Use when needing to navigate websites, verify deployments, check dashboards (Google Ads, Stripe, Cloudflare), test features as a real user, inspect rendered pages, capture screenshots, prove visual state, handle login/account/admin-console workflows, or do any browser automation. Also use when the user says "use agent browser", "visual verification", "visual proof", "verify what renders", "check page in browser", "test", or "verify" a web feature.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, checking rendered pages, proving visual state, logging into sites, using the real Chrome profile, or automating any browser task. Triggers include requests to "use agent browser", "open a website", "fill out a form", "click a button", "take a screenshot", "browser screenshot", "visual verification", "visual proof", "verify what renders", "check page in browser", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Self-orchestrating parallel browser agent swarm. Use for ANY task involving 3+ URLs or web pages. Triggers: multi-URL research, open-ended web research ("find examples of...", "compare sites", "analyze trends"), competitive analysis, design inspiration gathering, forum/discussion reading, parallel auditing, 3+ visual verifications, monitoring. If the task says "research"/"find"/"compare"/"analyze" + websites/pages/examples, use this skill.