How does ATR help with debugging failed tests?

When a test fails, ATR captures a screenshot, DOM snapshot, console logs, and network requests, then provides an AI-powered analysis of the root cause.

Does this skill support mobile testing?

Yes, you can specify custom viewport dimensions using the --viewport flag (e.g., 375x667) to simulate mobile device environments.

What is a .test.txt file?

It is a plain text file used by ATR to define test steps, prerequisites, and expected results in natural language, which the AI then translates into browser actions.

Can I see the browser while the test is running?

Yes, while tests run in headless mode by default, you can use the --headless=false flag to watch the AI execute steps in a visible browser window.

Do I need to manually write CSS selectors for these tests?

No, the AI uses various strategies like accessible names, labels, and text content to find elements, though you can still use CSS selectors or data-testids for higher precision.

ATR Behavior Testing

Name: ATR Behavior Testing
Author: imyousuf

byimyousuf

•

보안 및 테스팅

Executes automated browser-based behavior tests using natural language specifications and AI-driven navigation.

This skill leverages the Agentic Test Runner (ATR) to execute end-to-end browser tests written in plain English, eliminating the need for maintaining complex CSS or XPath selectors. It allows developers to define user journeys in .test.txt files which an AI agent then interprets and executes, providing robust element resolution through multiple strategies and detailed failure analysis including screenshots, console logs, and DOM snapshots.

주요 기능

01Configurable browser environments and custom viewport sizes

02Support for headless mode and remote CDP endpoint connection

03AI-driven element resolution using ARIA, Test IDs, and text content

04Natural language test execution from .test.txt files

05Automated failure analysis with screenshots and network logs

061 GitHub stars

사용 사례

01Debugging complex UI failures with AI-generated root cause analysis

02Automating end-to-end user journey testing without writing boilerplate code

03Verifying mobile responsiveness through custom viewport configurations

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add imyousuf/agentic-test-runner atr-behavior

For use in Claude.ai and ChatGPT

Download Skill