skills.rest
n4vysh
n4vyshCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

agent-browser

Automate browser interactions via Chrome/Chromium CDP for AI agents.

5|Updated Apr 29, 2023
Search Tags:#automation#testing#cdp#browser#ai-agents#accessible-refs
One-click install
npx skills add https://github.com/n4vysh/dotfiles --skill agent-browser-n4vysh
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/n4vysh/dotfiles/tree/main/home/dot_agents/skills/agent-browser
Command: npx skills add https://github.com/n4vysh/dotfiles --skill agent-browser-n4vysh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI agents often need to perform browser-based tasks such as navigating web apps, filling forms, taking screenshots, validating UI, and testing interfaces. This skill provides a fast, Rust-based CLI to automate those tasks via Chrome/Chromium CDP, with accessible element refs and reliable session handling.

Core Features & Use Cases

  • Native Rust CLI for reliable, fast browser automation.
  • Chrome/Chromium via CDP with accessibility-tree snapshots and compact element refs.
  • Sessions, authentication vault, state persistence, and optional video recording.
  • Specialized skills for Electron apps, Slack, exploratory testing, cloud providers, and QA workflows.
  • Use cases include automated QA tests, regression checks, data extraction from web pages, and repetitive web-navigation tasks for AI agents.

Quick Start

Install agent-browser globally and load core workflows with agent-browser skills get core.

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 for AI agents?▼

You can automate browser interactions for AI agents using a Rust-based CLI that drives Chrome/Chromium via CDP, enabling tasks like navigating pages, filling forms, taking screenshots, and extracting data with accessibility-tree snapshots.

Does this browser automation tool support Electron apps?▼

Yes, browser automation supports testing across web and Electron apps. It includes specialized skills for Electron apps, Slack, exploratory testing, cloud providers, and QA workflows to handle diverse automated testing environments.

How do I maintain state and sessions when automating web apps?▼

You can maintain state and sessions during web app automation using built-in session handling, state persistence, and an authentication vault, ensuring reliable and continuous interactions across multiple navigation tasks.

What is the best way to extract data from web pages using AI agents?▼

The best way to extract data from web pages with AI agents is using a Rust-based CLI with Chrome/Chromium CDP, which provides accessibility-tree snapshots and compact element refs for reliable, fast data extraction.

Can I record video of automated QA tests and regression checks?▼

Yes, you can record video of automated QA tests and regression checks. The runtime includes optional video recording features to support secure, auditable workflows during repetitive web-navigation tasks.

Do I need a Rust-based CLI to run automated browser testing?▼

Yes, a Rust-based CLI and the agent-browser runtime are required to run automated browser testing. This setup provides fast, scriptable automation and reliable session handling via Chrome/Chromium CDP.

Related Skills

Explore More Software Engineering Skills→
ChromeDevToolsChromeDevTools
48.8k

chrome-devtools

Control Chrome DevTools via MCP for debugging and browser automation.

Official
Intermediate
skwuwuskwuwu

gvm_audit

Verify GVM audit log integrity and export compliance reports.

Community
Intermediate
zerAdazerAda

bmad-qa-generate-e2e-tests

Generate end-to-end API and UI tests for identified application features.

Community
Advanced
AradotsoAradotso
70

lightpanda-browser

Provide a Zig-based headless browser with CDP support for automation.

Official
Intermediate