agent-browser

Automate browser tasks with persistent sessions and element references.

16|3|Updated May 5, 2026
One-click install
npx skills add https://github.com/Kevin-Liu-01/Agent-Machines --skill agent-browser-kevin-liu-01
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/Kevin-Liu-01/Agent-Machines/tree/main/knowledge/skills/agent-browser
Command: npx skills add https://github.com/Kevin-Liu-01/Agent-Machines --skill agent-browser-kevin-liu-01

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates repetitive browser-based tasks with persistent session continuity, eliminating the need to re-authenticate or recreate context across navigations.

Core Features & Use Cases

  • Persistent sessions: maintain browser state across tasks and navigations.
  • Element refs: snapshot and reuse element references for reliable interactions.
  • Batch operations: execute multiple steps in sequence with minimal overhead.
  • Use Case: Open a site, log in, extract data, and take screenshots across pages.

Quick Start

Open a URL and capture an element, then interact with it using stored references.

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 tasks while keeping a persistent session across navigations?

Persistent browser automation maintains your browser state across tasks and navigations, eliminating the need to re-authenticate. It applies to web scraping, form filling, and UI testing workflows by leveraging CDP-capable browsers for session continuity.

How does element reference snapshotting work for reliable UI testing interactions?

Element references snapshot and reuse specific browser elements for reliable interactions during UI testing. This mechanism allows automated workflows to consistently target and interact with captured elements across multiple batch execution steps with minimal overhead.

Do I need a CDP-capable browser to run automated web scraping workflows?

Yes, a CDP-capable browser is required to run automated web scraping workflows with persistent sessions. The automation process relies on the Chrome DevTools Protocol to maintain state, execute batch operations, and support element references during navigation.

What is the best way to open a site, log in, and extract data across multiple pages?

The best way to extract data across multiple pages is using persistent session automation with batch operations. You can open a URL, log in once, and then execute multiple steps in sequence to take screenshots and scrape data without recreating context.

Can I execute multiple automated browsing steps in sequence without losing context?

Yes, batch operations allow you to execute multiple automated browsing steps in sequence with minimal overhead. Persistent session continuity ensures you do not lose authentication context or browser state when navigating across different pages.

Why does my automated browser workflow lose its login state between navigations?

Standard browser workflows lose login state because they do not maintain persistent sessions. Using a CDP-capable browser with session management and element references eliminates the need to re-authenticate or recreate context across navigations.