agent-browser

Automate Chrome browser interactions for navigation, form filling, screenshots, and data extraction.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/jay6697117/HandDrawing --skill agent-browser-jay6697117
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/jay6697117/HandDrawing/tree/main/.agents/skills/agent-browser
Command: npx skills add https://github.com/jay6697117/HandDrawing --skill agent-browser-jay6697117

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Manual browser automation and repetitive web tasks slow down AI workflows. agent-browser provides a CLI to control Chrome/Chromium programmatically, enabling AI agents to interact with websites, fill forms, navigate pages, take screenshots, extract data, and run tests without manual scripting.

Core Features & Use Cases

  • Browser automation for AI agents: Navigate, fill, click, and capture data across websites.
  • Data extraction and testing: Snapshot element refs, extract content, verify page state, and generate reports.
  • Session and proxy support: Manage authenticated sessions, parallel browsing, and controlled network access for CI and geo-testing.

Quick Start

Open a target URL and begin an automated browser flow by snapshotting to identify refs, filling a form, submitting, and capturing a screenshot.

Frequently Asked Questions about agent-browser

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

FAQPage Schema
How do I automate browser interactions for AI agents without writing manual scripts?

You can automate browser interactions using a CLI to programmatically control Chrome or Chromium, enabling AI agents to navigate pages, fill forms, and click elements without manual scripting.

Can I extract data and capture screenshots during web testing automation?

Yes, web testing automation supports snapshotting element refs to extract content, verifying page state, taking screenshots, and generating reports across diverse web tasks.

Does browser automation support authenticated sessions and proxy networks for CI environments?

Browser automation includes session and proxy support to manage authenticated sessions, enable parallel browsing, and control network access for CI pipelines and geo-testing scenarios.

What is the best way to structure a browser automation project for AI workflows?

The best way is using a root SKILL.md with YAML frontmatter defining a mandatory name and description, optionally including scripts, references, and assets directories for extended functionality.

How do I start an automated browser flow to fill and submit a web form?

To start an automated browser flow, open a target URL, snapshot the page to identify element refs, fill the form fields, submit the form, and capture a screenshot of the result.

What are the limitations of using CLI browser automation for complex web app testing?

CLI browser automation requires a root SKILL.md configuration and relies on programmatic Chrome control, meaning tasks needing highly manual intervention or non-Chromium browsers may face limitations.