LaunchKit · 2026
Back to Skills

markitdown-skill

OpenClaw agent skill for converting documents to Markdown.

0
1.1k downloads
by @karmanverma

Setup & Installation

openclaw skills install @karmanverma/markitdown-skill

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install markitdown-skill

Version History

v1.0.1Feb 10, 2026 - Version note by skill developer:

Fixed metadata: added requires.bins, clarified skill provides docs + batch script (converter is Microsoft's pip package)

What This Skill Does

Converts documents, web pages, and media files to Markdown using Microsoft's MarkItDown library. Supports PDF, Word, PowerPoint, Excel, HTML, images (OCR), audio transcription, and YouTube transcripts. Includes a batch conversion script and full Python API access.

Handles formats that most Markdown converters skip, including audio transcription and image OCR, in a single pip install.

When to use it

  • Convert a PDF report to Markdown for editing
  • Extract text from a PowerPoint presentation
  • Pull a YouTube video transcript into a notes file
  • Batch convert a folder of Word docs to Markdown
  • Scrape a documentation page into a local .md file

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: convert this PDF to Markdown

AGENT
  1. 1Receive the file path or URL from the user
  2. 2Run `markitdown document.pdf -o output.md` via CLI
  3. 3Check output.md for successful text extraction
  4. 4Return the Markdown content to the user
OUTPUT

A .md file with the extracted text, headings, and tables from the PDF