skills.rest
haposoft
haposoftOFFICIAL
Explore all skills by this author →
WebsiteGitHub

hapo:agent-browser

Automate browser navigation and interactions via command-line interface.

54|Updated Jan 21, 2026
Search Tags:#browser automation#web testing#CLI#video recording#autonomous sessions
One-click install
npx skills add https://github.com/haposoft/cafekit --skill hapo-agent-browser
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hapo:agent-browser
Source: https://github.com/haposoft/cafekit/tree/main/packages/spec/src/claude/skills/agent-browser
Command: npx skills add https://github.com/haposoft/cafekit --skill hapo-agent-browser

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates browser interactions and workflows, ideal for long autonomous sessions, self-verifying processes, video recording, and cloud-based testing, significantly enhancing efficiency in technical and development tasks.

Core Features & Use Cases

  • Browser Automation: Execute complex navigation, interaction, and verification tasks on websites.
  • Long Autonomous Sessions: Supports prolonged automated tasks without manual intervention.
  • Video Recording: Records sessions for debugging and analysis.
  • Cloud Testing: Integrates with cloud browsers for testing on remote environments.
  • Use Case: Use this Skill to automate testing workflows, record browser interactions for later review, or perform automated debugging of web applications.

Quick Start

Start an agent-browser session with the following command: agent-browser open https://example.com

Frequently Asked Questions about hapo:agent-browser

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

FAQPage Schema
How do I automate browser navigation for long-running autonomous sessions?▼

Browser automation for long-running autonomous sessions is executed via a command-line interface, utilizing a 'snapshot + refs' approach to efficiently manage prolonged web interactions without manual intervention.

How do I start a web testing session from the command line?▼

Starting a web testing session requires the command-line interface; simply execute the command `agent-browser open https://example.com` to initiate automated browser navigation and interaction for your technical workflows.

Can I record video of browser interactions for automated debugging?▼

Video recording of browser interactions is fully supported for automated debugging; the Skill captures session video during long-running autonomous workflows, allowing you to review and analyze complex web interactions later.

Does browser automation work with cloud-based testing environments?▼

Cloud-based testing is supported through integration with cloud browsers, enabling you to execute automated navigation, interaction, and verification tasks on remote environments for web application testing.

What is the snapshot and refs approach for browser automation?▼

The 'snapshot + refs' approach for browser automation captures webpage state and element references to efficiently drive interactions, reducing overhead during long-running autonomous sessions and complex navigation workflows.

Related Skills

Explore More Software Engineering Skills→
docaohieu2808docaohieu2808

agent-browser

Automate browser interactions via a command-line interface with snapshot-and-reference context efficiency.

Community
Advanced
EnztunEnztun

video-understand

Analyze video content and generate summaries using the z-ai-web-dev-sdk.

Community
Advanced
flonatflonat
127

playwright-cli

Automate browser interactions and web page testing with Playwright.

Community
Intermediate
SufficientDaikonSufficientDaikon
8

webapp-testing

Test local web applications with Playwright and capture browser logs.

Community
Intermediate