agent-browser

Automates browser interactions and data extraction via snapshot refs and structured commands.

Updated Apr 27, 2026

Search Tags:#automation #cli #web-testing #browser #data-extraction #agent-browser #ref-snapshot

Ready to run

npx skills add https://github.com/Conradmaker/copilot-cockpit --skill agent-browser-conradmaker

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/Conradmaker/copilot-cockpit/tree/main/.github/skills/agent-browser
Command: npx skills add https://github.com/Conradmaker/copilot-cockpit --skill agent-browser-conradmaker

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill enables AI agents to automate complex browser tasks, including navigation, form interactions, data extraction, and visual/document capture, by providing a stable command surface and ref-based interactions.

Core Features & Use Cases

Deterministic browser automation: open pages, snapshot the DOM to generate stable element refs, then interact using those refs for reliable automation.
Data extraction and testing: capture text, URLs, titles, and screenshots to support QA, data collection, and documentation.
Workflow orchestration and state management: supports session management, authentication patterns, and optional script references to compose end-to-end tasks.

Quick Start

Open a target website, snapshot the page to capture element references, then interact with elements using those refs to automate a typical workflow.

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 form filling and web navigation using AI?▼

To automate browser tasks with AI, open a target website, snapshot the DOM to capture stable element references, then interact with elements using those refs to reliably execute form filling and web navigation workflows.

What is the best way to capture website data and screenshots for automated QA?▼

The best way to capture website data for automated QA is to use a structured command surface that snapshots the DOM, allowing you to capture text, URLs, titles, and screenshots deterministically via stable element references.

How does ref-based browser automation work for data extraction?▼

Ref-based browser automation generates stable element references by snapshotting the page DOM, then uses these references to execute reliable click, fill, and data extraction commands across websites without breaking interactions.

Can I manage authentication and session state for end-to-end web testing workflows?▼

Yes, you can manage authentication patterns and session state to compose end-to-end web testing workflows, organizing scripts, references, and assets to orchestrate deterministic tasks across multiple pages.

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

No external dependencies are required to run automated web testing and data capture; the skill provides a self-contained command surface for opening pages, snapshotting DOM elements, and interacting with them.

Why does my browser automation script fail when interacting with web elements?▼

Browser automation scripts often fail without stable element targeting; snapshotting the DOM to generate stable refs before interacting ensures deterministic click, fill, and data capture commands execute reliably.