firecrawl agent

SkillWeb & browsing

This skill gives your AI the ability to work with the web: it can scrape pages, run web searches, and browse site content. Once added, your agent can gather information from websites for you, whether you need the text of a specific page or results from a search.

Available today. Use it from your connected AI after setup.

After adding it, ask your agent to scrape a web page, search the web, or browse a site you are interested in. It is built on the Firecrawl command line tool.

Then ask your AI: use the firecrawl agent skill

What your AI can do with it

  • Scrape web pages to read their content
  • Search the web for information
  • Browse a site's pages to explore what is there

What this skill tells your AI

The instructions your AI receives, as published by firecrawl/cli in skills/firecrawl-agent/SKILL.md and read by ahel’s review.

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.

See also

Signals

GitHub stars
629
Forks
98
Last commit
Sep 2026
Installs
79k installs
Advanced
Catalog kind
skill
Gateway key
firecrawl-agent
Source
github.com/firecrawl/cli