markdown-converter

Converts PDF, DOCX, PPTX, XLSX, HTML, CSV, JSON, XML, images, audio, ZIP, YouTube URLs, EPUBs to Markdown via uvx markitdown.

1|Updated Oct 9, 2018

Search Tags:#ocr #document processing #pdf #markdown #transcription #conversion

Ready to run

npx skills add https://github.com/Apostolos-Delis/Dotfiles --skill markdown-converter-apostolos-delis

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: markdown-converter
Source: https://github.com/Apostolos-Delis/Dotfiles/tree/main/.agents/skills/markdown-converter
Command: npx skills add https://github.com/Apostolos-Delis/Dotfiles --skill markdown-converter-apostolos-delis

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the process of converting various document and media formats into Markdown, making them easily processable by LLMs and suitable for text analysis.

Core Features & Use Cases

Universal Conversion: Supports a wide array of file types including PDFs, Word documents, spreadsheets, presentations, HTML, CSV, JSON, XML, images (with OCR), audio (with transcription), ZIP archives, YouTube URLs, and EPubs.
LLM-Ready Output: Generates Markdown that preserves document structure (headings, tables, lists, links), ideal for AI consumption.
Use Case: You have a collection of research papers in PDF and DOCX format, along with some audio recordings of lectures. Convert all these into Markdown files to create a unified, searchable knowledge base for your AI assistant.

Quick Start

Convert the document 'research_paper.pdf' into markdown format and save it to 'research_paper.md'.

Frequently Asked Questions about markdown-converter

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

FAQPage Schema

How do I convert PDF documents to Markdown for LLM processing?▼

You can convert PDFs to Markdown by utilizing `uvx markitdown`, which transforms documents into LLM-ready text while preserving headings, tables, and lists. It also optionally supports Azure Document Intelligence for enhanced PDF extraction.

Can I transcribe audio files and convert them into Markdown format?▼

Yes, this conversion process supports audio files by utilizing transcription capabilities to generate Markdown output. This allows you to easily integrate transcribed lecture recordings or voice notes into a searchable text knowledge base.

Does this conversion method support extracting text from images using OCR?▼

Yes, image files are fully supported using OCR technology to extract text and convert it into structured Markdown. This allows visual content and scanned documents to be processed alongside standard text formats like DOCX and HTML.

What is the best way to convert YouTube URLs and EPUBs into Markdown text?▼

The conversion mechanism directly accepts YouTube URLs and EPUB files, transforming their content into structured Markdown. This preserves document structure and facilitates AI consumption without requiring intermediate manual extraction steps.

How do I process multiple file types like XLSX, CSV, and JSON into a unified Markdown format?▼

This conversion tool supports universal file type handling, transforming spreadsheets, CSVs, and JSON files into a single Markdown format. It preserves structural elements like tables and lists, making the output ideal for unified text analysis.

Do I need Azure Document Intelligence to extract text from complex PDF files?▼

No, Azure Document Intelligence is an optional dependency used only for enhanced PDF extraction. The base conversion process relies on `uvx markitdown` to handle PDFs and other formats autonomously without requiring external cloud services.