Description
firecrawl-parse is a skill for converting local documents into clean markdown saved to disk. It supports PDF, DOCX, DOC, ODT, RTF, XLSX, XLS and HTML files, which the skill lists as eight or more formats. The skill's quick start says to always save output to a .firecrawl folder with the -o option, because parsed documents can run to hundreds of kilobytes and would fill the agent's context if streamed to stdout, and it advises adding .firecrawl to .gitignore. It also has AI-powered options: a -S flag for summarization and a -Q flag for asking questions of the parsed document. It is installed with npx skills from the firecrawl/cli repository.…
Highlights
- Converts PDF, DOCX, DOC, ODT, RTF, XLSX, XLS and HTML
- Clean markdown saved to disk
- Summarization with -S
- Question answering with -Q
- Saves output to .firecrawl
Ratings & Reviews
No ratings yet
Be the first to rate firecrawl-parse.
People also visit
nutrient-document-processing
Process, convert, OCR, extract, redact, sign, and fill documents
firecrawl-parse FAQ
What file types can it parse?
PDF, DOCX, DOC, ODT, RTF, XLSX, XLS and HTML files.
Where does the output go?
To disk, in a .firecrawl folder, via the -o option. The skill says not to stream large output.
Can it summarize or answer questions?
Yes. The -S flag summarizes and the -Q flag answers a question from the parsed document.
Should I commit the output?
The skill advises adding .firecrawl to .gitignore.
How do I install it?
Run npx skills add https://github.com/firecrawl/cli --skill firecrawl-parse.
What are the best firecrawl-parse alternatives?
Popular alternatives to firecrawl-parse include nano-pdf, obsidian and nutrient-document-processing. See all firecrawl-parse alternatives