browser▌

Browser automation with page reuse, persistent cookies, and comprehensive interaction commands. \n \n Supports navigation, clicking, form filling, screenshots, content extraction, element waiting, and JavaScript execution \n Reuses existing pages by default and maintains login state through persistent user data directories \n Includes 20+ functions covering page operations, interactions, waiting, data retrieval, and advanced actions like file uploads and keyboard input \n Accepts CSS selectors a

Deterministic browser automation for AI agents with snapshot-based element references and multi-session support. \n \n Interact with web pages using stable element refs (@e1, @e2, etc.) generated from snapshots, enabling reliable automation across DOM changes \n Core commands cover navigation, form filling, clicking, waiting, screenshots, PDFs, and visual regression testing via baseline comparison \n Supports parallel isolated sessions, network-aware waits (networkidle), and selector-based targe

popo-document-browser

agent-browser

Invisible Chrome automation via CDP. Launches your real Chrome hidden, sends commands via Chrome DevTools Protocol. Sites see a normal browser - no detectable automation.

Browser automation and end-to-end testing using Vercel's agent-browser CLI. Uses ref-based element targeting for reliable, AI-friendly browser interaction.

Minimal CDP tools for collaborative site exploration and scraping.

The Skills CLI (npx adspower-browser) is the package manager for operate AdsPower browser profiles, groups, proxies, and application/category lists via the adspower-browser CLI. For more infomation about out product and services, visit AdsPower Official Website

Use agent-browser as the default CLI for deterministic UI checks.

This skill documents best practices for using agent-browser's built-in Kernel provider (-p kernel) for cloud browser automation.