skills.rest
fairchild
fairchildCOMMUNITY
Explore all skills by this author →
GitHub

firecrawl-agent

Extract structured JSON data from multi-page websites using autonomous Firecrawl agent runs.

1|Updated Nov 11, 2012
Search Tags:#structured data#data extraction#firecrawl#json#web scraping#web agent#pricing extraction
One-click install
npx skills add https://github.com/fairchild/dotfiles --skill firecrawl-agent-fairchild
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: firecrawl-agent
Source: https://github.com/fairchild/dotfiles/tree/main/agents/shared/first-party-skills/firecrawl-agent
Command: npx skills add https://github.com/fairchild/dotfiles --skill firecrawl-agent-fairchild

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Manually navigating complex multi-page websites to collect structured data like pricing tiers, product listings, or directory entries is slow and error-prone. This Skill delegates that navigation to the Firecrawl agent, which autonomously explores a site and returns the requested data as structured JSON. ## Core Features & Use Cases - Autonomous multi-page extraction: The agent navigates the site on its own to find where the requested data lives, without you specifying every page. - Schema-driven output: Pass a JSON schema via --schema or --schema-file to get predictable, structured results instead of freeform data. - Cost and model controls: Choose between spark-1-mini and spark-1-pro models and cap spending with --max-credits. - Use Case: Ask for all pricing tiers from a SaaS website; the agent crawls the relevant pages and writes a structured JSON file to .firecrawl/pricing.json. ## Quick Start Ask the agent to extract all pricing tiers from a target website and save the structured JSON output to a local file using the firecrawl agent command with the --wait flag.

Frequently Asked Questions about firecrawl-agent

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract structured data from a website as JSON?▼

Run firecrawl agent with a natural-language prompt describing the data, add --wait to get results inline, and use -o to write output to a file. Pass --schema with a JSON schema to enforce a predictable structure on the extracted data.

When should I use firecrawl agent instead of firecrawl scrape?▼

Use the agent when data is spread across multiple pages and you want the AI to navigate the site autonomously. For simple single-page extraction, scrape is faster and consumes fewer credits.

How do I control the cost of a Firecrawl agent run?▼

Agent runs consume more credits than simple scrapes. Use the --max-credits option to cap spending for a run, and choose the spark-1-mini model instead of spark-1-pro for cheaper extraction.

Why does firecrawl agent return a job ID instead of data?▼

Without the --wait flag, the command starts an asynchronous job and returns only its ID. Always include --wait so the command blocks until the agent completes and returns the extracted results inline.

Can I limit which pages the Firecrawl agent visits?▼

Yes, use the --urls option to provide starting URLs that focus the agent on specific pages. This narrows the navigation scope and can reduce both runtime and credit consumption.

Related Skills

Explore More Data & Analytics Skills→
ZJU-REALZJU-REAL
195

firecrawl-agent

Extract structured JSON data from multi-page websites via the Firecrawl CLI.

Official
Advanced
KaranKathur06KaranKathur06

data-pipeline

Build scheduled ETL workflows that extract, transform, and load data into analytics destinations.

Community
Intermediate
MantisWareMantisWare

reduce

Extract atomic claims with provenance from unstructured text sources.

Community
Intermediate
firecrawlfirecrawl
616

firecrawl

Search, scrape, crawl, and interact with websites via the Firecrawl CLI.

Official
Intermediate