skills.rest
itgoyo
itgoyoCOMMUNITY
Explore all skills by this author →
Website𝕏@itgoyoGitHub

agent-browser

Automate browser testing, form filling, and data extraction with snapshot and ref-based interactions.

Updated Jan 13, 2026
Search Tags:#automation#interaction#web-testing#browser#data-extraction#markdown-table
One-click install
npx skills add https://github.com/itgoyo/agent-browser-skill --skill agent-browser-itgoyo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/itgoyo/agent-browser-skill/tree/main
Command: npx skills add https://github.com/itgoyo/agent-browser-skill --skill agent-browser-itgoyo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manual web testing, data collection, and form automation are time-consuming and error-prone. This Skill streamlines browser interactions by providing a consistent set of commands to navigate pages, capture elements, fill inputs, execute actions, and extract data in structured formats.

Core Features & Use Cases

  • Automate navigation, element snapshotting, and ref-based interactions for reliable UI testing.
  • Extract text, titles, and URLs, and render results as markdown tables for reporting.
  • Support authentication flows, dynamic content handling, and multiple concurrent sessions for scalable testing.

Quick Start

Open a URL with agent-browser and snapshot the page to identify interactive elements.

Frequently Asked Questions about agent-browser

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate browser tasks like web testing and form filling?▼

Web data extraction can be automated by navigating to URLs, capturing interactive elements via snapshots, and extracting text, titles, and URLs. Results are rendered as markdown tables, providing structured and readable reporting for your extracted data.

Does browser automation work with dynamic content and authentication flows?▼

Yes, browser automation handles dynamic content and authentication flows using snapshot and ref-based interactions. This ensures reliable execution of multi-session workflows while maintaining robust error handling during complex navigation and login sequences.

Can I run multiple concurrent browser sessions for scalable testing?▼

Multiple concurrent browser sessions are supported for scalable testing. This allows you to execute parallel web testing and data extraction workflows simultaneously, maintaining deterministic commands and optional JSON output across all active sessions.

What is the best way to extract web page data into a markdown table?▼

The best way to extract web page data into a markdown table is to use automated browser interactions that capture text, titles, and URLs. The skill directly renders these extracted elements into structured markdown tables for immediate reporting.

Do I need external dependencies to run automated web testing and data extraction?▼

No external dependencies are required to run automated web testing and data extraction. The skill operates independently to deliver deterministic browser commands, handle multi-session workflows, and output structured data without additional component installations.

Related Skills

Explore More Software Engineering Skills→
JuanMS20JuanMS20

github-auth

Configure GitHub authentication for Hermes Agent using git, gh CLI, or SSH credentials.

Community
Intermediate
alibabaalibaba
10.5k

pdf-extractor

Extract text, tables, and metadata from PDF documents into JSON.

Official
Intermediate
hepai-labhepai-lab
21

playwright-cli

Automate browser interactions and testing tasks using the Playwright CLI.

Community
Advanced
zerwizzerwiz

scrapling

Extract web content from static, dynamic, and protected pages via Python and CLI.

Community
Advanced