Drive an authentication flow once, sanitize cookies through AIDefence, and vault a reusable cookie handle in browser-cookies for future…
Pre-flight resource check before launching Browser Subagent.
Browser-based QA and autonomous verification — Playwright, Chrome DevTools MCP, Computer Use for visual testing, pixel verification…
RULE: gsd-browser for new tasks. dev-browser for existing scripts.
Discover project routes/URLs BEFORE planning browser navigation.
Browser automation using local browser profile
GUI-R1 inspired Self-Reflection protocol.
Manage browser tabs during sessions. Check if a URL is already open before navigating to avoid duplicates. Close unused/stale tabs to save…
Routes browser tasks only through the Playwright CLI and Chrome DevTools MCP. Use for: browser testing, UI…
Detect the available browser interaction layer and load the right commands — then navigate, click, fill, and screenshot through a unified…
Use when you need to run arbitrary JS in a page, inspect cookies/localStorage, check computed styles, emulate devices, or drive real…
Navigate one isolated Goose browser Session, inspect the rendered page, interact with confirmed controls, and capture or download explicit…
Autonomous browser agent for complex multi-step web tasks.
Deploy serverless browser automation as cloud functions using Browserbase.
Run evidence-backed functional, responsive, cross-browser, and visual-design QA of a specific web page or critical page flow across…
Browser automation. MUST invoke before calling Playwright. Use when browsing websites, checking UI, filling forms, or automating web…
Run deep research on a topic. Web searches, data collection, source checking, and a structured report. Use when the user needs more than a…
Headless browser automation via Camofox (Firefox-based) running on localhost:9377.
Capture screenshots of all manual pages at high resolution for translation verification.
CBOE data via public APIs: delayed index quotes, VX futures, intraday charts, most-active, market summary (equities +…
This skill should be used when the user asks to "take browser screenshot", "list browser tabs", "click page element", "navigate browser"…