Firecrawl for Openclaw

A comprehensive web search and scraping tool designed for AI agents to extract structured data from any website including JS-heavy pages.

ashwingupy
v1.0.0
Jan 28, 2026
52
26.2k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install firecrawl-search

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install firecrawl-search 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?

Firecrawl is a robust integration for Openclaw Skills that enables AI agents to bypass the limitations of static datasets by accessing the live web. It provides specialized capabilities for searching search engines, scraping individual web pages with full JavaScript rendering, and performing deep crawls of entire domains. By using this skill, developers can ensure their agents have access to real-time information and cleanly formatted Markdown content, which is optimized for Large Language Model consumption. This makes Firecrawl a vital component for any sophisticated agentic workflow built with Openclaw Skills.

Firecrawl Use Cases

  • Performing real-time market research and competitive analysis within Openclaw Skills.
  • Scraping technical documentation from modern, JavaScript-dependent web applications.
  • Automating the collection of data from entire websites through recursive crawling.
  • Extracting clean, structured content from search results to fuel RAG (Retrieval-Augmented Generation) pipelines.

How Firecrawl Works

  1. The AI agent initiates a request using one of the core scripts provided in the Firecrawl repository.
  2. The skill authenticates with the Firecrawl API using a securely stored API key.
  3. For search requests, the skill queries the web and returns a list of relevant results; for scraping, it renders the page and converts HTML to Markdown.
  4. For crawling, the skill systematically visits multiple pages on a domain based on defined limits.
  5. The resulting structured data is then passed back to the Openclaw Skills agent for processing or storage.

Firecrawl Setup

To integrate Firecrawl with your Openclaw Skills environment, you must first obtain an API key from Firecrawl. Configure your environment by setting the FIRECRAWL_API_KEY variable:

export FIRECRAWL_API_KEY=fc-xxxxxxxxxx

You can verify the installation by running a quick search command from your terminal.

Firecrawl Data Schema & Taxonomy

The Firecrawl skill returns data in structured formats optimized for agentic reasoning. The following table describes the primary data outputs:

Feature Output Type Content Description
Search JSON Array Includes titles, URLs, and text snippets from top search results.
Scrape Markdown String The full, rendered content of a web page stripped of boilerplate code.
Crawl Collection A recursive set of page contents from a specific domain.
Metadata JSON Object Details regarding page status, crawl depth, and extraction success.

Firecrawl Advanced Features

  • High-fidelity scraping of JavaScript-heavy pages using automated browser rendering via Openclaw Skills.
  • Configurable crawling depth and page limits to manage resource consumption and speed.
  • Native support for structured data extraction, turning raw web content into usable intelligence.
  • Seamless integration with multi-agent workflows that require real-time web verification and research.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*