firecrawl-search

Search via self-hosted Firecrawl and extract full-page content from results.

3|Updated Jul 5, 2021

Search Tags:#automation #firecrawl #web-search #scrape #self-hosted #full-page-content

Ready to run

npx skills add https://github.com/iAziz786/dotfiles --skill firecrawl-search-iaziz786

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: firecrawl-search
Source: https://github.com/iAziz786/dotfiles/tree/main/.agents/skills/firecrawl-search
Command: npx skills add https://github.com/iAziz786/dotfiles --skill firecrawl-search-iaziz786

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Web search requires retrieving relevant pages and, optionally, the full content of each result for context, which this Skill enables via a self-hosted Firecrawl instance at localhost:3002.

Core Features & Use Cases

Real search results with optional full-page content extraction
Works with a self-hosted Firecrawl service to fetch and format results
Useful for researching topics, gathering sources, and keeping content up-to-date

Quick Start

Run a search query with firecrawl and optionally scrape full page content for each result.

Frequently Asked Questions about firecrawl-search

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

FAQPage Schema

How do I extract full-page content from web search results when I don't have a starting URL?▼

Web search with full-page extraction uses a self-hosted Firecrawl instance to return structured search results and optionally scrape the complete content of each page. This is useful for researching topics and gathering sources when a URL is not known.

What do I need to run a self-hosted Firecrawl instance for web scraping?▼

To run a self-hosted Firecrawl instance for web scraping, you need a running Firecrawl service accessible at localhost:3002. The search commands interact with this local service to fetch queries and format optional full-page content extraction.

Can I scrape full-page content from recent news articles across multiple topics?▼

Scraping full-page content from recent news articles is supported by querying topics through the Firecrawl service. It returns real search results and can extract the full page content for each result to provide comprehensive context.

How does a self-hosted Firecrawl search differ from standard web search APIs?▼

A self-hosted Firecrawl search differs by running locally at localhost:3002 and offering optional full-page content extraction alongside structured search results, whereas standard APIs typically return only snippets or metadata without full-page data.

Why is my Firecrawl web search not returning full-page content?▼

If your Firecrawl web search is not returning full-page content, ensure the optional scraping command is enabled and that your self-hosted Firecrawl service at localhost:3002 is actively running and correctly processing extraction requests.