agent-browser

Automate browser navigation, form filling, and page scraping via CLI.

7|1|Updated Jan 14, 2026

Search Tags:#screenshots #cli #browser automation #web scraping #form filling #headless browser

Ready to run

npx skills add https://github.com/eyadsibai/ltk --skill agent-browser-eyadsibai

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/eyadsibai/ltk/tree/main/plugins/ltk-devops/skills/agent-browser
Command: npx skills add https://github.com/eyadsibai/ltk --skill agent-browser-eyadsibai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates browser interactions directly from the command line, simplifying tasks like form filling, data scraping, and taking screenshots for AI agents.

Core Features & Use Cases

Headless Browser Automation: Control a Chromium browser programmatically.
Element Interaction: Navigate, click, fill forms, and scrape content using accessibility references.
Use Case: An AI agent needs to log into a web application, fill out a form, and then take a screenshot of the confirmation page. This Skill provides the commands to achieve this.

Quick Start

Use agent-browser 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 via a command line interface?▼

Browser automation via CLI allows AI agents to programmatically control a Chromium browser, enabling navigation, form filling, and page scraping. It uses a snapshot-and-reference pattern to select page elements and supports headless operation for unattended execution.

Can I run headless browser automation for unattended web scraping tasks?▼

Yes, headless browser automation supports unattended execution for web scraping and form filling. It operates a Chromium browser programmatically through a CLI interface, allowing AI agents to navigate pages and extract content without a graphical display.

How does the snapshot-and-reference pattern work for selecting web elements?▼

The snapshot-and-reference pattern captures page elements by their accessibility references rather than standard DOM selectors. This mechanism allows CLI commands to accurately identify and interact with navigation targets, form fields, and clickable elements during browser automation.

What is the best way to take screenshots during automated browser navigation?▼

Taking screenshots during automated browser navigation is handled directly through CLI commands. After an AI agent navigates to a target URL and completes interactions like form filling, the Skill captures the resulting page state as a screenshot for verification.

Do I need to install additional dependencies to run CLI browser automation?▼

No additional dependencies are required to run this CLI browser automation Skill. It operates independently to control a Chromium browser, enabling AI agents to execute headless navigation, form filling, and web scraping without external library setups.

Can an AI agent log into a web application and fill out forms automatically?▼

Yes, an AI agent can log into a web application and fill out forms automatically using CLI commands. The Skill controls the browser to navigate pages, populate form fields using accessibility references, and capture confirmation screenshots.