agent-browser

Automate browser interactions with a CLI for navigation, form filling, and data extraction.

7|4|Updated Jun 7, 2025
One-click install
npx skills add https://github.com/lootlog/monorepo --skill agent-browser-lootlog
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/lootlog/monorepo/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/lootlog/monorepo --skill agent-browser-lootlog

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Browser automation for AI agents is often manual and repetitive; this skill provides a CLI to navigate websites, fill forms, click elements, take screenshots, extract data, and test web apps, reducing manual effort.

Core Features & Use Cases

  • Automates browsing sessions: open URLs, snapshot structure, interact with elements via refs, and perform tasks end-to-end.
  • Data extraction and verification: capture page text, titles, URLs, and generate evidence for QA or audits.
  • Use Case: quickly assemble a reproducible web-test workflow that logs in, navigates to a dashboard, and records evidence in a single run.

Quick Start

Open a webpage with agent-browser, snapshot to discover element refs, then interact using those refs to automate common tasks.

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 tasks using a CLI for browser navigation and data extraction?

Browser automation via CLI lets you open URLs, snapshot page structure, interact with elements using refs, fill forms, click elements, and extract data for end-to-end workflows. You can automate login flows, navigate dashboards, and record evidence in a single run.

How do I fill forms and click elements during web testing without manual effort?

To fill forms and click elements during web testing, you snapshot the webpage to discover element refs, then issue CLI commands to interact using those refs. This allows you to automate repetitive browsing sessions and build reproducible test workflows.

Can I use browser automation to record evidence and capture page data for QA audits?

Yes, browser automation can capture page text, titles, URLs, and take screenshots to generate evidence for QA audits. It automates data extraction and verification across diverse websites and apps, reducing manual effort in quality assurance processes.

Does this browser automation CLI require any external dependencies to run?

No, this browser automation CLI requires no external dependencies to run. It provides built-in commands like open, snapshot, fill, click, wait, and screenshot to automate navigation and data extraction tasks across diverse websites and apps.

What is the best way to scrape data and automate login flows across diverse websites?

The best way to scrape data and automate login flows is using a CLI tool that snapshots page structures to locate elements via refs, then automates the clicking and form filling sequence end-to-end. This approach handles diverse websites and apps seamlessly.

Why does my browser automation workflow fail to interact with elements after opening a URL?

Browser automation workflows fail to interact with elements if you do not snapshot the page structure to discover element refs first. You must open the URL, snapshot to capture the structure, then use the returned refs to fill forms and click elements accurately.