agent-browser

Automate browser interactions via command-line interface for navigation, form filling, and data extraction.

Updated Feb 5, 2026
One-click install
npx skills add https://github.com/tc9011/my-skills --skill agent-browser-tc9011
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/tc9011/my-skills/tree/main/skills/agent-browser
Command: npx skills add https://github.com/tc9011/my-skills --skill agent-browser-tc9011

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates browser interactions, allowing AI agents to navigate websites, fill forms, extract data, and perform complex web-based tasks programmatically.

Core Features & Use Cases

  • Web Navigation: Open, close, and navigate between web pages.
  • Form Interaction: Fill text fields, select dropdowns, check boxes, and submit forms.
  • Data Extraction: Scrape text content, attributes, and structured data from web pages.
  • Screenshots & PDFs: Capture full-page screenshots or save pages as PDFs.
  • Use Case: An AI agent can use this Skill to log into a user's account, fill out a complex application form, and then scrape the confirmation details.

Quick Start

Use agent-browser to open the website '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?

Automating web scraping and form filling is achieved through a command-line interface that supports navigation, element interaction, and text extraction. You use semantic locators and JavaScript evaluation to execute deterministic web tasks programmatically.

Can I capture full-page screenshots and save web pages as PDFs via CLI?

Yes, capturing full-page screenshots and saving web pages as PDFs are supported features. The CLI enables an AI agent to command the browser to capture visual outputs or generate document files directly from the target URL.

Does browser automation CLI support JavaScript evaluation for data extraction?

JavaScript evaluation is supported for data extraction, allowing precise retrieval of text content and attributes. This ensures deterministic web task execution by interacting with page elements through semantic locators or direct script evaluation.

What is the best way to extract structured data from web pages programmatically?

The best way to extract structured data is using a CLI designed for browser automation. It allows AI agents to navigate target pages, locate elements via refs or semantic locators, and scrape text content and attributes reliably.

How do AI agents interact with web elements using this browser automation tool?

AI agents interact with web elements by referencing element refs, semantic locators, or evaluating JavaScript. This allows the agent to fill text fields, select dropdowns, check boxes, and submit complex application forms programmatically.

Can I use this tool to log into a user account and submit complex forms?

Yes, you can log into accounts and submit complex forms. The tool provides command-line interactions for filling text fields, selecting dropdowns, and checking boxes, enabling AI agents to complete multi-step web-based tasks.