markitdown-skill
⚠Review·Scanned 2/18/2026
This skill provides documentation and utilities for converting documents to Markdown using the markitdown CLI and Python API. It includes shell commands (pip install 'markitdown[all]', markitdown ...), a batch script (scripts/batch_convert.py), and instructs setting AZURE_DOCUMENT_INTELLIGENCE_KEY and calling external endpoints like https://your-endpoint.cognitiveservices.azure.com/.
from clawhub.ai·v0501036·23.8 KB·0 installs
Scanned from 1.0.1 at 0501036 · Transparency log ↗
$ vett add clawhub.ai/karmanverma/markitdown-skillReview findings below
markitdown-skill
📄 OpenClaw agent skill for converting documents to Markdown.
Documentation and utilities for Microsoft's MarkItDown library.
Author: Karman Verma
What This Skill Is
This skill provides:
- ✅ Documentation for using MarkItDown
- ✅ A batch conversion script (
scripts/batch_convert.py) - ✅ Usage examples and API reference
The actual document conversion is done by Microsoft's markitdown CLI, installed separately via pip.
Install
Via ClawHub
clawhub install markitdown-skill
pip install 'markitdown[all]' # Install the CLI
Manual
cd ~/.openclaw/skills
git clone https://github.com/karmanverma/markitdown-skill.git markitdown
pip install 'markitdown[all]'
Quick Start
# Convert PDF
markitdown document.pdf -o output.md
# Fetch web docs
markitdown https://example.com/docs -o docs.md
# Batch convert
python ~/.openclaw/skills/markitdown/scripts/batch_convert.py docs/*.pdf -o markdown/
Supported Formats
| Format | Features |
|---|---|
| Text extraction | |
| Word (.docx) | Headings, lists, tables |
| PowerPoint | Slides, text |
| Excel | Tables, sheets |
| Images | OCR + metadata |
| Audio | Speech transcription |
| HTML | Structure preservation |
| YouTube | Video transcription |
Documentation
- SKILL.md - Main documentation
- USAGE-GUIDE.md - Detailed examples
- reference.md - Full API reference
- POST_INSTALL.md - Setup guide
Credits
- Upstream library: Microsoft MarkItDown by AutoGen Team
- This skill: Karman Verma
License
MIT