FireCrawl Core Workflow B

Overview

Secondary workflow for FireCrawl. Complements the primary scraping workflow by focusing on structured data extraction and scheduled monitoring use cases. Use this skill when you need to extract specific fields from pages using a defined schema, set up recurring crawls for change detection, or convert an entire documentation site into a searchable knowledge base on a regular cadence.

Prerequisites

• Completed firecrawl-install-auth setup
• Familiarity with firecrawl-core-workflow-a
• Valid API credentials configured

Instructions

Step 1: Setup

Define the JSON schema describing the fields you want to extract from each page. FireCrawl's structured extraction mode uses this schema to return typed data rather than raw Markdown, which is more reliable for downstream database ingestion. Specify the target URLs or URL patterns and configure the recurrence schedule if monitoring for content changes.

// Step 1 implementation