agent-browser

Automates browser tasks for AI agents via command-line interface and snapshot-based element refs.

3|2|Updated Sep 25, 2025
One-click install
npx skills add https://github.com/oci-ai-incubations/ai-accelerator-starter-packs --skill agent-browser-oci-ai-incubations
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/oci-ai-incubations/ai-accelerator-starter-packs/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/oci-ai-incubations/ai-accelerator-starter-packs --skill agent-browser-oci-ai-incubations

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Browser automation for AI agents to interact with websites, including navigating pages, filling forms, clicking elements, taking screenshots, extracting data, testing web apps, or automating browser tasks.

Core Features & Use Cases

  • Automated interactions: Navigate pages, fill forms, click elements, and capture data across sessions.
  • Data extraction & testing: Retrieve text, data, and verify page states for QA workflows and monitoring.
  • Use Case: Automate login flows, session management, and end-to-end webpage testing for dynamic apps.

Quick Start

Open agent-browser and navigate to a URL to start automating a task.

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 testing for dynamic web apps across multi-page flows?

Automate browser tasks for web testing by using a command-line interface to navigate pages, fill forms, click elements, and capture data across multi-page flows. It applies snapshot-based element refs to interact with dynamic content and extract data.

How does browser automation with snapshot-based element refs work?

Browser automation with snapshot-based element refs works by capturing a snapshot of the page state, assigning references to elements, and chaining CLI commands to interact with those refs. This ensures reliable targeting of dynamic elements across isolated sessions.

Can I automate login flows and session management for web testing?

Yes, you can automate login flows and session management for web testing. The tool applies session isolation to manage authentication states, allowing you to fill forms, click elements, and navigate across pages without session conflicts.

What's the best way to extract data and verify page states for QA workflows?

The best way to extract data and verify page states for QA workflows is to chain CLI commands that capture text and data from pages using snapshot refs. This approach retrieves content and validates page states for monitoring and testing dynamic web apps.

Does this browser automation tool support session isolation for concurrent tasks?

Yes, browser automation supports session isolation for concurrent tasks. It applies isolated sessions to each automation workflow, allowing you to run multiple browser tasks, form automations, and data extractions simultaneously without interference.

Why use a CLI for browser automation instead of traditional scripts?

Using a CLI for browser automation allows you to chain commands and apply snapshot-based refs to interact with dynamic web apps. It provides templates and references to guide automation workflows, reducing the overhead of writing and maintaining traditional scripts.