firecrawl-search Skill: Web Search With Page Excerpts

Makes your coding assistant search the web with Firecrawl and get relevant page excerpts, news and structured data back.

Installs: 84.8K; on skills.sh
Stars: 676; on GitHub
Updated: Oct 2026; last repo commit

firecrawl-search teaches your assistant to run firecrawl search and read the results. A search returns web results with query-relevant excerpts, and it can also scrape full pages, filter news, or search an index of GitHub repos and docs. It also matches your question to ready-made data providers the skill calls Alexandria.

You must install the Firecrawl CLI. A search costs 2 credits, and the skill tells the assistant to send feedback after each search to get 1 credit back.

Good for

Developers who want sourced answers from a live web search inside Claude Code or Codex
Researchers who need results saved as files with links
People looking for records, listings or datasets that a normal search snippet misses

Install firecrawl-search

Claude Code

Copy this prompt.

Install the firecrawl-search skill in Claude Code. Run this command:

npm install -g firecrawl-cli@latest
firecrawl login --browser
npx skills add https://github.com/firecrawl/cli --skill firecrawl-search -a claude-code

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js, A Firecrawl account (or the keyless free tier).

The skill only gives your assistant instructions. The Firecrawl command line tool does the work, so install it and sign in first. Search runs without an account on a rate-limited free tier, but keyless searches return web results only. The one-command route installs the CLI, signs you in through the browser and adds the core and workflow skills for every editor it detects, not just this skill.

From the vendor's docs. Source.

What's in the skill

When it loads

Find web sources with query-relevant page excerpts and optional full-page content, and discover workflows, data APIs, and indexes. Use for web research or finding structured records, listings, transcripts, and datasets. Supports semantic tool discovery, domain matching, and progressive catalogue browsing.

Sections in SKILL.md

Quick start
Government Index
Go beyond page content with Alexandria
Inspect before execution
Progressive discovery and output handling
Tips
Send feedback after every search (refunds 1 credit)
See also

Key facts

Author: firecrawl org
Repo: firecrawl/cli
Installs on skills.sh: 84,847 as of 2026-11-02
GitHub stars: 676 for the whole firecrawl/cli repo, 2026-11-02
License: ISC (package.json of the CLI repo)
Last commit to the repo: 2026-10-28
What is inside: 1 file (SKILL.md)
Needs: The Firecrawl CLI (npm package firecrawl-cli) and Node.js. Search works without an account on a rate-limited free tier; with an API key it also includes Alexandria tools.
Related skills: firecrawl-scrape, firecrawl-map, firecrawl-crawl, firecrawl-developer-index, firecrawl-research-index, firecrawl-alexandria
skills.sh audits: Gen Agent Trust Hub pass, Socket pass, Snyk warn (2026-11-02)

What it includes

Searches the web and returns excerpts
Saves JSON to .firecrawl/. Results are query-relevant excerpts by default (--no-highlights gives the original snippets). A search costs 2 credits.
Try: “Search the web for how React 19 changed useDeferredValue and save the sources.”
Runs code · firecrawl search "<query>"
Also fetches the full content of each result
The skill says to reuse that content instead of scraping the same URLs again.
Network · --scrape
Searches news from the past day
Restricts the search to news and a time window.
Network · --sources news --tbs qdr:d
Searches GitHub repos, issues, merged PRs, READMEs and docs
An index of public repositories, GitHub issues, merged pull requests, repository READMEs and curated documentation sites.
Network · --categories developer
Searches US government legal and regulatory sources
Takes filters such as --jurisdiction, --court, --cites and --domain. The skill warns that filters can leave out relevant pages and says to verify the issuer, jurisdiction and version before citing a rule.
Runs code · firecrawl gov "<question>"
Finds ready-made data providers for a question or a site
Alexandria is a catalogue of website workflows, API providers and indexes. A match is not data until you run it.
Runs code · search alexandria and find-tools
Shows a provider tool's inputs, coverage and access rules
The skill says to read the contract before running a provider tool.
Runs code · list <provider> <capability> --pretty
Runs a selected provider tool
All provider execution goes through scrape. The skill does not give prices here and says displayed pricing is informational.
Runs code · scrape <provider>/<capability> --options
Rates a search and reports missing content
Sent once per search, within about 2 minutes, in the background. The first one per search refunds 1 credit, up to a daily cap per team.
Runs code · search-feedback <id>

