Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

MarkItDown Document-to-Markdown Conversion

Guides Claude to convert PDFs, Office files, HTML, CSV and more into clean Markdown with Microsoft MarkItDown for search, analysis, and RAG ingestion.

Docs & OfficeIntermediate★ 33,030⑂ 3,248AI score 10/10Last updated: Aug 9, 2026

What it does

  • Converts PDF, DOCX, PPTX, XLSX, HTML, CSV, EPUB and ZIP into structure-preserving Markdown using MarkItDown 0.1.6.
  • Provides a decision table for picking the narrowest safe API: convert_local, convert_stream, convert_response, or convert_uri.
  • Ships batch-conversion and literature-conversion helper scripts (YAML provenance front matter, year-based organization, index generation).
  • Covers OCR options for scanned PDFs (markitdown-ocr plugin, Azure Document Intelligence / Content Understanding), the official MCP server, quality checks and a troubleshooting table.
  • Enforces safety rules: treat converted text as untrusted (prompt-injection risk) and get approval before sending content to external services.

Who it's for

  • Developers and data engineers building RAG pipelines or internal search indexes.
  • Researchers and grad students who need hundreds of paper PDFs turned into text.
  • Knowledge workers standardizing office documents into LLM-readable Markdown.

Examples

  1. markitdown report.pdf -o report.md for a one-off report conversion.
  2. python scripts/batch_convert.py documents/ markdown/ --recursive --extensions .pdf .docx --manifest markdown/manifest.json to convert a whole tree with a manifest.
  3. python scripts/convert_literature.py papers/ literature-markdown/ --recursive --create-index to organize Smith_2025_Title.pdf style papers by year with an index.
  4. For scanned contracts with almost no extractable text, switch to the markitdown-ocr plugin or Azure OCR (requires explicit approval since data leaves the machine).

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/markitdown/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/markitdown folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/markitdown/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/sas && mkdir -p ~/.claude/skills && cp -r /tmp/sas/skills/markitdown ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repo: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  2. Copy the skill into your Claude Code skills folder: mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/markitdown ~/.claude/skills/
  3. Make sure you have Python 3.10+ and uv installed (uv --version).
  4. Create and activate a virtual environment: uv venv --python 3.12 .venv && source .venv/bin/activate
  5. Install MarkItDown: uv pip install "markitdown[all]==0.1.6" (or just the extras you need, e.g. markitdown[pdf,docx,pptx,xlsx]==0.1.6).
  6. Verify with markitdown --version.
  7. Restart Claude Code, then ask something like "convert this PDF to Markdown" to trigger the skill.
  8. (Optional) For OCR, Azure, or MCP workflows, read references/cloud_and_ocr.md and references/mcp_and_plugins.md first to set credentials and confirm your data-sharing policy.
View source on GitHub ↗License: MIT