agent-browser

Automate browser navigation, form filling, clicking, and screenshots for websites.

1|1|Updated Feb 9, 2026
One-click install
npx skills add https://github.com/przbadu/skills-factory --skill agent-browser-przbadu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/przbadu/skills-factory/tree/main/skills/agent-browser
Command: npx skills add https://github.com/przbadu/skills-factory --skill agent-browser-przbadu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill removes the friction of manual browser work by letting an AI reliably navigate websites, interact with page elements, and verify outcomes without guesswork.

Core Features & Use Cases

  • Web Navigation and Interaction: Open pages, click buttons, fill forms, select options, upload files, and handle dialogs.
  • Extraction and Verification: Capture screenshots, read page text and HTML, inspect element refs, and confirm state changes after actions.
  • Automation Workflows: Support login flows, authenticated sessions, proxy-based browsing, multi-session task isolation, and recorded runs for debugging.
  • Use Case: Use this Skill to log into a SaaS dashboard, submit a support form, extract the resulting confirmation details, and save evidence for later review.

Quick Start

Ask the skill to open the target website, inspect the page, and complete the requested browser action using the captured refs.

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 form filling and browser navigation without manual clicking?

Browser automation handles web navigation, form filling, and button clicking by using snapshot-based refs and semantic locators to interact with page elements reliably without manual input.

Can I maintain authenticated sessions across multiple browser automation tasks?

Yes, session management supports login flows, authenticated sessions, and multi-session task isolation, allowing state persistence across repeated browser automation runs on desktop and mobile Safari.

How does browser automation handle page elements for web testing?

Web testing uses snapshot-based refs and semantic locators to click buttons, select options, upload files, and handle dialogs, ensuring repeatable interaction with dynamic page elements.

What's the best way to capture screenshots and record browser sessions for debugging?

Session recording and screenshot capture document browser interaction runs, providing visual evidence and debugging output for automated workflows across desktop, local files, and mobile Safari.

Does this browser automation approach work with proxy-based browsing and network control?

Yes, proxy-based browsing and network control are supported, allowing repeatable session handling and multi-session task isolation for automated web interaction workflows.

Why do I need semantic locators and snapshot-based refs for web automation?

Semantic locators and snapshot-based refs provide precise element targeting, removing guesswork from browser automation by ensuring actions hit the correct page elements during navigation and form filling.