skills.rest
ovisan
ovisanCOMMUNITY
Explore all skills by this author →
GitHub

firecrawl-agent

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

2|Updated Mar 29, 2015
Search Tags:#automation#structured data#data extraction#pricing#firecrawl#json#web scraping
One-click install
npx skills add https://github.com/ovisan/dotfiles --skill firecrawl-agent-ovisan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: firecrawl-agent
Source: https://github.com/ovisan/dotfiles/tree/main/.grok/skills/firecrawl-agent
Command: npx skills add https://github.com/ovisan/dotfiles --skill firecrawl-agent-ovisan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Manually scraping complex multi-page websites to gather structured data like pricing tiers, product listings, or directory entries is slow and error-prone. This Skill automates that process by letting an autonomous agent navigate the site and return the data as structured JSON. ## Core Features & Use Cases - Autonomous Multi-Page Extraction: The agent navigates complex sites on its own to find and extract the data you describe. - Schema-Guided Output: Provide 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: You need every pricing tier from a SaaS competitor's site. Run the agent with a prompt like "extract all pricing tiers" and receive a clean JSON file with the results. ## Quick Start Ask the agent to extract all pricing tiers from a target website and save the structured JSON output to a 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 the firecrawl agent command with a natural language prompt describing the data, such as "extract all pricing tiers", and add the --wait flag to get results inline. Use -o to save the output to a JSON file.

How do I get predictable structured output from web extraction?▼

Pass a JSON schema with the --schema flag or reference a file with --schema-file. The agent then returns data matching your defined fields instead of freeform results.

When should I use the agent instead of a simple scrape?▼

Use the agent for complex multi-page sites where the data location is unknown and navigation is required. For single-page extraction, the scrape command is faster and consumes fewer credits.

How do I control costs when running web extraction agents?▼

Set a spending cap with the --max-credits option to limit consumption per run. Agent runs cost more credits than simple scrapes, so capping is recommended for large sites.

Why did my extraction return a job ID instead of data?▼

Without the --wait flag, the command returns a job ID immediately rather than waiting for completion. Always include --wait to receive the extracted results inline.

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
browser-actbrowser-act
5.5k

walmart-product-detail

Extract full structured product data from Walmart product detail pages.

Official
Intermediate
TeamWiseFlowTeamWiseFlow
8.4k

intel-gathering

Monitor social and web sources to extract and summarize new business intelligence.

Official
Intermediate
orthogonal-shorthogonal-sh
12

scrape

Extracts structured data from web pages and URLs via modular scraping workflows.

Official
Advanced