skills.rest
TNHoang2708
TNHoang2708COMMUNITY
Explore all skills by this author →
GitHub

ck:agent-browser

Automate browser interactions and capture page context via snapshots and refs.

1|Updated Jun 16, 2026
Search Tags:#browser automation#context-efficient#video recording#AI-optimized#cloud browser testing
One-click install
npx skills add https://github.com/TNHoang2708/Gym_Ver2 --skill ck-agent-browser-tnhoang2708
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ck:agent-browser
Source: https://github.com/TNHoang2708/Gym_Ver2/tree/main/.claude/skills/agent-browser
Command: npx skills add https://github.com/TNHoang2708/Gym_Ver2 --skill ck-agent-browser-tnhoang2708

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the challenge of long, autonomous AI sessions by providing a browser automation CLI that minimizes context overhead and offers features like video recording and cloud browser testing.

Core Features & Use Cases

  • Context-Efficient Snapshots: Reduces context by 93% compared to Playwright MCP, ideal for AI agents.
  • Browser Automation: Execute tasks like navigation, interaction, and state checks.
  • Use Case: Automate complex workflows such as form submissions, data extraction, and video recording for debugging purposes.

Quick Start

Use the agent-browser skill to navigate to a URL and interact with elements on the page.

Frequently Asked Questions about ck:agent-browser

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

FAQPage Schema
How do I reduce context overhead during long-running AI browser automation sessions?▼

Browser automation context overhead is reduced by using a snapshot and refs paradigm that captures page context efficiently, minimizing the data sent to AI agents during long-running sessions.

What is the best way to automate browser interactions for AI agents without exceeding context limits?▼

The best way to automate browser interactions for AI agents is using context-efficient snapshots, which reduce context usage by 93% compared to Playwright MCP while executing navigation and data extraction tasks.

Can I record video of browser automation workflows for debugging purposes?▼

Yes, video recording of browser automation workflows is supported for debugging purposes, allowing you to capture and review complex tasks like form submissions and data extraction.

Does this browser automation approach work with cloud browser testing environments?▼

Yes, this browser automation approach is designed to work with cloud browser testing environments, enabling remote execution of navigation, interaction, and state checks.

Why does my AI agent lose context when navigating complex web pages?▼

AI agents lose context navigating complex pages because traditional automation tools send excessive page data; using context-efficient snapshots and refs mitigates this by capturing only essential page state.

What do I need to navigate to a URL and interact with elements using agent-browser?▼

To navigate to a URL and interact with elements, you need a browser environment and specific browser automation commands to execute navigation, interaction, and information retrieval operations.

Related Skills

Explore More Software Engineering Skills→
marktantongcomarktantongco

playwright-cli

Automate headless browser navigation, clicks, and form submissions for testing and scraping.

Community
Intermediate
duwenjiduwenji

agent-tracing

Inspect JSON execution snapshots and step-level traces from .agent-tracing.

Community
Advanced
jangtrinhjangtrinh

ck:agent-browser

Automate browser workflows using snapshot-derived element references for clicks and form fills.

Community
Advanced
fajshahfajshah
1

browsing-with-playwright

Automate browser navigation, form interactions, and data extraction via Playwright MCP.

Community
Intermediate