firecrawl agent
SkillWeb & browsingThis 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.
No other account needed.
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
--waitfor inline results; omit it only when you want a job ID to poll later (see Job IDs). - Use
--schemafor predictable, structured output — otherwise the agent returns freeform data. - Agent runs consume more credits than simple scrapes. Use
--max-creditsto cap spending. - For simple single-page extraction, prefer
scrape— it's faster and cheaper.
See also
- firecrawl-scrape — simpler single-page extraction
- firecrawl-interact — scrape + interact for manual page interaction (more control)
- firecrawl-crawl — bulk extraction without AI
- firecrawl-build-scrape — building structured extraction into an app instead of running it here
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