Agent Browser

Automate browser navigation, clicking, typing, and page inspection via a headless browser CLI.

Updated Feb 16, 2026
One-click install
npx skills add https://github.com/wewetv1987-cell/openclaw-backup --skill agent-browser-wewetv1987-cell
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Agent Browser
Source: https://github.com/wewetv1987-cell/openclaw-backup/tree/main/skills/agent-browser
Command: npx skills add https://github.com/wewetv1987-cell/openclaw-backup --skill agent-browser-wewetv1987-cell

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Agent Browser removes repetitive browser work by letting you control a headless browser to navigate websites, click elements, fill forms, capture screenshots, and extract page data in a predictable way.

Core Features & Use Cases

  • Page navigation and interaction through stable element references.
  • Snapshots, text and HTML retrieval, screenshots, PDFs, and video recording for inspection and debugging.
  • Session management, tabs, network interception, cookies, storage, and saved state for authenticated or multi-step workflows.
  • Use it to automate sign-ins, scrape structured content, test web apps, and reproduce UI flows.

Quick Start

Tell the assistant to open a website, take an interactive snapshot, and then click or fill the referenced elements needed to complete your 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 scraping and form filling with a headless browser?

Automate web scraping and form filling by controlling a headless browser to navigate pages, click elements, and extract data via stable element references. It handles login flows and form submission predictably.

Can I capture screenshots and take interactive snapshots during web testing?

Yes, you can capture screenshots and take interactive snapshots during web testing. The tool supports snapshots, text retrieval, screenshots, PDFs, and video recording for debugging UI flows.

Does browser automation work with session management and network interception?

Browser automation works with session management and network interception by supporting tabs, cookies, storage, and saved state for authenticated multi-step workflows with JSON output.

What is the best way to reproduce UI flows and test web apps automatically?

The best way to reproduce UI flows and test web apps is through agent-driven tasks using a headless browser CLI with stable element references and Node.js fallback for reliable automation.

Do I need Node.js to run headless browser automation tasks?

You need Node.js as a fallback for reliable headless browser automation. The tool requires a headless browser CLI with stable element references, JSON output, and session isolation.