skills.rest
yuma588
yuma588COMMUNITY
Explore all skills by this author →
GitHub

firecrawl

Automate synchronous and asynchronous web crawling with nested parameters.

2|Updated Jan 7, 2026
Search Tags:#automation#asynchronous#sitemap#data-extraction#web-scraping#crawling#multi-mode
One-click install
npx skills add https://github.com/yuma588/skill-gallery --skill firecrawl-yuma588
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: firecrawl
Source: https://github.com/yuma588/skill-gallery/tree/main/skills/firecrawl
Command: npx skills add https://github.com/yuma588/skill-gallery --skill firecrawl-yuma588

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

多功能网页抓取和数据提取需求通常需要多工具协作、繁琐的参数对接与流程管理。Firecrawl 将抓取、搜索、网站地图获取和异步爬取整合为一个统一入口，简化工作流。

Core Features & Use Cases

  • 同步抓取: 直接获取网页内容与结构化数据。
  • 搜索与地图获取: 快速在目标站点内搜索信息并生成网站地图。
  • 异步爬取与提取: 支持 crawl 与 extract，并返回 job_id 以便后续跟踪。
  • 用例示例: 需要对大量页面提取标题、链接和元数据时，使用 firecrawl 的 crawl/extract 组合，批量完成并可在一个任务中统一处理结果。

Quick Start

给定一个目标页面 URL，选择一个模式（例如 crawl），并传入嵌套参数结构以执行异步抓取，随后通过返回的 job_id 进行状态查询。

Frequently Asked Questions about firecrawl

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

FAQPage Schema
How do I automate web scraping and data extraction across multiple pages?▼

You can automate web scraping and data extraction by using asynchronous crawling modes that process nested parameters across diverse sites. The system returns a job_id for tracking, allowing you to batch extract titles, links, and metadata efficiently.

What is the difference between synchronous fetch and asynchronous crawling?▼

Synchronous fetch returns immediate results directly from the target page, while asynchronous crawling issues a job_id to monitor large-scale extraction tasks. You use sync for quick single-page retrieval and async for mapping and extracting data across entire sites.

How do I generate a sitemap for a target website?▼

You generate a sitemap by utilizing the built-in sitemap mapping mode. This function scans the target website to map its structure, enabling you to identify accessible pages before initiating a full crawl or data extraction.

Can I extract structured data like titles and metadata from multiple URLs at once?▼

Yes, you can extract structured data from multiple URLs by configuring the crawl and extract modes with nested parameters. This allows you to process large volumes of pages and receive structured outputs like titles, links, and metadata in a unified task.

Do I need external dependencies to perform web crawling and site searches?▼

No external dependencies are required to perform web crawling, site searches, or sitemap mapping. The tool integrates these multi-mode capabilities into a single entry point, simplifying your workflow without needing additional parameter docking tools.

Related Skills

Explore More Software Engineering Skills→
jscraikjscraik
8

cf-crawl

Initiate, monitor, and export website crawls via the Cloudflare Browser Rendering API.

Community
Advanced
TIAN0517TIAN0517

web-search

Return structured web search results with URLs, titles, and metadata.

Community
Basic
TIAN0517TIAN0517

web-reader

Extract page title, HTML, text, and metadata from URLs via page_reader.

Community
Intermediate
Wike-CHIWike-CHI
2

web-content-fetcher

Fetch blocked webpage content as markdown via r.jina.ai, markdown.new, or defuddle.md.

Community
Basic