Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Wraps the Firecrawl API to fetch web pages as clean markdown, capture full-page screenshots, extract structured data using a JSON schema, search the web, and crawl documentation sites. Handles JavaScript-rendered content that basic HTTP requests cannot read. Free tier includes 500 credits; each page, screenshot, or search costs 1 credit.
Firecrawl renders JavaScript before returning content, so it works on modern SPAs and dynamic pages where curl or requests would return an empty shell.
When to use it
- Summarizing a blog post or article from a URL
- Capturing a screenshot of a live website for design reference
- Pulling product name, price, and features from an e-commerce page
- Crawling a framework's docs before starting a new project
- Mapping all URLs on a site to plan what to scrape
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: 'Extract the name, price, and features from https://example.com/product'
- 1Define a JSON schema with name, price, and features fields
- 2Run fc.py extract against the product URL with the schema file
- 3Firecrawl renders the page and maps content to the schema
- 4Return the structured JSON to the user
JSON object with name as a string, price as a number, and features as an array of strings
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.