Skill UI

A comprehensive skill for generating keyword-driven automated test scripts using Robot Framework. It supports front-end UI testing via SeleniumLibrary, robust API integration using RequestsLibrary, and complex custom keywords. Ideal for building end-to-end and functional test suites.

A comprehensive skill for generating production-grade, robust automation scripts and end-to-end tests using Selenium WebDriver. Supports multiple languages (Java, Python, JS, C#, etc.) and execution environments, including local machines and TestMu AI cloud for cross-browser compatibility. It guides users on best practices like explicit waits, Page Object Model (POM), and stable locator strategies, acting as a senior QA automation architect.

This skill generates comprehensive visual regression test configurations using SmartUI for accurate screenshot comparison on cloud platforms. It is framework-agnostic, supporting major tools like Playwright, Selenium, Cypress, and Puppeteer. Use it when detecting UI changes, ensuring visual consistency, or running automated visual tests across multiple viewports and browsers.

This skill serves as a senior QA automation architect to migrate and convert UI test automation scripts between popular frameworks, including Selenium, Playwright, Puppeteer, and Cypress. It handles complex conversions by applying API mapping, lifecycle adjustments, and pattern standardization, allowing users to port tests from one framework to another efficiently.

This skill helps generate comprehensive and structured TestNG test cases for Java. It supports advanced testing features crucial for enterprise automation, including method grouping, data-driven testing using @DataProvider, parallel execution setup, XML suite configuration, and custom listeners. Use it when building robust, scalable, and maintainable automated test suites.

This skill provides expert capabilities for training and fine-tuning transformer language models using the TRL (Transformers Reinforcement Learning) library. It supports state-of-the-art post-training methods, including Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), Group Relative Policy Optimization (GRPO), and Reward Model training. Use this skill to align and customize foundation models for advanced tasks via CLI commands.

This agent analyzes a Monte Carlo monitor's report and configuration to identify alert patterns. It recommends concrete configuration changes for metric, custom SQL, validation, and table monitors, helping reduce false positives and alert fatigue without sacrificing real signal.

A fast, grep-based linter that checks for common design system violations in CSS and component code, such as hardcoded colors, raw pixel values, and deprecated syntax. It provides immediate automated feedback to ensure code adheres to established design tokens and best practices.

This skill analyzes your project's current StyleSeed setup, detects outdated engine files, and safely updates the core components, skills, and rules. It follows a structured, non-destructive process, ensuring that user-defined code, such as theme.css and custom components, remains untouched while applying necessary upgrades.

This skill automatically rewrites raw commit messages to adhere to professional engineering standards. It strips out common 'AI/marketing slop' phrases (like 'robust implementation' or 'leverage') while strictly maintaining the Conventional Commits format. It ensures subjects are concise, bodies provide necessary context (why, breaking changes), and the tone is direct and actionable, making your project history clean and readable.

This skill generates comprehensive end-to-end (E2E) automation tests using WebdriverIO (WDIO) in JavaScript or TypeScript. It supports various frameworks (Mocha, Jasmine, Cucumber) and includes advanced patterns like the Page Object Model (POM) and robust selector strategies. Users can configure tests for local execution or integrate with cloud services like LambdaTest, making it ideal for simulating complex user interactions and ensuring application quality across multiple browsers and environments.