ck:agent-browser

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

Updated Mar 30, 2026
One-click install
npx skills add https://github.com/mafvietnam/mafapp --skill ck-agent-browser-mafvietnam
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ck:agent-browser
Source: https://github.com/mafvietnam/mafapp/tree/main/.claude/skills/agent-browser
Command: npx skills add https://github.com/mafvietnam/mafapp --skill ck-agent-browser-mafvietnam

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Browsers are a core bottleneck for AI workflows; manual navigation and repetitive tasks waste time and introduce errors. This Skill provides a compact, reliable CLI to automate browser actions, capture element references, and run multi-step interactions with minimal context.

Core Features & Use Cases

  • 4-step interaction pattern: open/navigate, snapshot with element refs, perform actions, re-snapshot to verify page changes.
  • Context-efficient automation for long-running AI sessions, testing, form filling, and cloud-browser workflows (Browserbase) in CI/CD.
  • Supports multiple sessions, video recording, and cloud-browsing providers for scalable automation in development and production.

Quick Start

Install the tool globally and start by opening a URL to begin an automated browser session.

Frequently Asked Questions about ck:agent-browser

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

FAQPage Schema
How do I automate browser tasks for AI agents without consuming too much context?

Browser automation for AI agents uses a CLI to capture context-efficient snapshots with element references. This allows long-running autonomous sessions to interact with web pages and perform multi-step tasks with minimal context overhead.

What is the standard workflow for web automation testing using this CLI?

Web automation testing follows a 4-step pattern: navigate to a URL, snapshot the page to capture element references, perform actions like form filling, and re-snapshot to verify the resulting page changes.

Can I run cloud browsers in CI/CD pipelines for automation testing?

Cloud browsers in CI/CD are supported through the Browserbase provider. This enables scalable execution, video recording, and multi-session capabilities for development and production environments.

Does browser automation CLI support multiple sessions and recording?

The browser automation CLI supports multiple concurrent sessions and built-in video recording. This is useful for tracking long-running autonomous web navigation and form filling tasks.

Why use element references instead of raw HTML for web navigation automation?

Element references provide a compact representation of page structure for web navigation automation. This context-efficient method prevents token limits from being exceeded during long-running AI sessions.