agent-browser

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

46|6|Updated Jan 28, 2026
One-click install
npx skills add https://github.com/aresbit/MateBot --skill agent-browser-aresbit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/aresbit/MateBot/tree/main/skills/agent-browser
Command: npx skills add https://github.com/aresbit/MateBot --skill agent-browser-aresbit

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automates browser interactions for web testing, form filling, and data extraction.

Core Features & Use Cases

  • Automate browser navigation, element detection, and interactions using a compact snapshot/ref workflow.
  • Use cases include automated form submission, data extraction from web pages, end-to-end demos, and QA testing with reproducible steps.
  • Real-world example: a QA engineer runs a script to open a page, snapshot elements for refs, fill a login form, and verify the resulting URL.

Quick Start

agent-browser open https://example.com agent-browser snapshot -i agent-browser fill @e1 "[email protected]" agent-browser fill @e2 "password" agent-browser click @e3 agent-browser wait --load networkidle agent-browser screenshot --full

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 form filling and web testing tasks?

Browser automation for form filling and web testing is achieved via a CLI workflow using snapshot-generated refs to drive actions. You open a target page, snapshot elements for refs, fill fields, click targets, and wait for page loads to verify results.

What is the snapshot and ref workflow for browser automation?

The snapshot and ref workflow captures page elements into actionable references, allowing CLI commands to target specific UI components. You take an interactive snapshot of the page, which generates refs like @e1, then use those refs to fill forms, click buttons, and extract data.

How do I extract data and capture screenshots from web pages?

Data extraction and screenshot capture are performed by navigating to a page, taking a snapshot to generate element refs, interacting with the UI as needed, and executing a screenshot command. You can capture full-page screenshots after waiting for network idle states.

Can I use this browser automation tool for end-to-end QA testing?

Yes, this browser automation tool supports end-to-end QA testing with reproducible steps. QA engineers can script sequences to open pages, snapshot elements, fill login forms, click buttons, wait for network idle, and verify resulting URLs.

Does this web testing automation require any external dependencies?

No external dependencies are required to run this browser automation workflow. It operates through a CLI interface using snapshot-generated refs to navigate, interact with UI elements, fill forms, and capture screenshots without additional package installations.

What are the limitations of using CLI refs for browser automation?

Using CLI refs for browser automation requires taking a snapshot before each interaction, meaning dynamic pages may need repeated snapshots to locate changing elements. It is designed for structured navigation, form filling, and data extraction rather than highly dynamic single-page applications.