agent-browser

Automate browser navigation, form filling, clicking, screenshots, and content extraction.

Updated Jan 7, 2026
One-click install
npx skills add https://github.com/oneqmethod/next-payload-shadcn-starter-kit --skill agent-browser-oneqmethod
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/oneqmethod/next-payload-shadcn-starter-kit/tree/main/.claude/skills/agent-browser
Command: npx skills add https://github.com/oneqmethod/next-payload-shadcn-starter-kit --skill agent-browser-oneqmethod

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates routine browser interactions such as navigating web pages, filling forms, clicking elements, taking screenshots, and extracting content, reducing manual QA and repetitive data-entry work.

Core Features & Use Cases

  • Automated navigation and interaction: open pages, snapshot interactive elements, click refs, and fill inputs.
  • Content capture and verification: generate screenshots and extract text for QA reports and demos.
  • Use Case: QA engineers can script end-to-end flows for login, form submission, and data extraction to run repeatedly with consistent results.

Quick Start

  1. Open a URL: agent-browser open https://example.com
  2. Snapshot elements: agent-browser snapshot -i
  3. Interact using refs: agent-browser click @e1
  4. Fill inputs: agent-browser fill @e2 "sample text"
  5. Capture: agent-browser screenshot ./output.png

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 testing tasks like form filling and taking screenshots?

Automate web testing tasks using a Bash-based CLI to navigate pages, snapshot interactive elements, fill forms, click refs, and capture screenshots. It generates consistent QA results by scripting end-to-end browser flows for repetitive data entry.

Can I run browser automation for QA inside CI/CD pipelines?

Browser automation for QA supports integration into CI/CD pipelines. You can script navigation, form submission, and screenshot capture to run repeatedly with consistent results, reducing manual QA work across modern web applications.

How do I identify and interact with elements during browser automation?

Identify and interact with elements using compact element refs. You snapshot interactive elements to generate refs, then use commands to click or fill inputs by referencing those specific identifiers for precise browser automation control.

Does this browser automation CLI support multi-session isolation?

This browser automation CLI supports multi-session isolation. It manages multiple isolated browser sessions simultaneously, allowing you to run parallel web testing and data extraction workflows across different modern web applications without session conflicts.

What is the best way to extract content and capture screenshots from web pages?

Extract content and capture screenshots from web pages by navigating to the URL, taking interactive snapshots, and executing capture commands. This approach generates text and image outputs directly for QA reports and demonstrations.

Why use compact element refs instead of standard selectors for web testing?

Compact element refs provide an AI-friendly approach for web testing automation. Instead of relying on complex standard selectors, refs simplify the process of clicking and filling inputs, making browser automation scripts more robust and easier to maintain.