firecrawl-agent

Set it loose on a website and a few minutes later it comes back with the specific facts you asked for, gathered from however many pages it had to visit.

WHEN TO USE

SCOPE

USE FOR

Pull every pricing tier off a site into one tidy data file.
Collect a product catalog's names and prices without visiting each page yourself.
Extract data from a site whose layout needs clicking or scrolling to reveal it.
Check how far along a long extraction has got, or cancel it.

NOT FOR

Pulling one simple page's content — scrape does that faster and cheaper.

This is a saved copy of the skill's SKILL.md instructions. It may differ from the upstream file or the version you install.

In this document (5)

firecrawl agent

AI-powered autonomous extraction. The agent navigates sites and extracts structured data (takes 2-5 minutes).

Quick start

# Extract structured data
firecrawl agent "extract all pricing tiers" --wait --json -o .firecrawl/pricing.json

# With a JSON schema for structured output
firecrawl agent "extract products" --schema '{"type":"object","properties":{"name":{"type":"string"},"price":{"type":"number"}}}' --wait --json -o .firecrawl/products.json

# Focus on specific pages
firecrawl agent "get feature list" --urls "<url>" --wait --json -o .firecrawl/features.json

Run firecrawl agent --help for the full option list.

Done when: the output file contains valid JSON answering the request — or a job ID was intentionally returned for later polling.

Job IDs

Omitting --wait returns a job ID. A UUID positional argument is auto-detected as a status check:

# Check once (equivalent to adding --status)
firecrawl agent "<job-id>"

# Wait on an existing job, polling every 10 seconds for up to 5 minutes
firecrawl agent "<job-id>" --wait --poll-interval 10 --timeout 300

# Cancel an active job
firecrawl agent "<job-id>" --cancel

Tips

Use --wait for inline results; omit it only when you want a job ID to poll later (see Job IDs).
Use --schema for predictable, structured output — otherwise the agent returns freeform data.
Agent runs consume more credits than simple scrapes. Use --max-credits to cap spending.
For simple single-page extraction, prefer scrape — it's faster and cheaper.

Check selected tools if a picker appears; Claude Code may be unchecked under Additional agents. ↑/↓ moves, Space toggles selections, Enter confirms.
Without a tool picker, check Installing to: for your intended tool. Stop if it names a different tool.
If asked, choose Symlink (Recommended) for shared files or Copy to all agents for separate copies; review the summary before confirming installation.
Install the find-skills skill? defaults to Yes, adding another skill for all projects. Choose No if you don't want that extra installation.

Skills CLI 1.7.2 sends install data to skills.sh by default, including the source, skill names, target tools and file details; GitHub sources are reported only when GitHub confirms the repository is public, while other remote sources can also be reported. Confirmed-public GitHub sources also trigger a security-audit request. Before installing, set the environment variable DO_NOT_TRACK=1 or DISABLE_TELEMETRY=1 to disable both.

npx skills add firecrawl/cli --skill firecrawl-agent firecrawl-alexandria firecrawl-crawl firecrawl-developer-index firecrawl-download firecrawl-interact firecrawl-map firecrawl-research-index firecrawl-scrape firecrawl-search --full-depth

It installs 10 skills: this one and the 9 it relies on, listed below. Once these skills are installed where Claude Code loads them, their descriptions help Claude decide when to use them.

What's inside

Files included with this skill.

View on GitHub

firecrawl agent

Quick start

Job IDs

Tips

See also

Local tool required

What's inside

firecrawl-agent

firecrawl agent

Quick start

Job IDs

Tips

See also

Local tool required

What's inside

More skills

MCP keyword matches