agent-browser

Control Chrome or Chromium via CLI using accessibility-tree snapshots and element references.

1|Updated Jun 27, 2026
One-click install
npx skills add https://github.com/babually/bongo-template --skill agent-browser-babually
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/babually/bongo-template/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/babually/bongo-template --skill agent-browser-babually

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you control websites and browser-based apps programmatically when you need to navigate pages, interact with elements, or verify web behavior without doing the work manually.

Core Features & Use Cases

  • Website Interaction: Open pages, click buttons, fill forms, and submit workflows in a real browser.
  • Testing and QA: Validate web apps, reproduce bugs, take screenshots, and inspect page state during exploratory testing.
  • Cross-App Automation: Automate Electron desktop apps like Slack, Discord, VS Code, Figma, Notion, and Spotify, plus supported cloud browser environments.

Quick Start

Use the agent-browser skill to open the target website and complete the requested browser interaction step by step.

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 web scraping without manual effort?

Automate browser tasks by controlling Chrome or Chromium through a CLI with accessibility-tree snapshots and element references. This approach handles website navigation, form filling, clicking, and scraping programmatically without manual effort.

What is the best way to automate Electron desktop apps like VS Code or Slack?

The best way to automate Electron desktop apps is by using browser automation techniques that leverage accessibility-tree snapshots. This method applies to automating Slack, Discord, VS Code, Figma, Notion, and Spotify by interacting with their underlying Chromium engine.

Can I use browser automation for web testing and QA screenshots?

Yes, browser automation supports web testing and QA screenshots. By controlling a real browser session, you can validate web apps, reproduce bugs, capture screenshots, and inspect the page state during exploratory testing.

Do I need to manage browser sessions and authentication for web scraping?

Yes, reliable web scraping requires browser session management and optional authentication handling. These capabilities ensure your automated browser interactions maintain state and successfully access protected pages.

How does browser automation interact with web pages using accessibility-tree snapshots?

Browser automation interacts with web pages using accessibility-tree snapshots by generating element references. This allows precise control over Chrome or Chromium, enabling targeted clicking, form filling, and navigation without relying on visual coordinates.

Does this browser automation approach work with cloud browser environments?

Yes, this browser automation approach works with supported cloud browser environments. It controls Chrome or Chromium instances through CLI commands and accessibility-tree snapshots, making it applicable for remote web testing and scraping workflows.