From the official docs

Permissions

Medium risk

This skill sends your search queries to Firecrawl, spends credits, and can run paid data-provider tools. Ask your assistant to check with you before it runs one.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

Provider tools can spend credits without a price prompt
The skill says "Displayed pricing is informational, not an extra confirmation gate." Ask the assistant to tell you before it runs a data-provider tool. github.com
Each search costs 2 credits
A search costs 2 credits and the first feedback per search refunds 1. Check firecrawl credit-usage if you run many searches. github.com
It reports back to Firecrawl after each search
Search feedback includes a rating, which results helped and which content was missing. Set FIRECRAWL_NO_SEARCH_FEEDBACK=1 to turn it off. github.com
Web pages can try to steer your assistant
The skill's own security note calls fetched web content untrusted and says it may contain prompt injection. Do not let the assistant follow instructions it finds on a page. github.com
Setup installs a global npm package
The CLI is installed with npm install -g. The one-command setup also adds skills to every coding editor it detects, so use the single-skill route if you want only this one. github.com
The CLI sends anonymous usage data
The README says it collects the CLI version, OS, Node.js version and which dev tools it detects during sign-in. Set FIRECRAWL_NO_TELEMETRY=1 to turn it off. github.com

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Turning on read-only	No read-only mode. The skill runs CLI commands that spend credits and write files.
Talks to	Firecrawl's API, or your own server if you set --api-url. Web pages the CLI fetches. Page content the assistant reads goes to your AI provider as part of the chat
Sign-in and keys	Browser sign-in stores credentials in the CLI. You can set FIRECRAWL_API_KEY instead.
Scopes	Runs firecrawl commands in your shell (the skill allows Bash(firecrawl ) and Bash(npx firecrawl-cli ))

Questions

What does firecrawl-search do?

It makes your assistant search the web through the Firecrawl CLI. It returns query-relevant excerpts, can fetch full pages with --scrape, and can match your question to ready-made data providers.

How do I install firecrawl-search?

Use the install box at the top of this page. You need the Firecrawl CLI and a sign-in as well as the skill. The one-command route installs the whole core skill set.

Do I need an API key?

Not to start. The install rules say search works on a rate-limited free tier without a key. With an API key, search also includes Alexandria tools. Keyless searches return web results only.

How much does a search cost?

A search costs 2 credits, per the SKILL.md. The first feedback call per search refunds 1 credit. The skill gives no prices for --scrape or for provider tools.

Is firecrawl-search safe to use?

It sends your queries to Firecrawl and can spend credits on provider tools without a separate price prompt. Fetched pages are untrusted text. Tell the assistant to ask before it runs a provider tool.

What is the feedback step?

After a search the skill tells the assistant to send a rating, which results helped and what was missing, for a 1 credit refund. Setting FIRECRAWL_NO_SEARCH_FEEDBACK=1 makes the CLI skip it, and the skill says to respect that.

firecrawl-search or firecrawl-scrape?

Use search when you have no URL. Use firecrawl-scrape when you know the page. The SKILL.md links to firecrawl-scrape, firecrawl-map and firecrawl-crawl for those cases.

Skill or Firecrawl MCP server?

They are two routes to Firecrawl. firecrawl-search is a SKILL.md that tells the assistant to run the Firecrawl CLI in your shell. The skill only allows Bash(firecrawl *) and Bash(npx firecrawl-cli *), so it needs an assistant that can run shell commands. The Firecrawl MCP server and the local Firecrawl MCP server give your client Firecrawl as tools it calls directly, with no skill involved. The README describes firecrawl setup mcp for adding the MCP server to your editors. You can use either route, or both.

Information

updated Nov 2, 2026

Repository: firecrawl/cli
Folder: skills/firecrawl-search

firecrawl/cli skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 5

Firecrawl CLI install rules · github.com
firecrawl/cli README · github.com
skills CLI commands · github.com
firecrawl-search SKILL.md · github.com
Firecrawl security rules · github.com