Firecrawl Skills
Firecrawl CLI for web scraping, crawling, and search. Scrape single pages or entire websites, map site URLs, and search the web with full content extraction. Returns clean markdown optimized for LLM context. Use for research, documentation extraction, competitive intelligence, and content monitoring.
Why this rating
Deterministic checks triggered by the tool capabilities and evidence.
- Locality: Hybrid
Uses the `firecrawl` CLI authenticated via `FIRECRAWL_API_KEY` and targets user-provided URLs.
- Data access: Sensitive
Can extract full page content (markdown/HTML/raw HTML/links/screenshots) and crawl many pages.
- Action surface: Read
Performs web content retrieval and saves results locally; it does not modify target sites.
Best practices
Follow these steps to reduce risk when using this skill.
- Add `.firecrawl/` to `.gitignore` and avoid committing scraped outputs that may contain sensitive content.
- Use conservative limits/concurrency and respect target site terms and robots; avoid scraping authenticated/private areas unless authorized.
- Keep `FIRECRAWL_API_KEY` in env vars, rotate if exposed, and monitor credit usage before running large crawls.
Evidence links
Public sources backing the indicator assignments.
Always be careful when navigating away from the website.
Max-risk rule
If any capability reaches a higher level, the entire indicator level bumps up to keep ratings deterministic and easy to scan.