skills.rest
patrickhaahr
patrickhaahrCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

Browse web pages, inspect accessibility trees, and interact with UI elements via CLI.

Updated Jun 15, 2025
Search Tags:#automation#accessibility#cli#snapshot#web-automation#headless-browser#ui-interaction
One-click install
npx skills add https://github.com/patrickhaahr/dotfiles --skill agent-browser-patrickhaahr
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/patrickhaahr/dotfiles/tree/main/opencode/.config/opencode/skills/agent-browser
Command: npx skills add https://github.com/patrickhaahr/dotfiles --skill agent-browser-patrickhaahr

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI agents often struggle to autonomously navigate, inspect, and interact with modern web pages. agent-browser provides a CLI workflow to browse URLs, view accessibility trees, and perform UI actions without manual browser control.

Core Features & Use Cases

  • Navigate to URLs and iterate across pages or sessions.
  • Snapshot the accessibility tree to identify interactive elements and reference IDs.
  • Interact with elements via click, type, fill, and keyboard actions; capture screenshots for verification.
  • Automate frontend testing, accessibility analysis, and data gathering across dynamic pages.

Quick Start

Open a page: agent-browser open https://example.com Take a snapshot: agent-browser snapshot Interact: agent-browser click @5 Capture a screenshot: agent-browser screenshot page.png

Frequently Asked Questions about agent-browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate web page interaction with AI agents using a CLI?▼

You can automate web page interaction by using a CLI workflow to open URLs, inspect accessibility trees, and execute UI actions like click, type, and fill. This enables deterministic workflows without manual browser control.

How does an accessibility tree snapshot help with frontend UI automation?▼

An accessibility tree snapshot identifies interactive frontend UI elements and their reference IDs. This allows automated agents to target specific elements for clicking, typing, and filling during dynamic web page testing.

Can I capture screenshots during automated web testing workflows?▼

Yes, you can capture screenshots for verification during automated web testing workflows. The CLI supports taking screenshots of pages to verify UI interactions and visual states after executing actions.

What is the best way to gather data across dynamic web pages without manual browser control?▼

The best way to gather data across dynamic pages is using a CLI workflow that navigates URLs, snapshots accessibility trees, and interacts with forms. This enables autonomous data gathering without manual browser control.

Does headless browser automation work for accessibility analysis on dynamic pages?▼

Yes, headless browser automation supports accessibility analysis on dynamic pages. By inspecting the accessibility tree and interacting with UI elements, agents can evaluate and analyze frontend accessibility.

What are the limitations of using a CLI for web automation compared to manual browser control?▼

Using a CLI for web automation relies on deterministic workflows and accessibility tree snapshots rather than visual inspection. This means complex visual interactions or non-accessible elements may present limitations compared to manual control.

Related Skills

Explore More Software Engineering Skills→
majiayu000majiayu000
258

playwright-automation

Automate browser interactions and UI validation for web applications using Playwright.

Community
Intermediate
archibatearchibate
6

slack

Automate Slack web workspace interactions to read messages and extract channel metadata.

Community
Intermediate
Devsoul2026Devsoul2026
150

instructor

Extract structured data from LLM responses with Pydantic validation and automatic retries.

Community
Advanced
Ikram-AlamIkram-Alam

browsing-with-playwright

Automate browser tasks via a Playwright MCP server for navigation, form filling, and data extraction.

Community
Advanced