A powerful command-line interface for scraping, crawling, and searching the web to generate clean markdown for AI context.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install firecrawl-skills
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install firecrawl-skills using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Firecrawl CLI?
Firecrawl CLI is a high-performance tool built to transform the vast information of the web into a format that AI agents can easily consume. It specializes in converting complex websites into clean, structured markdown while handling modern web challenges like JavaScript rendering and anti-bot protections. By utilizing this tool within your Openclaw Skills library, you can automate the retrieval of high-quality data for research, documentation, and competitive intelligence.
Whether you need to scrape a single page, map out an entire site's architecture, or perform a deep web search across multiple sources, Firecrawl provides a developer-friendly interface to get the job done. It is designed specifically with LLM context windows in mind, ensuring that the data returned is concise, relevant, and free of unnecessary clutter like ads, navigation bars, and footers.
Firecrawl CLI Use Cases
- Automating the collection of technical documentation for RAG (Retrieval-Augmented Generation) systems.
- Conducting deep market research by searching across news, web, and research categories simultaneously.
- Extracting structured content from Single Page Applications (SPAs) that require heavy JavaScript execution.
- Monitoring specific website paths for updates to feed into automated content pipelines.
- Mapping entire domains to discover all available URLs for auditing or indexing.
How Firecrawl CLI Works
- The user authenticates the CLI using an API key to manage concurrency and credit limits.
- A command is issued (search, scrape, crawl, or map) targeting specific URLs or search queries.
- Firecrawl handles the heavy lifting of fetching the content, bypassing blocks, and rendering dynamic elements.
- The raw data is processed and converted into clean markdown or structured JSON based on user preferences.
- Results are saved to a local .firecrawl/ directory to prevent flooding the agent's immediate context with large data streams.
Firecrawl CLI Setup
To get started with this skill, install the Firecrawl CLI globally using npm:
npm install -g firecrawl-cli
Authenticate your session by logging in via your browser:
firecrawl login --browser
Verify your installation and check your available credits:
firecrawl --status
Firecrawl CLI Data Schema & Taxonomy
Firecrawl organizes output into a local directory for efficient data management. Results are typically categorized by operation type:
| Operation | Default Format | Description |
|---|---|---|
| Scrape | .md | Clean markdown extraction of page content. |
| Search | .json | Structured results including snippets, titles, and links. |
| Crawl | .json | Recursive site extraction results with metadata. |
| Map | .txt / .json | A comprehensive list of discovered URLs on a domain. |
| HTML | .html | Raw HTML content when full source preservation is needed. |
Firecrawl CLI Advanced Features
- Parallel execution support using xargs for high-volume scraping tasks.
- Advanced search filtering including time-based filters (e.g., past 24 hours) and location-based targeting.
- Targeted extraction using CSS selectors with include-tags and exclude-tags parameters.
- Integration with jq for sophisticated post-processing of JSON search and crawl data.
- Configurable crawl depth and path-based inclusion/exclusion for precise site indexing.
SKILL.md
Loading
Related Openclaw Skills
Timestamp Converter
A versatile utility for converting between Unix timestamps, ISO 8601 dates, and localized human-readable formats.
API Tester
A versatile testing tool for validating REST API endpoints, authentication flows, and webhook integrations with customizable request parameters.
QR Code Generator
A versatile tool for generating customizable, high-quality QR codes for URLs, WiFi credentials, contact cards, and more.
Batch File Renamer
An efficient utility for bulk renaming files using powerful regex patterns, sequential numbering, and timestamping.
Tuniu Flight Assistant
A comprehensive AI skill for managing domestic flight searches and bookings through the Tuniu Open Platform via standard shell commands.
Tuniu Hotel Assistant
A professional AI agent skill for searching, detailing, and booking hotels via the Tuniu platform using MCP and shell execution.
Featured*
