From firecrawl
Integrate Firecrawl `/interact` into product code for dynamic pages and browser actions after scraping. Use when a feature needs clicks, form fills, pagination, authentication-aware flows, or other multi-step interactions that plain `/scrape` cannot complete.
npx claudepluginhub firecrawl/skills --plugin firecrawlThis skill uses the workspace's default tool permissions.
Use this when `/scrape` is not enough because the feature needs to act on the page.
CLI browser automation: navigate URLs, snapshot pages with @refs, click/type elements by ref/text/query, extract structured data/markdown, search/filter web content.
Performs deep web scraping, screenshots, PDF parsing, and website crawling using Firecrawl API. Useful for content extraction from pages, page interactions like clicking/scrolling, or batch scraping URLs.
Automates real browser tasks: viewing pages, login-gated sites, UI operations, social media scraping (Xiaohongshu/Weibo/X), JS-rendered pages, bot bypass, form filling, e2e checks via CLI/Python SDK.
Share bugs, ideas, or general feedback.
Use this when /scrape is not enough because the feature needs to act on the page.
/scrape, then escalate to /interact./interact scoped to the smallest browser workflow that unlocks the data./interact is the right tool when the page must be manipulated, not just read.Read the source-of-truth page for your project language before writing integration code: