Markdown Converter

Convert documents and files to Markdown using markitdown. Use when converting PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls), HTML, CSV, JSON, XML, images (with EXIF/OCR), audio (with transcription), ZIP archives, YouTube URLs, or EPubs to Markdown format for LLM processing or text analysis.

Security Scan

The skill's instructions are coherent with a document-to-Markdown converter, but it relies on an external CLI (uvx markitdown), mentions enabling 3rd‑party plugins and sending data to external services (Azure, YouTube) without describing credentials or trust boundaries — this creates operational and data-exfil risks the user should understand before installing.

Purpose & Capability

The name/description (convert many file types to Markdown) matches the SKILL.md usage of `uvx markitdown`. However the skill is instruction-only and assumes the `uvx` CLI exists on the host even though no required binaries or install steps are declared; that should be called out to users.

Instruction Scope

Instructions tell the agent to run `uvx markitdown` with options that may send data to external endpoints (e.g., Azure Document Intelligence via -d/-e, fetching YouTube content) and to enable `--use-plugins` (3rd‑party plugins). The SKILL.md does not document how plugins are sourced/installed or how credentials/API keys are supplied, which broadens the agent's discretion over what it may send or execute.

Install Mechanism

There is no install spec and no code files — the lowest-risk model from a disk/write perspective. All execution depends on an existing `uvx` binary on PATH.

Credentials

The skill declares no required environment variables or credentials, which matches the instruction-only nature. But it references Azure Document Intelligence (an external service that typically requires keys) and plugin usage; the SKILL.md omits how to provide authentication or whether the `uvx` tool will read env vars or config files, creating uncertainty about where secrets may be needed or stored.

Persistence & Privilege

always is false and there is no installation altering agent configs. The skill does not request persistent privileges or automatic inclusion.

What to consider before installing

This skill is basically a set of usage notes for the external CLI `uvx markitdown`. Before using/installing: 1) Verify you have the `uvx` binary from a trusted source (the skill provides no install or homepage). 2) Be cautious with `--use-plugins` — third‑party plugins may execute code or access the network; only enable them if you trust their source. 3) When using Azure Document Intelligence or other external services, understand that document contents will be sent to those endpoints and that additional credentials (API keys) may be required — confirm how `uvx` expects those keys and where they are stored. 4) Test the tool on non-sensitive sample files first to observe network activity and plugin behavior. If you need this capability but want lower risk, prefer a verified converter binary or a documented installation from an official project page.

Convert files to Markdown using uvx markitdown — no installation required.

Basic Usage

# Convert to stdout
uvx markitdown input.pdf

# Save to file
uvx markitdown input.pdf -o output.md
uvx markitdown input.docx > output.md

# From stdin
cat input.pdf | uvx markitdown

Supported Formats

• Documents: PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls)
• Web/Data: HTML, CSV, JSON, XML
• Media: Images (EXIF + OCR), Audio (EXIF + transcription)
• Other: ZIP (iterates contents), YouTube URLs, EPub

Options

-o OUTPUT      # Output file
-x EXTENSION   # Hint file extension (for stdin)
-m MIME_TYPE   # Hint MIME type
-c CHARSET     # Hint charset (e.g., UTF-8)
-d             # Use Azure Document Intelligence
-e ENDPOINT    # Document Intelligence endpoint
--use-plugins  # Enable 3rd-party plugins
--list-plugins # Show installed plugins

Examples

# Convert Word document
uvx markitdown report.docx -o report.md

# Convert Excel spreadsheet
uvx markitdown data.xlsx > data.md

# Convert PowerPoint presentation
uvx markitdown slides.pptx -o slides.md

# Convert with file type hint (for stdin)
cat document | uvx markitdown -x .pdf > output.md

# Use Azure Document Intelligence for better PDF extraction
uvx markitdown scan.pdf -d -e "https://your-resource.cognitiveservices.azure.com/"

Notes

• Output preserves document structure: headings, tables, lists, links
• First run caches dependencies; subsequent runs are faster
• For complex PDFs with poor extraction, use -d with Azure Document Intelligence