firecrawl-agent

Name: firecrawl-agent
Author: firecrawl

byfirecrawl· 131 skills

Installs

75k

Stars

539

Forks

How to install firecrawl-agent?

firecrawl/cli/firecrawl-agent

$npx -y skills add firecrawl/cli --skill firecrawl-agent

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Use this skill

Run `npx skills use "https://github.com/firecrawl/cli" --skill "firecrawl/cli/firecrawl-agent"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.

Use the whole pack

Use the skills in "https://github.com/firecrawl/cli" that are relevant to the current task. Run `npx skills add "https://github.com/firecrawl/cli"` and select the relevant skills, then follow their instructions.

Files · 1

View on GitHub

SKILL.md

1	# firecrawl agent
2
3	AI-powered autonomous extraction. The agent navigates sites and extracts structured data (takes 2-5 minutes).
4
5	## When to use
6
7	- You need structured data from complex multi-page sites
8	- Manual scraping would require navigating many pages
9	- You want the AI to figure out where the data lives
10
11	## Quick start
12
13	```bash
14	# Extract structured data
15	firecrawl agent "extract all pricing tiers" --wait -o .firecrawl/pricing.json
16
17	# With a JSON schema for structured output
18	firecrawl agent "extract products" --schema '{"type":"object","properties":{"name":{"type":"string"},"price":{"type":"number"}}}' --wait -o .firecrawl/products.json
19
20	# Focus on specific pages
21	firecrawl agent "get feature list" --urls "<url>" --wait -o .firecrawl/features.json
22	```
23
24	## Options
25
26	\| Option \| Description \|
27	\| ---------------------- \| ----------------------------------------- \|
28	\| `--urls <urls>` \| Starting URLs for the agent \|
29	\| `--model <model>` \| Model to use: spark-1-mini or spark-1-pro \|
30	\| `--schema <json>` \| JSON schema for structured output \|
31	\| `--schema-file <path>` \| Path to JSON schema file \|
32	\| `--max-credits <n>` \| Credit limit for this agent run \|
33	\| `--wait` \| Wait for agent to complete \|
34	\| `--pretty` \| Pretty print JSON output \|
35	\| `-o, --output <path>` \| Output file path \|
36
37	## Tips
38
39	- Always use `--wait` to get results inline. Without it, returns a job ID.
40	- Use `--schema` for predictable, structured output — otherwise the agent returns freeform data.
41	- Agent runs consume more credits than simple scrapes. Use `--max-credits` to cap spending.
42	- For simple single-page extraction, prefer `scrape` — it's faster and cheaper.
43
44	## See also
45
46	- [firecrawl-scrape](../firecrawl-scrape/SKILL.md) — simpler single-page extraction
47	- [firecrawl-interact](../firecrawl-interact/SKILL.md) — scrape + interact for manual page interaction (more control)
48	- [firecrawl-crawl](../firecrawl-crawl/SKILL.md) — bulk extraction without AI

6 picks

Type

Run `npx skills use "https://github.com/firecrawl/cli" --skill "firecrawl/cli/firecrawl-agent"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.

Use the skills in "https://github.com/firecrawl/cli" that are relevant to the current task. Run `npx skills add "https://github.com/firecrawl/cli"` and select the relevant skills, then follow their instructions.

firecrawl-agent

How to install firecrawl-agent?

Related

firecrawl-agent

How to install firecrawl-agent?

Related