skills.rest
Spagestic
SpagesticCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

Automate browser navigation, form filling, screenshots, and data extraction.

4|1|Updated Oct 17, 2025
Search Tags:#testing#data extraction#screenshots#browser automation#web scraping#form filling
One-click install
npx skills add https://github.com/Spagestic/thenorthstar --skill agent-browser-spagestic
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/Spagestic/thenorthstar/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/Spagestic/thenorthstar --skill agent-browser-spagestic

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 for tasks like web testing, form filling, data extraction, and capturing screenshots without manual intervention.

Core Features & Use Cases

  • Web Navigation: Open URLs, go back/forward, reload pages.
  • Element Interaction: Click, fill forms, type, check/uncheck, select options.
  • Data Extraction: Get text, HTML, attributes, and count elements.
  • Screenshots & PDF: Capture full-page screenshots or save pages as PDFs.
  • Use Case: Automate the process of logging into a web application, filling out a complex form, and submitting it, then taking a screenshot of the confirmation page.

Quick Start

Use the agent-browser skill to open the URL 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 intervention?▼

Automate web scraping and form filling by executing command-line browser actions that navigate URLs, interact with elements, and extract text or HTML. This enables deterministic web task execution for data extraction and automated form submission without manual intervention.

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

Yes, you can capture full-page screenshots and save web pages as PDFs through automated browser navigation. The tool opens the target URL and renders the page state to capture the complete visual output for testing or archival purposes.

What is the best way to manage browser state and network control for web testing?▼

The best way to manage browser state and network control for web testing is using deterministic browser automation. It supports navigation, element interaction, and state management to ensure consistent, repeatable task execution across test runs.

Does browser automation support clicking, typing, and selecting options on dynamic pages?▼

Browser automation supports clicking, typing, and selecting options on dynamic pages through direct element interaction. It handles checkboxes, form inputs, and dropdown selections, allowing automated navigation and interaction with complex web applications.

How do I extract text and attributes from web pages during browser automation?▼

Extract text and attributes from web pages during browser automation by targeting specific elements. The tool retrieves text content, HTML structure, and attribute values, and can count elements to validate page state during automated testing workflows.

Do I need any external browser dependencies to run automated web tasks?▼

No external browser dependencies are required to run automated web tasks. The Skill operates independently with its internal scripts and assets, executing specified browser actions and targets directly via the command line for deterministic task execution.

Related Skills

Explore More Software Engineering Skills→
fbrierfbrier

agent-browser

Automate browser interactions for web testing, form filling, and data extraction.

Community
Advanced
xberg-ioxberg-io
26

extracting-metadata

Extract titles, descriptions, language, and Open Graph tags from HTML documents.

Official
Intermediate
rkumar261rkumar261
1

gstack

Drive a headless browser to navigate pages, interact with UI elements, and verify state.

Community
Advanced
otrebuotrebu
4

web-to-markdown

Batch-convert JavaScript-rendered web pages to a timestamped Markdown file.

Community
Advanced