agent-browser

Automate Chrome and Electron browser interactions via command-line accessibility targeting.

248|30|Updated Feb 18, 2026
One-click install
npx skills add https://github.com/cafe3310/public-agent-skills --skill agent-browser-cafe3310
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/cafe3310/public-agent-skills/tree/main/skills/agent-browser
Command: npx skills add https://github.com/cafe3310/public-agent-skills --skill agent-browser-cafe3310

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the complexity of browser and Electron application automation by giving AI agents a reliable way to navigate, inspect, and interact with user interfaces.

Core Features & Use Cases

  • Browser Automation: Control Chrome or Chromium sessions through a fast CLI with accessibility-tree snapshots and compact element references.
  • Agent-Oriented Workflows: Support web navigation, element interaction, authentication state handling, and repeatable browser tasks for AI agents.
  • Electron Support: Extend automation workflows to desktop applications such as VS Code, Slack, Discord, and Figma.
  • Use Case: Use this Skill when an AI agent needs to complete website workflows, test interfaces, or operate browser-based applications reliably.

Quick Start

Ask the agent-browser skill to automate a browser workflow and retrieve the required interaction instructions before running commands.

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 for AI agents using Chrome or Chromium?

Browser automation for AI agents is handled through a command-line interface that controls Chrome or Chromium sessions. It uses accessibility-tree snapshots and compact element references to navigate, inspect, and interact with web pages reliably.

Can I automate Electron desktop applications like VS Code or Slack?

Electron application automation supports desktop apps like VS Code, Slack, Discord, and Figma. It extends browser interaction workflows to these desktop environments using accessibility-based element targeting via the CLI.

What do I need to set up before running browser automation workflows?

Running browser automation requires the agent-browser CLI, Chrome or Chromium connectivity, and Node.js availability. These components provide the execution environment needed to support reliable interaction workflows.

How does the CLI handle web navigation and element interaction?

The CLI handles web navigation and element interaction by capturing accessibility-tree snapshots. This provides AI agents with compact element references to execute clicks, inputs, and authentication state handling accurately.

Is this approach suitable for UI testing and repeatable website workflows?

UI testing and repeatable website workflows are core use cases. The CLI provides stable, accessibility-based element targeting that allows AI agents to execute navigation and interaction tasks consistently across multiple runs.

Why use accessibility-tree snapshots instead of traditional CSS selectors for web automation?

Accessibility-tree snapshots provide compact element references that are more reliable than CSS selectors. This approach ensures AI agents can consistently target and interact with UI elements during navigation workflows and UI testing.