convert-documents-to-markdown

Turn hard-to-read documents into usable Markdown.

document conversion

What it does

Converts supported office, ebook, CSV, and PDF files to GitHub-Flavored Markdown.

When to use it

Use it when a task needs content from an office document, spreadsheet, presentation, ebook, or PDF that cannot be read directly.

Give it a document file; it returns GitHub-Flavored Markdown on stdout or writes it to a file.

What you provide

This skill

Firecrawl Parse

Write

Sends PDFs for hosted OCR

@firecrawl/anydoc

Execute

The anydoc CLI

Node.js 20 or newer must be available.

Firecrawl Parse is needed only for hosted OCR of scanned or image-only PDF pages.

The environment variable enables higher limits for hosted OCR; no signup is needed for the hosted OCR path.