skilld
All skills
firecrawl avatar

/firecrawl-parse

@509dd9c official
by firecrawlfirecrawl/cli643 stars
110

Convert a local file (PDF, DOCX, XLSX, HTML, …) to markdown, or answer questions about its content. Use whenever the input is a file path, not a URL.

Ask your Agent

Use this Skill: https://skilld.dev/gh/firecrawl/cli/firecrawl-parse

This session only. Nothing lands on disk.

SKILL.md

≈42 tokens always: the name and description. ≈376 when used: this file.

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.

Tips

  • Quote paths with spaces: firecrawl parse "./My Doc.pdf" -o .firecrawl/mydoc.md.
  • Max upload size: 50 MB per file.
  • Credits: ~1 per PDF page; HTML is 1 flat.
  • Check .firecrawl/ before re-parsing the same file.
  • To check your credit balance (recommended for batch processing and similar workflows), use firecrawl credit-usage (requires authentication).

See also

Source: SKILL.md on GitHub

Third-party checks

No alerts16d3 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    The skill facilitates the conversion of local files to markdown or allows querying their content using the Firecrawl CLI. It introduces an indirect prompt injection surface when handling untrusted documents, as the output is subsequently read by the agent without sanitization or boundary isolation.

  • Socket16d

    No alerts

  • Snyk16d

    Risk: LOW · No issues

Provenance

Signed by skilld at 509dd9c. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 13 hours ago.

Activeupdated last month

Capability

What it can do
Runs commands
All 2 allowed tools
Bash(firecrawl *)Bash(npx firecrawl-cli *)

Topics

  • CLI
  • firecrawl
  • pdf
  • docx
  • document-parsing
  • markdown
  • extraction
  • local-files

README badge

README badge for firecrawl/cli/firecrawl-parse

What it does

Converts local documents (PDF, DOCX, XLSX, HTML, and others) to clean markdown saved to disk, with optional AI-powered summaries and question-answering. Use this when parsing files on your machine rather than scraping URLs, and always save output to `.firecrawl/` to avoid bloating context.

Generated from the current SKILL.md.

Frequently asked

What file types does this skill support?
PDF, DOCX, DOC, ODT, RTF, XLSX, XLS, and HTML/HTM/XHTML. Maximum file size is 50 MB per upload.
Should I use this for URLs or local files?
Use this skill only for local files on disk. For URLs, use the firecrawl-scrape skill instead.
Can this skill summarize or answer questions about a document?
Yes. Use the `-S` flag to generate an AI summary, or the `-Q` flag to ask a specific question about the document's content.
Why should I always use the -o flag to save output?
Parsed documents can be hundreds of KB. Saving to disk with `-o .firecrawl/output.md` prevents large content from bloating your agent's context; you can then read the file incrementally as needed.
How much does parsing cost in credits?
PDF parsing costs approximately 1 credit per page; HTML files cost 1 credit flat. Use `firecrawl credit-usage` to check your balance before batch processing.

Generated from the current SKILL.md. These answers refresh after source changes.