agent-browser

Automate browser navigation, form filling, and data extraction via Chrome CDP.

Updated Nov 26, 2025
One-click install
npx skills add https://github.com/Aias/dotfiles --skill agent-browser-aias
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/Aias/dotfiles/tree/main/agents/skills/agent-browser
Command: npx skills add https://github.com/Aias/dotfiles --skill agent-browser-aias

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates browser-based tasks to replace manual testing and repetitive web interactions, enabling consistent navigation, form filling, data extraction, and UI validation.

Core Features & Use Cases

  • Programmatic navigation with agent-browser commands (open, back, forward)
  • Snapshot-based element refs for deterministic interactions (click, fill, select, upload)
  • Screenshots, PDF capture, network monitoring, and debugging aids
  • Session and proxy management for multi-user workflows and geo-testing Use cases include automated login flows, data scraping, form automation, end-to-end UI checks, and cross-environment testing.

Quick Start

Open a page, snapshot to generate element refs, interact with the page using those refs, and verify the result.

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 like form filling and data extraction?

You can automate browser tasks by using programmatic commands for navigation, taking page snapshots to generate deterministic element refs, and executing interactions like click, fill, and select to extract data or validate UI.

How does snapshot-based element interaction work for web testing?

Snapshot-based element interaction works by capturing the page state and generating reliable refs for elements. These refs allow you to deterministically execute clicks, fill forms, and select options for consistent UI verification.

Can I manage browser sessions and proxies for multi-user workflows?

Yes, you can manage browser sessions and configure optional proxies. This supports multi-user workflows and allows for effective geo-testing across local, staging, and production environments.

What's the best way to capture screenshots and PDFs during browser automation?

The best way to capture screenshots and PDFs during browser automation is to use the built-in navigation and snapshot commands, which also support network monitoring and debugging aids for comprehensive UI checks.

Does browser automation via CDP work for end-to-end UI checks across environments?

Browser automation via CDP works effectively for end-to-end UI checks across local, staging, and production environments by using a native Rust daemon to control Chrome and manage repeatable web interactions like login flows.

Why use deterministic refs for browser scripting instead of standard selectors?

Deterministic refs generated from page snapshots provide more reliable browser control than standard selectors. They ensure consistent element targeting for interactions like form filling and data scraping during automated web testing.