agent-browser

Automate browser interactions and capture web content across isolated sessions.

1|Updated Apr 19, 2026
One-click install
npx skills add https://github.com/arthtyagi/onloop --skill agent-browser-arthtyagi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/arthtyagi/onloop/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/arthtyagi/onloop --skill agent-browser-arthtyagi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Agent-browser removes the manual, error-prone work of navigating websites, filling forms, extracting information, and checking UI behavior by giving agents precise control over live browser sessions.

Core Features & Use Cases

  • Interactive snapshots provide compact refs for clicking, typing, selecting, hovering, and reading page state without brittle selectors.
  • Session management, saved state, authentication helpers, proxy settings, and tab or frame controls support realistic workflows across multiple browsing contexts.
  • Screenshots, PDF export, video recording, network inspection, and JavaScript evaluation make it useful for QA, scraping, demo capture, and debugging.
  • Example use case: log into a web app once, reuse the saved session, validate a checkout flow, and capture a full-page screenshot for review.

Quick Start

Open the target site, take an interactive snapshot, and use the returned refs to click, fill, or extract exactly what you need.

Frequently Asked Questions about agent-browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate browser interactions without using brittle CSS selectors?

Interactive snapshots provide compact refs for clicking, typing, and reading page state without brittle selectors. This enables reliable low-token automation across isolated browser sessions for web testing, form filling, and scraping.

Can I reuse authentication sessions and saved login state for web testing?

Yes, session management and authentication helpers let you log into a web app once and reuse the saved state. This supports realistic web testing workflows across multiple isolated browsing contexts with proxy settings.

Does browser automation work with screenshots, PDF export, and video recording?

Yes, browser automation supports screenshots, PDF export, video recording, and network inspection. These features make it suitable for QA testing, web scraping, demo capture, and debugging across isolated browser sessions.

What is the best way to extract web content and fill forms during scraping?

Open the target site, take an interactive snapshot, and use the returned refs to click, fill, or extract exactly what you need. This approach provides precise control over live browser sessions for scraping and form filling.

Do I need proxy support and tab controls for realistic web testing workflows?

Proxy support and tab or frame controls are available to support realistic workflows across multiple browsing contexts. Combined with session persistence and authentication handling, they ensure accurate web testing and automation.

Why does web automation fail when using traditional selectors and how to fix it?

Traditional selectors are brittle and break on UI changes. Interactive snapshots provide compact refs for clicking, typing, and reading page state, ensuring reliable low-token automation that adapts to dynamic web content.