skills.rest
xongtao
xongtaoCOMMUNITY
Explore all skills by this author →
GitHub

Agent Browser

Launch and automate web interactions via the agent-browser CLI.

Updated Mar 10, 2026
Search Tags:#cli#headless#ai-agents#web-automation#browser-automation#automation-testing#agent-browser
One-click install
npx skills add https://github.com/xongtao/openclaw-backup --skill agent-browser-xongtao
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Agent Browser
Source: https://github.com/xongtao/openclaw-backup/tree/main/skills/agent-browser
Command: npx skills add https://github.com/xongtao/openclaw-backup --skill agent-browser-xongtao

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Agent Browser provides fast, scriptable browser automation for AI agents, enabling navigation, clicking, typing, and snapshotting of pages via a lightweight CLI.

Core Features & Use Cases

  • Navigate, snapshot, and interact with web pages using deterministic commands.
  • Automate testing, data extraction, form filling, and UI workflows in modern apps.
  • Use cases include AI agents handling onboarding flows, data collection, and automated QA across web interfaces.

Quick Start

Open a URL and begin interacting with elements using refs produced by a snapshot.

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 interactions using a CLI?▼

You can automate web interactions using a CLI by launching the agent-browser tool to navigate, snapshot, and manipulate page content via deterministic commands.

What is headless browser automation for AI agents?▼

Headless browser automation for AI agents provides fast, scriptable navigation, clicking, typing, and snapshotting of web pages using a lightweight command-line interface.

How do I extract data and fill forms in modern web apps?▼

To extract data and fill forms in modern web apps, open a URL and interact with elements using refs produced by a page snapshot to execute deterministic commands.

Do I need Node.js to run agent-browser commands?▼

Yes, you need the Node.js environment and the agent-browser binary to execute the deterministic web automation commands defined in the SKILL.md file.

Can I use this for automated UI testing and onboarding flows?▼

Yes, you can use this for automated UI testing and onboarding flows, as it safely navigates and manipulates page content across modern web applications.

Related Skills

Explore More Software Engineering Skills→
dsactivi-2dsactivi-2

Agent Browser

Automate headless browser navigation, form filling, and data extraction via CLI.

Community
Advanced
maxvaegamaxvaega
146

json-parser

Parse and validate JSON data against schemas and JSONPath queries.

Community
Intermediate
ngx-signal-formsngx-signal-forms
3

playwright-cli

Automate browser interactions and testing workflows using Playwright CLI commands.

Official
Advanced
pth-droidpth-droid

agent-browser

Automate browser navigation, element interaction, and screenshots for web testing.

Community
Intermediate