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.

skills.sh installs: 51.5K
GitHub stars: 682
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add firecrawl/cli --skill firecrawl-parse --agent claude-code

Installs into .claude/skills of the current project.

Files

firecrawl parse

Turn a local document into clean markdown on disk. Supports PDF, DOCX, DOC, ODT, RTF, XLSX, XLS, HTML/HTM.

Quick start

Always save to .firecrawl/ with -o — parsed docs can be hundreds of KB and blow up context if streamed to stdout. Add .firecrawl/ to .gitignore.

mkdir -p .firecrawl

# File → markdown
firecrawl parse ./paper.pdf -o .firecrawl/paper.md

# AI summary
firecrawl parse ./paper.pdf -S -o .firecrawl/paper-summary.md

# Ask a question about the doc
firecrawl parse ./paper.pdf -Q "What are the main conclusions?" \
  -o .firecrawl/paper-qa.md

Then read the output incrementally with head, grep, or rg.

Run firecrawl parse --help for the full option list.

Done when: the markdown, summary, or answer is written under .firecrawl/ and you have inspected it with bounded reads.