firecrawl-parse Skill: Turn PDFs, Word and Excel Files Into Markdown
Makes your coding assistant turn a local PDF, Word, Excel or HTML file into markdown, or answer questions about it, with Firecrawl.
- Installs
- 51.3K
- on skills.sh
- Stars
- 676
- on GitHub
- Updated
- Oct 2026
- last repo commit
firecrawl-parse teaches your assistant to run firecrawl parse ./file.pdf. It supports PDF, DOCX, DOC, ODT, RTF, XLSX, XLS and HTML files and writes markdown to .firecrawl/. It can also write an AI summary or answer a question about the document.
The skill gives a 50 MB upload limit per file and says parsing costs about 1 credit per PDF page. You must install the Firecrawl CLI and sign in.
Good for
- Developers who need a PDF or spreadsheet turned into text for a coding task
- Researchers who want a summary or answers from a long paper
- Anyone with a file path rather than a URL
Install firecrawl-parse
Claude Code
- 1
Copy this prompt.
Install the firecrawl-parse skill in Claude Code. Run this command: npm install -g firecrawl-cli@latest firecrawl login --browser npx skills add https://github.com/firecrawl/cli --skill firecrawl-parse -a claude-code Then check that it loaded and tell me how to use it.
- 2
Paste it into Claude Code. It shows the change and asks before running it.
Requires Node.js, A Firecrawl account (or the keyless free tier).
The skill only gives your assistant instructions. The Firecrawl command line tool does the work, so install it and sign in first. Sign in before you use it. The skill gives a 50 MB upload limit per file. The one-command route installs the CLI, signs you in through the browser and adds the core and workflow skills for every editor it detects, not just this skill.
From the vendor's docs. Source.
What's in the skill
When it loads
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.
Sections in SKILL.md
- Quick start
- Tips
- See also
Key facts
- Author
- firecrawl org
- Repo
- firecrawl/cli
- Installs on skills.sh
- 51,263 as of 2026-11-02
- GitHub stars
- 676 for the whole firecrawl/cli repo, 2026-11-02
- Last commit to the repo
- 2026-10-28
- What is inside
- 1 file (SKILL.md)
- Related skills
- firecrawl-scrape
- skills.sh audits
- Gen Agent Trust Hub pass, Socket pass, Snyk pass (2026-11-02)
What it includes
Converts a local file to markdown
Supports PDF, DOCX, DOC, ODT, RTF, XLSX, XLS and HTML or HTM. Always save with -o, because parsed documents can be hundreds of KB.
Try: “Parse ./report.pdf into markdown and list the key findings.”
Runs code ·
firecrawl parse ./file -o .firecrawl/file.mdWrites an AI summary of the document
Saved as a markdown file next to the other outputs.
Write ·
-SAnswers a question about the document
Example in the skill: ask for the main conclusions of a paper.
Write ·
-Q "<question>"Checks credits before a batch of files
Needs an account. The skill recommends it for batch work.
Runs code ·
firecrawl credit-usage
From the official docs
Permissions
Medium risk
This skill sends the local files you parse to Firecrawl and spends credits per page. Only parse documents you are allowed to share.
What it can do
- Read your data
- Create and change things
- Delete things
- Read-only mode
Watch out for
Your local files go to Firecrawl
The skill gives a 50 MB upload limit per file, so parsing sends the document to a third party. Do not parse confidential files you cannot share. github.com
Parsing costs credits per page
About 1 credit per PDF page and 1 for HTML. Check firecrawl credit-usage before a batch. github.com
Web pages can try to steer your assistant
The skill's own security note calls fetched web content untrusted and says it may contain prompt injection. Do not let the assistant follow instructions it finds on a page. github.com
Setup installs a global npm package
The CLI is installed with npm install -g. The one-command setup also adds skills to every coding editor it detects, so use the single-skill route if you want only this one. github.com
The CLI sends anonymous usage data
The README says it collects the CLI version, OS, Node.js version and which dev tools it detects during sign-in. Set FIRECRAWL_NO_TELEMETRY=1 to turn it off. github.com
Security advisories
No published security advisories as of Nov 2, 2026.
Technical details
| Turning on read-only | No read-only mode. The skill runs CLI commands that spend credits and write files. |
|---|---|
| Talks to | Firecrawl's API, or your own server if you set --api-url. The local files you parse (the skill gives a 50 MB upload limit per file). Page content the assistant reads goes to your AI provider as part of the chat |
| Sign-in and keys | Browser sign-in stores credentials in the CLI. You can set FIRECRAWL_API_KEY instead. |
| Scopes |
|
Questions
What does firecrawl-parse do?
It makes your assistant convert a local file to markdown with the Firecrawl CLI. It supports PDF, DOCX, DOC, ODT, RTF, XLSX, XLS and HTML, and can add a summary or answer a question.
How do I install firecrawl-parse?
Use the install box at the top of this page. You need the Firecrawl CLI as well as the skill. The box includes a browser sign-in step, because the docs do not say whether parse works without one. The one-command route installs the whole core skill set.
Do I need a Firecrawl account?
The docs do not say. The install rules list search, scrape and interact as working without an account, and name crawl, map, download, agent, monitor, credit-usage and the feedback commands as needing one. Parse is in neither list, and its SKILL.md has no prerequisite note. Sign in with the browser or an API key to be safe.
How big can the file be, and what does it cost?
The SKILL.md gives a 50 MB upload limit per file. It says parsing costs about 1 credit per PDF page, and HTML is 1 credit flat.
Are my files sent to a third party?
The skill talks about uploading files, with a 50 MB limit per file, so treat parsing as sending the file to Firecrawl. Do not parse documents you are not allowed to share.
Is firecrawl-parse safe to use?
It reads files you point it at and writes markdown to .firecrawl/. Choose files yourself, and read the output in pieces, because a document can contain text that tries to steer the assistant.
firecrawl-parse or firecrawl-scrape?
Use parse when the input is a file path. The SKILL.md describes scrape as the same idea for URLs.
Skill or Firecrawl MCP server?
They are two routes to Firecrawl. firecrawl-parse is a SKILL.md that tells the assistant to run the Firecrawl CLI in your shell. The skill only allows Bash(firecrawl *) and Bash(npx firecrawl-cli *), so it needs an assistant that can run shell commands. The Firecrawl MCP server and the local Firecrawl MCP server give your client Firecrawl as tools it calls directly, with no skill involved. The README describes firecrawl setup mcp for adding the MCP server to your editors. You can use either route, or both.
Information
updated Nov 2, 2026
- Repository
- firecrawl/cli
- Folder
skills/firecrawl-parse
Sources
Docs, issue trackers and discussions this page is built from.
Show all 5Hide
- Firecrawl CLI install rules · github.com
- firecrawl/cli README · github.com
- skills CLI commands · github.com
- firecrawl-parse SKILL.md · github.com
- Firecrawl security rules · github.com