ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified developer tools Safety 3/5

firecrawl

Web scraping and crawling with Firecrawl API. Fetch webpage content as markdown, take screenshots, extract structured data, search the web, and crawl documentation sites. Use when the user needs to scrape a URL, get current web info, capture a screenshot, extract specific data from pages, or crawl docs for a framework/library.

Why use this skill?

Integrate Firecrawl with OpenClaw to scrape websites, extract structured data, capture screenshots, and crawl documentation for smarter AI assistance.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/andrewdmwalker/firecrawler
Or

What This Skill Does

The Firecrawl web skill enables your OpenClaw agent to interact with the live internet by turning complex, JavaScript-rendered websites into clean, usable data. By leveraging the Firecrawl API, this skill allows the agent to scrape full webpages and convert them into clean markdown, capture high-quality screenshots for visual verification, extract specific structured data using custom JSON schemas, perform live web searches, and perform full-site crawls. It acts as the bridge between your agent and the vast repository of documentation and real-time information available on the web.

Installation

  1. Ensure you have obtained an API key from firecrawl.dev.
  2. Set your environment variable: export FIRECRAWL_API_KEY=fc-your-key-here.
  3. Install the required SDK via pip: pip3 install firecrawl.
  4. Install the skill into your OpenClaw environment using: clawhub install openclaw/skills/skills/andrewdmwalker/firecrawler.

Use Cases

  • Automated Research: Quickly scrape and summarize technical blogs, news articles, or research papers without manual navigation.
  • Documentation Integration: Crawl entire documentation websites to help your agent gain context on specific frameworks or libraries, allowing it to provide more accurate coding assistance.
  • Data Extraction: Use structured extraction to pull specific product information (like pricing or feature lists) from e-commerce websites into machine-readable JSON format.
  • Visual Verification: Capture screenshots of web applications or dashboards for record-keeping or debugging purposes.
  • Web Reconnaissance: Discover internal site structures and mapping via the map functionality to understand the footprint of a target domain.

Example Prompts

  • "Can you scrape the documentation at https://docs.astro.build and use that information to help me build a new landing page?"
  • "Please visit https://www.example-store.com/laptop and extract the model name, current price, and technical specifications into a structured format."
  • "Search for the latest security updates regarding the Linux kernel and summarize the top three findings for me."

Tips & Limitations

Each request typically consumes 1 credit per page or action. Keep an eye on your usage limits to avoid unexpected costs. When scraping, use the --main-only flag to avoid cluttering your context window with navigation menus and footers. If you are crawling documentation, always start with a smaller limit (e.g., 50 pages) to ensure you are gathering relevant data before committing to larger crawls.

Metadata

Stars1054
Views0
Updated2026-02-16
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-andrewdmwalker-firecrawler": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#web-scraping#automation#data-extraction#crawling#research
Safety Score: 3/5

Flags: network-access, file-write, external-api