firecrawl-search
Web search with full page content extraction. Use this skill whenever the user asks to search the web, find articles, research a topic, look something up, find recent news, discover sources, or says "search for", "find me", "look up", "what are people saying about", or "find articles about". Returns real search results with optional full-page markdown — not just snippets. Provides capabilities beyond Claude's built-in WebSearch.
Security Assessment
About firecrawl-search
The 'firecrawl-search' skill enables comprehensive web searches with optional content extraction from search results. It solves the problem of needing to quickly discover articles, research topics, or gather up-to-date news from the web without having a specific URL. This skill is designed to help users search for information across a wide range of sources, whether looking for articles, news, research papers, or other resources, making it a versatile tool for information discovery.
FAQ
How do I use firecrawl-search for a basic web search?
To perform a basic web search, you can use the following command: `firecrawl search "your query" -o .firecrawl/result.json --json`. This will return search results in JSON format.
Can firecrawl-search scrape the full content of search results?
Yes, by adding the `--scrape` flag, you can scrape the full page content of each search result. For example: `firecrawl search "your query" --scrape -o .firecrawl/scraped.json --json`.
What file format does firecrawl-search output?
By default, firecrawl-search outputs the results in JSON format. You can specify this with the `--json` flag.
Are there any time-based search filters available?
Yes, firecrawl-search allows you to filter search results by time using the `--tbs <qdr:h|d|w|m|y>` option, where 'h' stands for hours, 'd' for days, 'w' for weeks, 'm' for months, and 'y' for years.
Install firecrawl-search
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill
Repository
firecrawl/cli