firecrawl-parse

Convert local PDF, DOCX, XLSX, and HTML files into markdown on disk.

Updated Jul 16, 2026
One-click install
npx skills add https://github.com/The-Focus-AI/walking-thoughts --skill firecrawl-parse-the-focus-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: firecrawl-parse
Source: https://github.com/The-Focus-AI/walking-thoughts/tree/main/.agents/skills/firecrawl-parse
Command: npx skills add https://github.com/The-Focus-AI/walking-thoughts --skill firecrawl-parse-the-focus-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Reading content out of local documents like PDFs, Word files, and spreadsheets is tedious and often produces messy output. This Skill converts those files into clean markdown saved to disk, so the content can be searched, summarized, or queried without loading the entire document into context. ## Core Features & Use Cases - Local file to markdown conversion: Parse PDF, DOCX, DOC, ODT, RTF, XLSX, XLS, and HTML files into well-formatted markdown written to a specified output path. - AI summaries and Q&A: Generate a summary of a document with the -S flag or ask a specific question about its content with -Q. - Context-safe output handling: Results are saved to a .firecrawl/ directory so large parsed documents can be read incrementally with head, grep, or rg instead of flooding the conversation. - Use Case: A user drops a 40-page research PDF into the project and asks for its main conclusions; the Skill parses it to .firecrawl/paper.md and answers the question without dumping the full text into context. ## Quick Start Ask the assistant to parse a local file such as "parse ./report.pdf and save the markdown output", optionally requesting a summary or a specific question about its contents.

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 parsed markdown is written to disk so you can read it 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 on disk; for URLs, 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 path on your computer. Use scrape when the source is a URL. Parse is preferred for local files because it produces structured markdown suited for downstream tasks.

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; check your balance with firecrawl credit-usage before batch jobs.

How do I get a summary of a PDF without reading the whole file?

Add the -S flag to generate an AI summary, for example firecrawl parse ./paper.pdf -S -o .firecrawl/paper-summary.md. You can also ask a targeted question with -Q followed by your prompt.