markitdown
MarkItDown
Purpose
Convert a wide variety of file formats into Markdown text using Microsoft's markitdown CLI. Useful for extracting text from documents for LLM analysis, summarization, or ingestion into knowledge bases.
Supported Formats
| Category | Formats |
|---|---|
| Documents | PDF, DOCX, PPTX, XLSX, XLS |
| Web & Data | HTML, CSV, JSON, XML |
| Media | Images (EXIF + OCR), Audio (metadata + transcription) |
| eBooks | EPub |
| Archives | ZIP (iterates over contents) |
| Other | YouTube URLs, Outlook messages |
Basic Usage
More from yutakobayashidev/dotnix
dce
Detect and eliminate dead code in TypeScript projects using ts-remove-unused (tsr). Use when the user wants to find unused exports, unused files, or clean up dead code.
1gha-lint
Lint and secure GitHub Actions workflows using pinact, actionlint, ghalint, and zizmor. Use when the user adds, updates, or reviews GitHub Actions workflows and wants to check correctness, security, or pin action versions.
1oura-daily-watch
Build and run a daily Oura + Discord behavior monitor. Use when the user wants morning wellness summaries, anomaly alerts, readiness/sleep trend checks, or advice based on Oura Ring data combined with chat activity patterns.
1speakerdeck
Download slide images from a SpeakerDeck presentation. Use when the user provides a SpeakerDeck URL and wants to read, summarize, or convert the slides.
1check-similarity
Detects duplicate TypeScript/JavaScript code using AST comparison for refactoring. Use when the user wants to find similar or duplicated functions, plan refactoring, or clean up redundant code in TS/JS projects.
1social-digest
Fetch today's Discord channel + Mastodon posts via API tokens, summarize to Markdown, and save into an Obsidian vault (Bun script).
1