Agent skills

AI code reviewer grounded in classic software engineering books for catching design smells, coupling issues, and architectural risks.

Automate Gmail: send/reply, search, labels, drafts, and attachments.

Control the user's actual browser through the browse-now CLI when a task needs authenticated pages, dynamic interaction, form filling…

Operate a persistent headless Chromium browser via the `browse` CLI for web automation, content extraction, scraping, and page interaction.

Search a store's catalog, prices and policies over its UCP/MCP backend, strictly read-only

Root-cause fix for browser click loops. Combines 4 top community solutions: (1) AXTree over raw HTML, (2) Stagehand hybrid code+AI, (3)…

Drive Browserbase cloud browser sessions via the browse CLI when local automation is blocked.

Automate browser interactions, test web pages, and verify browser-runtime behavior.

Native Rust browser automation CLI for AI agents.

Test across multiple browsers and devices for cross-browser compatibility.

Full browser control for authenticated web interactions using Playwright scripts

Capture browser console, network, and performance logs for debugging.

Inspect and debug live web pages using the Chrome DevTools Protocol via the `bdg` CLI.

Download files from authenticated web sessions.

Always use browser-harness for any web interaction: automation, scraping, testing, or site/app work.

Guide AI agents in creating Browser Library tests using Playwright-powered automation with auto-waiting, assertion engine, and modern web…

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…

Discover project routes/URLs BEFORE planning browser navigation.

This skill should be used when users need to capture screenshots of web pages.

Browser automation using local browser profile