firecrawl-search: a Claude Code skill by Firecrawl
Official
For people who want Claude to search the web from the terminal and keep results with excerpts as JSON. Skip it if you do not want to spend credits per search.
Before you install: After every search it has Claude send feedback to Firecrawl in the background about which results were useful, unless you set FIRECRAWL_NO_SEARCH_FEEDBACK=1.
- Score
- 78of 100
- Rank
- #75of 239
- Installs
- 85.2Kon skills.sh
- Security
- Mixed 5 scanners
- Updated
- 2026
- Context
- ~80tokens always
Install
npx skills add https://github.com/firecrawl/cli --skill firecrawl-search
Run it in your terminal. View the source
Using the Claude app rather than Claude Code? You can add a skill there too. How to add it in the app
What does firecrawl-search do?
firecrawl-search is a Claude skill that runs web searches through the Firecrawl CLI and saves the results as JSON files under .firecrawl/. A basic call is firecrawl search with your question, --scrape pulls full page content, and --sources news with a time filter finds recent news. It can also search Alexandria, Firecrawl's catalogue of ready-made site workflows and data providers, for structured records like listings or transcripts, and firecrawl gov searches US legal and regulatory sources. Claude reads the saved file with jq instead of loading it whole. Each search costs 2 credits, and the rated feedback Claude sends afterwards refunds 1.
When should you use firecrawl-search?
Use it when
- Researching a topic and citing source links
- Finding structured listings or datasets on the web
- Looking up US laws or regulations
Skip it when
- You do not want to pay per search
- You only need to read one page you already know
What it needs and what it can touch
You need
- The Firecrawl CLI
- A Firecrawl API key for the full feature set
What it can do
- Runs firecrawl shell commands
- Writes result files to .firecrawl/ in your project
- Sends your queries and search feedback to Firecrawl
From reading its instructions, not from running it.
Why it scores 78
Strongest on upkeep (100 of 100), weakest on adoption (53).
Is firecrawl-search safe to install?
At least one scanner raised a medium warning. Read the results below. Scanners often miss what other scanners catch, and a skill can change after a scan. Read its source before you install it.
| Scanner | Result | Date |
|---|---|---|
| Gen Agent Trust Hub | Passed | Oct 22, 2026 |
| Socket | Passed | Oct 22, 2026 |
| Snyk | Medium risk | Oct 22, 2026 |
| Runlayer | Passed | Mar 10, 2026 |
| ZeroLeaks | Passed | Apr 15, 2026 |
Details
- Installs
- 85,204
- Repository stars
- 682
- Last repository change
- Tokens always loaded
- about 80
- Tokens when used
- about 3,394
- License
- Not stated
- Data confidence
- High
Did it do the job for you?
Alternatives to firecrawl-search
All skills for this job-
Get tavily-searchtavily-search
For anyone who wants Claude to check current facts, news or sources on the web through Tavily.
-
Get firecrawl-agentfirecrawl-agent
For people who need structured data pulled from sites that take many pages to navigate.
-
Get firecrawl-scrapefirecrawl-scrape
For people who have a URL and want its content as markdown or typed JSON.
-
Get opencli-usageopencli-usage
For developers who use OpenCLI and want Claude to find and run its site adapters and Chrome tools.