Firecrawl Parse

Turns local PDFs, DOCXs, spreadsheets, and other documents into clean markdown files on disk. The smart move here is always piping to `.firecrawl/` instead of stdout since parsed docs can easily hit hundreds of KB and destroy your context window. Beyond basic extraction, you get AI summaries and question answering built in, which is handy when you just need specific info from a dense research paper or contract. Supports files up to 50MB and costs roughly one credit per PDF page. If you're working with URLs instead of local files, reach for firecrawl-scrape. The tooling is straightforward and the output format makes it easy to grep or incrementally process results without loading everything at once.