# Convert To Markdown

> This skill should be used when the user asks to "convert a document to markdown", "extract text from PDF", "convert Word/PowerPoint/Excel to markdown", or needs to transform documents into markdown format.

- **Type:** Skill
- **Install:** `agentstack add skill-mfmezger-ai-agent-dotfiles-convert-to-markdown`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [mfmezger](https://agentstack.voostack.com/s/mfmezger)
- **Installs:** 0
- **Category:** [Content & Media](https://agentstack.voostack.com/c/content-and-media)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [mfmezger](https://github.com/mfmezger)
- **Source:** https://github.com/mfmezger/ai_agent_dotfiles/tree/main/shared/skills/convert-to-markdown

## Install

```sh
agentstack add skill-mfmezger-ai-agent-dotfiles-convert-to-markdown
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Document to Markdown Converter

Convert various document formats to Markdown using markitdown and pandoc.

## Supported Formats

| Format      | Extension               | Notes                            |
| ----------- | ----------------------- | -------------------------------- |
| PDF         | .pdf                    | Text + OCR hybrid mode available |
| Word        | .docx                   | Full support                     |
| PowerPoint  | .pptx                   | Extracts text from slides        |
| Excel       | .xlsx                   | Converts tables                  |
| HTML        | .html, .htm             | Full support                     |
| EPUB        | .epub                   | Via pandoc                       |
| Images      | .jpg, .png, .gif, .webp | OCR extraction                   |
| Google Docs | URL                     | Public docs, exports as docx     |

## Usage

```bash
uvx --with markitdown python ~/.claude/skills/convert-to-markdown/scripts/convert.py INPUT
```

### Options

| Flag                     | Description                                      |
| ------------------------ | ------------------------------------------------ |
| `-o, --output PATH`      | Output path (default: input.md next to original) |
| `--mode auto\|ocr\|text` | Extraction mode (default: auto)                  |
| `--hybrid`               | PDF only: run both text + OCR, merge results     |

### Examples

```bash
# Basic conversion (saves as document.md)
uvx --with markitdown python ~/.claude/skills/convert-to-markdown/scripts/convert.py document.pdf

# Force OCR mode for scanned document
uvx --with markitdown python ~/.claude/skills/convert-to-markdown/scripts/convert.py scanned.pdf --mode ocr

# Hybrid extraction for PDFs with mixed content
uvx --with markitdown python ~/.claude/skills/convert-to-markdown/scripts/convert.py report.pdf --hybrid

# Convert Word document
uvx --with markitdown python ~/.claude/skills/convert-to-markdown/scripts/convert.py report.docx

# Convert public Google Doc
uvx --with markitdown python ~/.claude/skills/convert-to-markdown/scripts/convert.py "https://docs.google.com/document/d/DOCUMENT_ID/edit"

# Specify output location
uvx --with markitdown python ~/.claude/skills/convert-to-markdown/scripts/convert.py slides.pptx -o notes.md
```

## Mode Details

- **auto**: Smart detection - uses OCR for images, text extraction for documents
- **text**: Pure text extraction, faster but misses image content
- **ocr**: Force OCR on everything, slower but catches all visual content
- **hybrid** (PDF only): Runs both text and OCR extraction, merges results for best coverage

## Google Docs

For Google Docs conversion:

- Document must be publicly accessible (or "Anyone with link can view")
- Provide the full URL: `https://docs.google.com/document/d/DOC_ID/edit`
- Script exports as docx, then converts to markdown

## Output

- Default: Creates `filename.md` next to the original file
- Use `-o` to specify a different location
- Prints the output path when complete

## Requirements

- **markitdown**: Installed automatically via uvx
- **pandoc**: Must be installed on system (for epub, odt, rst, tex formats)
  ```bash
  brew install pandoc  # macOS
  ```

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [mfmezger](https://github.com/mfmezger)
- **Source:** [mfmezger/ai_agent_dotfiles](https://github.com/mfmezger/ai_agent_dotfiles)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-mfmezger-ai-agent-dotfiles-convert-to-markdown
- Seller: https://agentstack.voostack.com/s/mfmezger
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.