Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

MarkItDown Document-to-Markdown

Convert PDFs, Office files, HTML, and more into clean Markdown with Microsoft MarkItDown for search, analysis, and LLM/RAG ingestion.

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

What it does

This skill teaches Claude to drive Microsoft MarkItDown 0.1.6 correctly and safely.

  • Converts PDF, DOCX, PPTX, XLSX/XLS, HTML, CSV, EPUB, ZIP, and Outlook mail into structure-preserving Markdown
  • Provides a decision table for picking the narrowest API: convert_local() for paths, convert_stream() with StreamInfo for bytes, convert_response() after your own validated HTTP fetch
  • Bundles batch helpers (batch_convert.py, convert_literature.py) with manifest files, YAML front matter provenance, and year-based organization
  • Explains scanned-PDF/image text options: the markitdown-ocr vision plugin, Azure Document Intelligence, Azure Content Understanding
  • Covers the official markitdown-mcp server plus STDIO vs HTTP/SSE security tradeoffs
  • Includes a troubleshooting table and a post-conversion quality checklist

Security rules are explicit: treat converted text as untrusted (prompt-injection risk), keep plugins opt-in, and get approval before sending content to external services.

Who it's for

  • Engineers building RAG pipelines or search indexes over internal document stores
  • Researchers and grad students turning hundreds of paper PDFs into analyzable Markdown
  • Knowledge workers feeding reports, decks, and spreadsheets to an LLM
  • Teams that must keep confidential documents on local-only conversion paths

Examples

  1. Single report: "Convert report.pdf to Markdown" → runs markitdown report.pdf -o report.md, then verifies headings and tables against the quality checklist.
  2. Literature library: batch-convert 300 PDFs in papers/ with convert_literature.py --recursive --create-index, organizing output by year parsed from Smith_2025_Title.pdf.
  3. Scanned document: when a PDF yields almost no text, choose between the markitdown-ocr plugin and Azure Document Intelligence, confirming with the user first because data leaves the machine.

· · · Install guide · · ·

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/scientific-agent-skills && mkdir -p ~/.claude/skills && cp -r /tmp/scientific-agent-skills/skills/markitdown ~/.claude/skills/

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

  1. Open a terminal and clone the skill repository: 
    git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  2. Create your Claude skills folder and copy just this skill: 
    mkdir -p ~/.claude/skills
cp -r scientific-agent-skills/skills/markitdown ~/.claude/skills/
  3. Make sure Python 3.10+ and uv are installed (curl -LsSf https://astral.sh/uv/install.sh | sh if needed).
  4. Create an isolated environment and install MarkItDown: 
    uv venv --python 3.12 .venv && source .venv/bin/activate
uv pip install "markitdown[all]==0.1.6"
  5. Verify with markitdown --version.
  6. Restart Claude Code, then ask something like "Convert this PDF to Markdown" and the skill will activate.
  7. (Optional) For OCR or Azure extraction, install the extra plugin and set the API keys. Keep confidential files on the local-only path.
View source on GitHub ↗License: MIT