firecrawl-cli

What This Skill Does

The firecrawl-cli skill integrates OpenClaw with the powerful Firecrawl platform, enabling seamless web scraping, site crawling, and intelligent search capabilities. It transforms raw, complex web content into clean, LLM-ready markdown. By handling JavaScript rendering, bypassing common anti-bot mechanisms, and providing structured data outputs, it acts as a bridge between the vast, unstructured web and your AI agent's knowledge base. Whether you are performing competitive intelligence, conducting deep research, or extracting documentation from technical websites, this skill ensures the data you receive is concise, formatted correctly, and free from unnecessary boilerplate.

Installation

To integrate this skill into your environment, use the OpenClaw management command: clawhub install openclaw/skills/skills/ctbritt/firecrawl-skills. Before use, ensure the Firecrawl CLI is installed globally via npm install -g firecrawl-cli. Authentication is handled via the firecrawl login --browser command, which allows you to securely manage your API keys. You should always monitor your account status using firecrawl --status to check your remaining credits and concurrency limits, ensuring your automated tasks run smoothly without interruption.

Use Cases

• Research & Intelligence: Automate the gathering of news or technical updates from multiple sources simultaneously, with the ability to filter by time-based constraints or categories.
• Documentation Extraction: Scrape entire technical documentation hubs and convert them into structured markdown files that can be easily indexed or summarized by LLMs.
• Content Monitoring: Regularly crawl specific domains to track changes or retrieve the latest posts, perfect for competitive analysis.
• Data Pipelines: Generate JSON outputs from search queries to feed directly into other data processing or analytical tools within your OpenClaw workflow.

Example Prompts

1. "Search for the latest research papers published this week on Transformer architecture and save the results to the .firecrawl folder in JSON format."
2. "Crawl the documentation for the React Server Components website and consolidate the output into a single markdown file for my project review."
3. "Find current tech news regarding AI agents and scrape the top 5 results into separate files within the .firecrawl directory."

Tips & Limitations

Always use the -o flag to write your results to the .firecrawl/ directory; this prevents the AI from cluttering your chat context window. Remember to add .firecrawl/ to your .gitignore file to avoid tracking scraped data in version control. Keep an eye on your concurrency limits; running too many jobs in parallel may result in failed tasks if you exceed your current tier's capabilities. For best results, use the --json flag when performing searches to ensure the output is programmatic and ready for secondary processing by the agent.