skills.rest
leonardoacosta
leonardoacostaCOMMUNITY
Explore all skills by this author →
GitHub

firecrawl-agent

Extract structured JSON data from websites using autonomous multi-page navigation.

Updated Aug 2, 2026
Search Tags:#data extraction#firecrawl#web scraping#web crawling#autonomous agent#structured json
One-click install
npx skills add https://github.com/leonardoacosta/agents --skill firecrawl-agent-leonardoacosta
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: firecrawl-agent
Source: https://github.com/leonardoacosta/agents/tree/main/skills/firecrawl-agent
Command: npx skills add https://github.com/leonardoacosta/agents --skill firecrawl-agent-leonardoacosta

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Single-page scrapers cannot gather data spread across many pages of a site, such as pricing tiers or product catalogs. This Skill runs an autonomous extraction agent that navigates a website and returns structured JSON matching your request or schema. ## Core Features & Use Cases - Autonomous multi-page extraction: Describe the data you want in natural language and the agent navigates the site to collect it. - Schema-driven output: Pass a JSON schema with --schema to get predictable, structured results instead of freeform data. - Async job management: Omit --wait to receive a job ID, then poll, wait on, or cancel the job later. - Use Case: Extract every pricing tier from a SaaS website into .firecrawl/pricing.json, or pull a product catalog with name and price fields into a structured JSON file. ## 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 an entire website?▼

Run firecrawl agent with a natural language prompt describing the data, plus --wait and --json to get inline results. Add --schema with a JSON schema to enforce a predictable output structure, and -o to write results to a file.

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

Use the agent when data spans multiple pages and requires autonomous navigation, such as full pricing pages or product catalogs. For single-page extraction, scrape is faster and consumes fewer credits.

How do I check the status of a firecrawl agent job?▼

Pass the job ID as a positional argument to firecrawl agent, which auto-detects it as a status check. Add --wait with --poll-interval and --timeout to block until the job finishes, or use --cancel to stop it.

How can I control credit usage for web extraction agents?▼

Agent runs consume more credits than simple scrapes because they navigate multiple pages. Use the --max-credits flag to cap spending on any given run.

Why does my extraction return unstructured freeform data?▼

Without a --schema argument, the agent returns freeform data based on its interpretation of your prompt. Provide a JSON schema defining the properties and types you need to get consistent, structured output.

Related Skills

Explore More Data & Analytics Skills→
firecrawlfirecrawl
616

firecrawl-agent

Extract structured JSON data from websites via autonomous multi-page navigation.

Official
Intermediate
KaranKathur06KaranKathur06

data-pipeline

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

Community
Intermediate
reomgitreomgit

scrape

Extract text and structured data from web pages using Bash, Read, and AskUserQuestion tools.

Community
Intermediate
taiyousan15taiyousan15

firecrawl

Extract web content via Firecrawl API through URLs, crawls, and keyword searches.

Community
Intermediate