agent-browser

Control browsers programmatically via Chrome DevTools Protocol for testing and automation.

211|9|Updated Dec 16, 2025

Search Tags:#automation #testing #devtools #scraping #browser #web #selenium

Ready to run

npx skills add https://github.com/nexxeln/opencode-config --skill agent-browser-nexxeln

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/nexxeln/opencode-config/tree/main/skill/agent-browser
Command: npx skills add https://github.com/nexxeln/opencode-config --skill agent-browser-nexxeln

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Automates complex browser tasks including navigation, data extraction, form filling, and testing, simplifying web interactions for users and developers.

Core Features & Use Cases

Web Interaction Automation: Navigates pages, clicks buttons, fills forms, and captures screenshots to streamline testing and data collection.
Content Extraction and Analysis: Retrieves page text, DOM structure, and visual changes, facilitating content audits and verification.
Use Case: Automate login workflows, validate webpage layouts, or scrape data from multiple pages efficiently.

Quick Start

Request the agent-browser skill to open a website, wait for content, and take a 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 form filling and capture screenshots for testing?▼

Web form filling and screenshot capture are automated using programmable browser control. This skill manages navigation, clicks, and form submissions, enabling repeatable testing and data collection workflows across various web environments.

Can I use Chrome DevTools Protocol for headless browser scraping and debugging?▼

Chrome DevTools Protocol enables high-fidelity browser scraping and debugging. This skill supports both headless and headed modes, allowing detailed DOM inspection, content extraction, and network monitoring without a graphical interface.

Does browser automation support proxy configurations and authentication?▼

Proxy configuration and authentication are fully supported during browser automation. The skill manages complex session states, allowing automated login workflows and authenticated scraping behind corporate proxies or restricted networks.

What is the best way to extract page text and DOM structure for content audits?▼

Extracting page text and DOM structure for content audits is handled through detailed content retrieval commands. The skill retrieves visual changes and structural data, facilitating automated verification of webpage layouts and text.

Are there limitations when running automated web interactions across multiple pages?▼

Automated web interactions across multiple pages require session management to maintain reliability. While the skill handles repeatable workflows, complex dynamic content may need explicit wait commands to ensure elements load before extraction.

Do I need external dependencies to monitor webpage performance during automation?▼

Monitoring webpage performance during automation does not require external dependencies. The skill utilizes built-in browser protocols to track visual changes and network metrics directly within the controlled session.