markitdown

Convert PDFs, Office documents, images, and archives into Markdown.

783|65|Updated Feb 27, 2026
One-click install
npx skills add https://github.com/LeonChaoX/qinyan-academic-skills --skill markitdown-leonchaox
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: markitdown
Source: https://github.com/LeonChaoX/qinyan-academic-skills/tree/main/skills/14-%E6%96%87%E6%A1%A3%E5%A4%84%E7%90%86%E4%B8%8E%E6%95%B0%E6%8D%AE%E5%B7%A5%E5%85%B7/markitdown
Command: npx skills add https://github.com/LeonChaoX/qinyan-academic-skills --skill markitdown-leonchaox

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Converting PDFs, Office files, and other document formats into text you can analyze or reuse is slow and error-prone, especially when you need consistent formatting for literature review, note-taking, or LLM workflows.

Core Features & Use Cases

  • Convert files to structured Markdown: Turn PDFs, DOCX, PPTX, XLSX/CSV/JSON/XML, HTML, images, and archives into Markdown for easier reading and downstream processing.
  • Handle scanned and visual content: Perform OCR for images/scanned documents and optionally generate AI-enhanced image descriptions for figures and slide visuals.
  • Fit into research workflows: Use the Markdown output as LLM-friendly input for summarization, extraction, indexing, and comparative literature review.

Quick Start

Ask the agent to convert the file invoice.pdf into Markdown and return the extracted text content.

Frequently Asked Questions about markitdown

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

FAQPage Schema
How do I convert a PDF to Markdown for LLM workflows?

You can convert PDFs to Markdown by asking the agent to process the input file and return the extracted text content. This Skill applies faithful format-to-Markdown conversion to provide clean, LLM-friendly text for downstream analysis.

Can I extract text from scanned documents and images using OCR?

Yes, you can extract text from scanned documents and images using OCR. This Skill performs OCR for images and scanned documents, and optionally generates AI-enhanced descriptions for figures and slide visuals to support complete document processing.

Does this tool convert Office files like PPTX and DOCX into Markdown?

Yes, this tool converts Office files including DOCX and PPTX into Markdown. It supports turning PDFs, DOCX, PPTX, XLSX, CSV, JSON, XML, HTML, and archives into structured Markdown for easier reading and downstream processing.

What is the best way to prepare academic literature for a comparative review?

The best way to prepare academic literature for a comparative review is to convert the source documents into structured Markdown. This generates consistent, LLM-friendly input that enables accurate summarization, extraction, indexing, and comparative literature review.

What file formats are supported for converting to Markdown text?

Supported file formats for converting to Markdown text include PDFs, DOCX, PPTX, XLSX, CSV, JSON, XML, HTML, images, and archives. These formats are processed into clean, LLM-friendly Markdown to fit into academic and research document workflows.

Why convert documents to Markdown for note-taking and extraction?

You convert documents to Markdown for note-taking and extraction because it creates consistent, structured formatting from PDFs and Office files. This clean text output prevents formatting errors and serves as LLM-friendly input for downstream indexing and analysis.