skills.rest
dungnt97
dungnt97COMMUNITY
Explore all skills by this author →
GitHub

ck:agent-browser

Automate browser navigation and interaction via CLI with refs-based snapshots.

Updated Aug 23, 2026
Search Tags:#testing#cli#agent#playwright#browser-automation#cloud-browsers
One-click install
npx skills add https://github.com/dungnt97/wallet-portal --skill ck-agent-browser-dungnt97
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ck:agent-browser
Source: https://github.com/dungnt97/wallet-portal/tree/main/claude/skills/agent-browser
Command: npx skills add https://github.com/dungnt97/wallet-portal --skill ck-agent-browser-dungnt97

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill provides an efficient CLI-based tool for AI agents to automate browser tasks, enabling long-running sessions and reproducible web interactions without manual browser control.

Core Features & Use Cases

  • Long autonomous sessions with documented snapshots and refs to minimize context switching.
  • Cloud browser support via Browserbase for CI/CD and parallel testing.
  • State persistence and robust navigation/interactions for testing, QA, and automation workflows.

Quick Start

Open a target URL with agent-browser and capture an interactive snapshot using element refs.

Frequently Asked Questions about ck:agent-browser

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

FAQPage Schema
How do I run long autonomous browser automation sessions for AI agents?▼

Browser automation for AI agents is driven by a CLI that parses commands, captures page snapshots, and manages element refs. This refs-based system allows agents to navigate and interact without manual browser control.

Can I use Playwright for reproducible testing in CI/CD with cloud browsers?▼

Reproducible testing in CI/CD is supported through optional cloud browser integration via Browserbase. This enables parallel testing and long-running workflows using robust state persistence and navigation interactions.

What is the refs-based system for browser automation and how does it work?▼

The refs-based system captures interactive snapshots of web pages and assigns element references. AI agents use these refs to navigate and interact with specific page elements accurately during long-running autonomous sessions.

Does this browser automation CLI support state persistence across long sessions?▼

The browser automation CLI supports state persistence and robust navigation interactions. This ensures reproducible web interactions and maintains session context for AI agents during long-running tasks.

Best way to automate web interactions across diverse web apps for AI agents?▼

Automating web interactions for AI agents is handled by a CLI that provides command parsing, snapshot management, and a refs-based system. This enables reproducible testing and navigation across diverse web apps.

When should I not use a CLI-based approach for browser automation?▼

A CLI-based browser automation approach is not ideal for manual visual testing or tasks requiring real-time human oversight. It is optimized for long-running autonomous sessions, CI/CD workflows, and reproducible testing.

Related Skills

Explore More Software Engineering Skills→
mafvietnammafvietnam

ck:agent-browser

Automate browser navigation, snapshotting, and interaction via a CLI workflow.

Community
Intermediate
NammDevNammDev
2

agent-browser

Automate browser tasks with snapshot refs and CLI commands.

Community
Advanced
BuilderIOBuilderIO
11

playwright-cli

Automate browser interactions and Playwright test workflows via command-driven tooling.

Official
Advanced
tom-xstom-xs

playwright-cli

Operate a live browser via command line with Playwright.

Community
Advanced