skills.rest
gvkhosla
gvkhoslaCOMMUNITY
Explore all skills by this author →
Website𝕏@geetkhoslaGitHub

agent-browser

Automate browser navigation, form filling, clicking, and data scraping via accessibility snapshots.

49|4|Updated Feb 12, 2026
Search Tags:#AI agent#browser automation#CLI#web scraping#form filling#headless browser
One-click install
npx skills add https://github.com/gvkhosla/compound-engineering-pi --skill agent-browser-gvkhosla
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/gvkhosla/compound-engineering-pi/tree/main/plugins/compound-engineering/skills/agent-browser
Command: npx skills add https://github.com/gvkhosla/compound-engineering-pi --skill agent-browser-gvkhosla

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates browser interactions, allowing AI agents to navigate websites, fill forms, click elements, and extract data without manual intervention.

Core Features & Use Cases

  • Web Automation: Programmatically control a headless browser for tasks like form submission, data scraping, and screenshotting.
  • AI-Friendly Interaction: Utilizes accessibility snapshots and ref-based element selection for reliable AI control.
  • Use Case: Automate the process of logging into a web application, filling out a multi-step form, and taking a screenshot of the confirmation page.

Quick Start

Use the agent-browser skill to open the URL https://example.com and take a screenshot.

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 scraping and form filling with an AI agent?▼

AI agent browser automation handles web scraping and form filling by utilizing the agent-browser CLI to navigate sites, click elements, and extract data without manual intervention.

What is accessibility snapshot-based element selection for browser automation?▼

Accessibility snapshot-based element selection captures page structure to generate ref-based locators, allowing AI agents to reliably identify and interact with web elements during headless browser tasks.

Can I run parallel browser sessions for concurrent web automation tasks?▼

Parallel browser sessions are supported, enabling concurrent execution of multiple web automation tasks like data scraping and form submission through the agent-browser CLI.

How do I debug headless browser automation scripts when elements are not clicking?▼

Debug headless browser automation by enabling the visible browser window option, allowing you to monitor navigation, form filling, and element clicking behavior in real-time.

Does AI-driven browser automation require manual element locator configuration?▼

AI-driven browser automation does not require manual element locator configuration, as it uses accessibility snapshots and ref-based locators to dynamically identify interactive elements.

Related Skills

Explore More Software Engineering Skills→
AshesOfTheUndeadAshesOfTheUndead

Agent Browser

Automate headless browser navigation, element manipulation, and data extraction via CLI.

Community
Advanced
xberg-ioxberg-io
26

extracting-metadata

Extract titles, descriptions, language, and Open Graph tags from HTML documents.

Official
Intermediate
acarmonagacarmonag
2

browser

Automate web browser interactions and data extraction using accessibility snapshots.

Community
Advanced
rmarino550rmarino550

browse

Automate web page navigation and interaction with headless Chromium via Playwright.

Community
Advanced