skills.rest
Baltsat
BaltsatCOMMUNITY
Explore all skills by this author →
GitHub

agent-browser

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

Updated Aug 23, 2026
Search Tags:#automation#screenshots#web-testing#browser#data-extraction#form-filling
One-click install
npx skills add https://github.com/Baltsat/box --skill agent-browser-baltsat
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-browser
Source: https://github.com/Baltsat/box/tree/main/tools/claude/skills/agent-browser
Command: npx skills add https://github.com/Baltsat/box --skill agent-browser-baltsat

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates repetitive browser interactions for testing, data collection, and form filling, reducing manual effort and human error.

Core Features & Use Cases

  • Snapshot-based element interaction: capture the accessible element tree and refs, then drive actions using refs.
  • Stepwise browser control: open URLs, navigate back/forward, and manage sessions for end-to-end testing.
  • Data capture and form automation: fill forms, take screenshots, and extract information for reports.

Quick Start

Open a URL and interact with page elements using element references from a prior 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 testing and form filling for dynamic web apps?▼

Automate web testing by using a CLI to open URLs and interact with page elements through snapshot references. You can fill forms, click elements, and capture screenshots across dynamic web apps with built-in error handling.

How does snapshot-based element interaction work for browser automation?▼

Snapshot-based interaction captures the accessible element tree and references, then drives actions using those refs. This allows precise browser control for clicking and filling forms without hardcoding selectors.

Can I extract visible data and take screenshots from websites automatically?▼

Yes, you can extract visible data and take screenshots from websites automatically. The automation CLI provides specific commands to capture page states and extract information for reports or testing logs.

What is the best way to manage browser sessions for end-to-end web testing?▼

The best way to manage browser sessions is using stepwise browser control commands to open URLs and navigate back or forward. This manages sessions effectively for sequential end-to-end web testing workflows.

Does browser automation include safety checks to prevent unintended actions?▼

Yes, browser automation includes error handling and safety checks to prevent unintended actions. These safety mechanisms ensure that automated form filling and element interactions execute securely.

Do I need specific dependencies to run browser automation for data extraction?▼

No specific dependencies are required to run browser automation for data extraction. The skill operates independently using its robust CLI interface to execute commands for web testing and data capture.

Related Skills

Explore More Software Engineering Skills→
hemoryhemory

agent-browser

Displays a list of available commands for the specified tool.

Community
Intermediate
tblakex01tblakex01
1

qa-only

Test a web application and output a structured bug report with health score, screenshots, and repro steps.

Community
Intermediate
webmaxruwebmaxru
49

playwright-cli

Automate web navigation, form filling, and data extraction with Playwright CLI.

Community
Intermediate
mikkelkrogsholmmikkelkrogsholm
66

agent-browser

Automate browser interactions and extract structured web content via CLI daemon.

Community
Advanced