A high-performance web scraping and crawling engine that transforms any URL into clean, AI-ready markdown or structured data.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install firecrawler
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 firecrawler 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 Web Skill?
The Firecrawl skill is a robust integration designed for the Openclaw Skills ecosystem, enabling developers to bridge the gap between static LLMs and the dynamic web. It utilizes the Firecrawl API to handle complex tasks like JavaScript rendering and bot detection, ensuring that your AI agent receives high-quality, noise-free content. Whether you need to scrape a single page or index an entire documentation site, this skill provides the necessary tools to feed context-rich data directly into your workflows.
By incorporating this into your setup, you gain the ability to navigate the web with the precision of a human browser but at the speed of an automated system. It is specifically optimized to output content in formats that LLMs prefer, such as clean markdown and validated JSON, making it an essential component of the Openclaw Skills library.
Firecrawl Web Skill Use Cases
- Ingesting technical documentation into an AI's context for real-time coding assistance.
- Automated competitive intelligence by extracting pricing and feature lists from e-commerce sites.
- Generating visual snapshots of UI/UX designs through full-page screenshots.
- Conducting deep-web searches to provide up-to-date answers beyond a model's training cutoff.
- Mapping website architectures to identify specific API endpoints or sub-pages for data analysis.
How Firecrawl Web Skill Works
- The user provides a target URL or search query along with the desired action (scrape, crawl, map, or search).
- The skill authenticates with the Firecrawl API using a securely stored environment variable.
- Firecrawl's engine visits the target site, executes any necessary JavaScript, and strips away non-essential elements like ads and trackers.
- The processed content is converted into the requested format, such as markdown or a structured JSON object based on a schema.
- The resulting data is returned to the agent, enabling it to perform summaries, code generation, or data analysis based on the fresh web content.
Firecrawl Web Skill Setup
To begin using this skill within the Openclaw Skills framework, follow these steps:
# 1. Obtain your API key from firecrawl.dev/app/api-keys
# 2. Set the environment variable in your terminal or .env file
export FIRECRAWL_API_KEY=fc-your-key-here
# 3. Install the required Python SDK
pip3 install firecrawl
Firecrawl Web Skill Data Schema & Taxonomy
The Firecrawl skill organizes its output into structured formats to ensure compatibility with various AI processing pipelines. Below is the metadata and file organization taxonomy:
| Data Type | Description | Format |
|---|---|---|
| Markdown | Cleaned webpage content stripped of HTML boilerplate | .md |
| Screenshots | Full-page visual captures of the target URL | .png |
| Structured Data | Data extracted via custom JSON schema (e.g., price, title) | JSON |
| Site Map | A comprehensive list of URLs discovered on a domain | Array |
| Search Results | Metadata and snippets from live web search queries | JSON |
Firecrawl Web Skill Advanced Features
- Main-only content filtering to focus exclusively on the primary article text while ignoring navbars and footers.
- Schema-driven extraction which allows users to define exactly which data points (like dates or prices) the AI should target.
- Depth-controlled crawling to index large documentation sets without exceeding credit limits.
- Real-time site mapping to visualize a domain's structure before initiating a heavy scrape.
- Multi-format support allowing for simultaneous markdown retrieval and screenshot generation.
SKILL.md
Loading
Related Openclaw Skills
D&D 5e Toolkit
A comprehensive Dungeons & Dragons 5th Edition utility for automating gameplay mechanics like dice rolling, stat lookups, and character generation.
Attio CRM
A comprehensive integration for managing Attio CRM data, including records, pipelines, notes, and tasks directly through an AI agent.
Apollo Enrichment
A powerful data enrichment skill for identifying prospects and fetching deep company intelligence via the Apollo.io API.
Ham Radio DX Monitor
A real-time amateur radio DX cluster monitor and alerting tool designed to help operators identify and contact rare stations.
Geo-Optimization (GEO) for AI Search
A comprehensive framework and toolset to optimize web content for discovery and citation by Generative AI engines like Perplexity, ChatGPT, and Google AI Overviews.
Ham Radio DX Monitor
A real-time amateur radio DX cluster monitor for tracking rare stations, expeditions, and band activity via CLI or automated alerts.
Featured*
