agent-browser

Automate browser navigation, form submission, data scraping, and screenshot capture via CLI.

2|Updated Feb 15, 2026
One-click install
npx skills add https://github.com/Crokily/pi-backup --skill agent-browser-crokily
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/Crokily/pi-backup/tree/main/external-skills/agent-browser
Command: npx skills add https://github.com/Crokily/pi-backup --skill agent-browser-crokily

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates interactions with web browsers, enabling users to navigate websites, fill forms, extract data, and perform complex web-based tasks programmatically.

Core Features & Use Cases

  • Web Navigation: Open URLs, go back/forward, reload pages.
  • Form Interaction: Fill text fields, select dropdowns, check boxes, click buttons.
  • Data Extraction: Scrape text content, attributes, and structured data from web pages.
  • Screenshots & PDFs: Capture full-page screenshots or save pages as PDFs.
  • Session Management: Run multiple isolated browser sessions concurrently.
  • Use Case: Automate the process of logging into a web application, filling out a multi-step form, and submitting it, then extracting the confirmation details.

Quick Start

Use the agent-browser skill to open the website 'https://example.com' and take a full-page 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 without manual browser interaction?

You can automate web scraping and form filling by using a command-line interface to programmatically navigate URLs, input text into fields, select dropdowns, and click buttons. This eliminates manual interaction by directly controlling the browser session.

Can I run multiple isolated browser sessions concurrently for web automation?

Yes, you can run multiple isolated browser sessions concurrently. The skill provides session management capabilities, allowing you to execute parallel automation tasks like concurrent web scraping or form submission without conflicts.

Does headless browser automation support proxy configuration and screenshots?

Headless browser automation supports proxy configuration and screenshots. You can route traffic through proxies and capture full-page screenshots or save pages as PDFs while running the browser without a graphical interface.

How do I extract structured data and text content from web pages using browser automation?

To extract structured data and text content, use the command-line interface to navigate to the target web page and scrape text content or attributes. The skill utilizes semantic locators to robustly identify and extract the required data.

What is the best way to automate multi-step form submission and extract confirmation details?

The best way to automate multi-step form submission is to use the command-line interface to sequentially fill text fields, select dropdowns, and click buttons across pages. After submitting, you can scrape the confirmation details directly from the resulting page.

How do semantic locators improve the reliability of web automation scripts?

Semantic locators improve web automation reliability by targeting elements based on meaningful attributes rather than fragile structural paths. This ensures scripts remain robust against minor layout changes during navigation, form filling, or data scraping.