markitdown

name	markitdown
description	Convert any document to Markdown with Microsoft's `markitdown` CLI — PDF, Word, Excel, PowerPoint, HTML, CSV, JSON, XML, ZIP, EPub, images (OCR/EXIF), audio (transcription), and YouTube URLs. Use whenever the user wants to extract text from a binary document, transcribe audio, OCR an image, scrape a YouTube transcript, or pre-process a file for an LLM context window — even when they just say "convert this pdf", "what's in this docx", "transcribe this mp3", or "get the text out of this".
when_to_use	When the user has a non-Markdown file (PDF, DOCX, PPTX, XLSX, HTML, CSV, JSON, XML, EPub, ZIP, image, audio) or a YouTube URL and wants the contents as Markdown — for reading, summarising, feeding to an LLM, or saving as a clean text file. Keywords — convert to markdown, extract text, ocr, transcribe, read pdf, parse document, youtube transcript, markitdown, doc to md. Skip when the file is already Markdown, when the user wants visual rendering instead of text extraction, or when only a tiny snippet is needed and the Read tool is faster.
argument-hint	[-s] [-S] [-d] [-p] [-k] [-l] <file-or-url>
allowed-tools	Bash(bash *) Bash(markitdown *) Bash(command *) Read
license	MIT
metadata	{"author":"coroboros","sources":["github.com/microsoft/markitdown"]}

MarkItDown

Convert a document, image, audio file, or YouTube URL to Markdown using Microsoft's markitdown CLI. The skill validates the input, composes the right flags, optionally saves the result under ~/.agents/output/<project>/markitdown/<slug>/, and reports a one-line summary with the fully-expanded absolute path (no tilde, no magic).

The deterministic work — install check, validation, slug derivation, save path, command composition — happens in scripts/markitdown.sh. The skill parses $ARGUMENTS, hands them to the script, and turns the script's RESULT: lines into a human report.

Install

pip install 'markitdown[all]'

For a smaller install, pick only what you need:

Group	Adds
[pdf]	PDF parsing
[docx]	Word documents
[pptx]	PowerPoint
[xlsx] [xls]	Excel
[outlook]	Outlook .msg
[audio-transcription]	MP3/WAV via local Whisper
[youtube-transcription]	YouTube transcripts
[az-doc-intel]	Azure Document Intelligence backend

For Azure Document Intelligence, also export MARKITDOWN_DOCINTEL_ENDPOINT=https://<resource>.cognitiveservices.azure.com/ before invoking with -d.

Parameters

Flag	Default	Effect
-s	off	Save Markdown to ~/.agents/output/<project>/markitdown/<slug>/<stem>.md
-S	off	Force no-save (override an ambient save mode)
-d