Eric Ciarla
Today, we're launching Firecrawl CLI and Skill to give your AI agents reliable access to real-time web data.
TL;DR:
- Firecrawl CLI is a command-line tool for scraping, searching, crawling, and mapping the web with results written directly to the filesystem.
- The Firecrawl Skill teaches AI agents how to install and use the CLI on their own - no manual setup required.
- Together, they give agents clean, structured web data exactly when they need it.
Just run:
$ npx skills add firecrawl/cliThat's it. The Firecrawl Skill handles the rest.
The Problem: Agents Need Better Web Data
Most agents rely on web fetch tools that break on JavaScript-heavy sites, miss key content, or return unusable HTML. When they do get data, they dump entire pages into context, wasting tokens and slowing down reasoning.
The Firecrawl CLI and Skill helps AI agents reliably access real-time web data on their own. With a single install, agents like Claude Code, Antigravity, and OpenCode can access all of your favorite Firecrawl endpoints - including scrape, search, crawl, and map for any use case you need.
Meet Firecrawl CLI
Firecrawl CLI is a command-line tool designed for agents and developers who need reliable web data.
Core Commands
- scrape - Pull clean markdown from any page, even JavaScript-heavy sites
- crawl - Follow links recursively and gather content from an entire site
- map - Discover all URLs on a domain for comprehensive coverage
- search - Search the web and scrape the results in one step
Context-Efficient Data for Agents
Firecrawl CLI uses a file-based approach for context management and bash methods for efficient search and retrieval.
Industry-Leading Reliability
Firecrawl delivers >80% coverage on benchmark evaluations - outperforming every other provider tested. It handles JavaScript rendering, dynamic content, authentication flows, and complex page structures that break other scrapers.
(Methodology: Checked 1,000 URLs for content recall and whether various tools in the market retrieved at least 10% of the expected content gap, using the Firecrawl scrape-content-dataset-v1 dataset.)
Example usage:
# Scrape a page to markdown
$ firecrawl scrape https://example.com/pricing --format markdown -o pricing.md
# Crawl an entire website, wait for completion, and output results
$ firecrawl crawl https://example.com --wait --progress -o example-crawl.json
# Map an entire domain
$ firecrawl map https://example.com -o sitemap.json
# Search and scrape top results
$ firecrawl search "AI agent benchmarks 2026" --scrape --limit 5 -o results/All results are written to the filesystem, so agents can search, analyze, or process data locally.
Firecrawl Skill: Teach Agents to Use the CLI
The Firecrawl Skill is a skill package that teaches AI agents how to install, authenticate, and use Firecrawl CLI - end to end.
Skills are declarative packages that agents can install via the npx skills protocol. Once installed, agents know how to use the tool without manual integration.
What the Skill Teaches
- How to install Firecrawl CLI
- How to authenticate with an API key
- When and how to use scrape, map, and search commands
- How to structure output for efficient filesystem usage
Coding Agent Harness Compatibility
The Firecrawl Skill works with any agent that supports the Skills protocol:
- Claude Code — Agentic coding in your terminal
- OpenAI Codex — Build with GPT-4 in the CLI
- Gemini CLI — Google's agent interface
- OpenCode — Open-source agent harness
- And more
One skill, every major coding agent harness.
Why Skills Matter
You don't configure endpoints, handle auth, or write tool definitions. The Skill does it. Add Firecrawl once, and your agent knows how to use it forever.
As the Skill evolves, your agent learns new capabilities automatically. No code changes. No redeployment. It just works.
Firecrawl CLI + Skill: Agents Empowered with Live Web Data
When you combine Firecrawl CLI with our skill, your agent can reliably access web data on its own.
How It Works
- You run
$ npx skills add firecrawl/cli - The skill teaches your agent about Firecrawl CLI capabilities
- When your agent needs web data, it installs and uses the CLI automatically
- Results are written to the filesystem, not dumped into context
- Your agent searches, analyzes, or processes the data locally
Here's a quick look at common use cases where agents with Firecrawl shine:
| Use case | Value |
|---|---|
| Competitor product research | Track pricing, feature pages, and changes across competitor sites - so you get fresh data on specs, updates, and positioning without manual checking |
| Documentation and help centers | Pull full docs and help centers for the latest information, giving agents current API references and guides instead of stale training data |
| Site change monitoring | Detect updates across large sites, from pricing shifts to new content, and map entire domains to track changes over time automatically |
| Deep research with sources | Collect structured sources with URLs and timestamps to ground answers in verifiable data with proper attribution |
Get Started
Install the Firecrawl Skill:
$ npx skills add firecrawl/cliOr use the CLI directly:
$ npm install -g firecrawl-cli
$ firecrawl auth --api-key fc-YOUR_KEY
$ firecrawl scrape https://example.comCheck out our docs for more info.
Give your agent the best web data available. No context bloat. Just reliable, real-time information when it needs it.
Resources:
- GitHub: github.com/firecrawl/cli
- Documentation: docs.firecrawl.dev/cli
- Get an API key: firecrawl.dev
data from the web