firecrawl-parse

Converts local PDF, DOCX, XLSX, and HTML files into markdown saved to disk.

Updated Apr 18, 2026
One-click install
npx skills add https://github.com/webdevarif/claude-skills --skill firecrawl-parse-webdevarif
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: firecrawl-parse
Source: https://github.com/webdevarif/claude-skills/tree/main/firecrawl-parse
Command: npx skills add https://github.com/webdevarif/claude-skills --skill firecrawl-parse-webdevarif

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Reading content out of local documents like PDFs, Word files, and spreadsheets is tedious and error-prone, and dumping raw output into a chat context wastes tokens. This Skill converts any local file into clean markdown written to disk, so you can inspect, search, and reuse the content incrementally. ## Core Features & Use Cases - Local File Parsing: Converts PDF, DOCX, DOC, ODT, RTF, XLSX, XLS, and HTML files into well-formatted markdown saved under .firecrawl/. - AI Summaries and Q&A: Generates summaries with -S or answers specific questions about a document with -Q, without reading the whole file yourself. - Use Case: A user drops a 200-page research PDF and asks for the main conclusions. Run firecrawl parse ./paper.pdf -Q "What are the main conclusions?" -o .firecrawl/paper-qa.md and read the concise answer from disk instead of loading the entire document. ## Quick Start Ask the assistant to parse a local file, for example: "Parse ./report.pdf and save the markdown output, then summarize its key findings."

Frequently Asked Questions about firecrawl-parse

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert a PDF to markdown from the command line?

Run firecrawl parse with the file path and an output flag, for example firecrawl parse ./paper.pdf -o .firecrawl/paper.md. The command writes clean markdown to disk, which you can then read incrementally with head, grep, or rg.

What file formats can firecrawl parse handle?

It supports PDF, DOCX, DOC, ODT, RTF, XLSX, XLS, and HTML/HTM/XHTML files. The source must be a local file path; for URLs you should use the firecrawl scrape command instead.

Should I use firecrawl parse or scrape for a document?

Use parse when the source is a local file on disk, and scrape when the source is a URL. Parse is optimized for local document formats like PDF and DOCX and produces structured markdown output.

What is the maximum file size for firecrawl parse?

The maximum upload size is 50 MB per file. Credit usage is roughly one credit per PDF page, while HTML files cost one flat credit, so check your balance with firecrawl credit-usage before batch jobs.

How do I ask questions about a PDF without reading the whole file?

Use the -Q flag with your question, for example firecrawl parse ./paper.pdf -Q "What are the main conclusions?" -o .firecrawl/qa.md. The answer is written to the output file, and -S similarly generates an AI summary.