agent-browser

Automate web interactions including navigation, form submission, and data scraping.

Updated Feb 23, 2026
One-click install
npx skills add https://github.com/BozhidarN7/ds-algo-visualizer --skill agent-browser-bozhidarn7
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/BozhidarN7/ds-algo-visualizer/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/BozhidarN7/ds-algo-visualizer --skill agent-browser-bozhidarn7

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill eliminates the tedious manual work of interacting with websites, scraping data, testing web applications, and automating repetitive browser tasks for AI agents, saving hours of manual effort for developers, QA testers, and data professionals.

Core Features & Use Cases

  • Full Browser Automation: Navigate pages, fill forms, click buttons, take screenshots, capture PDFs, and execute any browser action programmatically with element reference tracking to reduce context usage.
  • Data Extraction & Testing: Scrape structured data from web pages, run end-to-end tests for web apps, and capture visual evidence like recordings and annotated screenshots for debugging and documentation.
  • Use Case: Imagine you need to test a login flow with two-factor authentication for a SaaS app, scrape product pricing data from 100 e-commerce pages, or automate form submissions for a user registration process. This Skill handles all these tasks reliably with session persistence and state management.

Quick Start

Use the agent-browser skill to open a target e-commerce website, extract all product names and prices from the page, and save the data to a local text file.

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 for an AI agent?

You can automate web scraping and form filling by using browser automation commands that navigate pages, submit forms, and extract structured data programmatically with session persistence and element reference tracking.

Can I run end-to-end web app testing with login flows and two-factor authentication?

Yes, end-to-end web app testing supports automated login flows with two-factor authentication by managing isolated sessions and handling authentication state persistence without manual intervention.

How does browser automation handle session persistence and authentication state?

Browser automation manages session persistence by maintaining isolated sessions and storing authentication state, allowing AI agents to execute multi-step browser commands without repeatedly logging in.

What's the best way to scrape product pricing data from multiple e-commerce pages?

The best way to scrape product pricing data is using programmatic browser interaction to navigate e-commerce pages, extract structured data, and save the captured content locally with reduced context usage.

Do I need a specific CLI tool to automate browser tasks and capture screenshots?

Yes, you need the agent-browser CLI tool to execute browser commands, take screenshots, capture PDFs, and manage isolated sessions for web automation tasks.

Can I capture visual evidence like annotated screenshots during web testing?

Yes, web testing supports capturing visual evidence including annotated screenshots and recordings for debugging and documentation during automated browser interaction sessions.