firecrawl-crawl

Crawls websites following links to bulk extract content from multiple pages.

2|Updated Mar 29, 2015
One-click install
npx skills add https://github.com/ovisan/dotfiles --skill firecrawl-crawl-ovisan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: firecrawl-crawl
Source: https://github.com/ovisan/dotfiles/tree/main/.grok/skills/firecrawl-crawl
Command: npx skills add https://github.com/ovisan/dotfiles --skill firecrawl-crawl-ovisan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Extracting content from many pages on the same website one URL at a time is slow and repetitive. This Skill automates bulk extraction by crawling a site or site section, following links up to a configurable depth, and collecting content from all matching pages in one operation. ## Core Features & Use Cases - Bulk Site Crawling: Follow links from a starting URL with configurable depth limits, page limits, and concurrency controls. - Path Filtering: Scope crawls with include/exclude path patterns so you only extract the sections you need, such as everything under /docs. - Async Job Management: Run crawls asynchronously with job IDs, or wait with progress reporting until the crawl completes. - Use Case: You need the entire documentation section of a vendor site for offline reference. Run a crawl scoped to /docs with a page limit, wait for completion, and save the structured JSON output locally. ## Quick Start Ask the AI to crawl a website's docs section with firecrawl, limiting it to 50 pages under /docs, and save the extracted content to a local JSON file.

Frequently Asked Questions about firecrawl-crawl

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

FAQPage Schema
How do I crawl an entire website with firecrawl?

Run firecrawl crawl with the target URL, adding --wait to block until completion and -o to save results to a JSON file. Use --limit and --max-depth to control how many pages are crawled and how deep links are followed.

How to extract all pages under a specific path like /docs?

Use the --include-paths option with firecrawl crawl to restrict the crawl to URLs matching that path, for example --include-paths /docs. This prevents crawling the entire site when you only need one section.

What is the difference between firecrawl crawl, scrape, and map?

Scrape extracts a single page, map discovers URLs on a site without extracting content, and crawl follows links to bulk extract many pages. A typical workflow is map first to discover URLs, then crawl when you need content from all of them.

Does firecrawl crawl run asynchronously?

Yes, without the --wait flag the crawl returns a job ID immediately for async polling. You can check status later with firecrawl crawl followed by the job ID, or add --wait and --progress to block until completion.

Why is my firecrawl crawl consuming too many credits?

Crawls consume credits per page extracted, so unscoped crawls of large sites get expensive. Use --include-paths, --limit, and --max-depth to narrow scope, and check firecrawl credit-usage before starting large crawls.