surf

Name: surf
Availability: InStock
Author: Graham

Control Chrome via CLI to open URLs, click elements, and type forms.

1|Updated Nov 12, 2025

Search Tags:#automation #cli #chrome #browser #web-automation #ai-assist #surf-cli

Ready to run

npx skills add https://github.com/grahama1970/fetcher --skill surf

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: surf
Source: https://github.com/grahama1970/fetcher/tree/main/.agents/skills/surf
Command: npx skills add https://github.com/grahama1970/fetcher --skill surf

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI-powered agents need reliable browser automation to perform tasks like navigation, interaction, and data extraction without manual steps.

Core Features & Use Cases

Zero-config browser automation via a CLI, enabling agents to open pages, click elements, type input, and read page content.
Supports taking screenshots, reading accessibility trees, and scripting common browser tasks across sessions.
Use cases include automated testing, data collection, and task automation for AI assistants.

Quick Start

Install and run surf to automate your browser with a single command.

Frequently Asked Questions about surf

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

FAQPage Schema

How do I automate browser interactions for an AI agent?▼

Browser automation for AI agents is handled by controlling Chrome through a CLI to open URLs, click elements, type into forms, and take screenshots. It enables agents to perform navigation and data extraction without manual steps.

Can I run web automation commands without installing extra dependencies?▼

Zero-config web automation is supported via npx directly from GitHub, requiring no extra dependencies. You can execute browser tasks immediately as long as the matching Chrome host extension is installed.

What do I need to use a CLI to control Chrome and extract page content?▼

To control Chrome via a CLI, you need the Chrome browser installed along with its matching host extension. Once configured, you can automate interactions, read accessibility trees, and capture screenshots across sessions.

How do I click elements and type into forms during web automation?▼

Clicking elements and typing into forms is done using a compact command set exposed by the CLI. These commands handle navigation, interaction, and waiting, allowing automated scripts to fill out and submit web data.

Does this browser automation tool support reading accessibility trees?▼

Reading accessibility trees is fully supported alongside taking screenshots and scripting common tasks. This allows AI assistants to extract structured page content and verify element states during automated browser sessions.