Skill UI

This skill provides expert-level control over a live Chrome browser. It enables full web automation (clicking, form filling, navigation), deep debugging (analyzing console logs, network requests), visual inspection (screenshots, snapshots), and detailed performance profiling. Ideal for QA engineers, web scraping, and front-end development testing.

This guide outlines the structure and content guidelines for an AGENTS.md file. This file serves as a comprehensive 'README for agents,' providing detailed, technical context and operational instructions (such as setup, development workflow, testing procedures, and code style) that enable advanced AI coding agents to interact with and understand a codebase effectively. It greatly complements traditional READMEs by focusing purely on machine-readable technical requirements.

Phoenix Evals enables developers to build and run evaluators for AI and LLM applications. It supports both code-based and LLM-based evaluation methods, including RAG systems. Users can create datasets, run experiments, validate evaluator accuracy, and implement production guardrails. Available in Python and TypeScript, it helps ensure model performance and reliability through systematic testing and human validation.

This skill guides comprehensive website exploration using Playwright MCP for robust testing. It involves navigating a specified URL, identifying and simulating 3-5 core user flows, meticulously documenting user interactions, relevant UI locators, and expected outcomes. Upon completion, the skill summarizes findings and generates detailed, actionable test cases, ensuring thorough coverage of the application's functionality.

Analyzes Copilot guidance files and repository docs to craft structured README.md content, detailing the project purpose, architecture, technology stack, workflows, coding standards, testing approach, and contributing advice for fellow developers.

Provides an expert Spring Boot 4 testing guide that explains the test pyramid, slice annotations, AssertJ-centric assertions, MockMvcTester, RestTestClient, Testcontainers, and practical coverage goals.

Applies proven testing patterns (AAA, Given-When-Then, builders, spies, doubles) to help write maintainable unit, integration, and end-to-end suites, covering structuring, naming, TDD/BDD, and mocks across frameworks like Jest, Vitest, or pytest.

This skill systematically reviews test code to identify and correct common anti-patterns. It detects issues such as flaky tests, overly mocked dependencies (over-mocking), brittle assertions, excessive test size (The Giant), and structural dependencies. It explains the flaw, provides best practices, and suggests refactored, reliable implementations, helping maintain high test quality and stability.

A specialized tool designed to explore uncertain futures by mapping the entire possibility space. Instead of relying on a single prediction, the Oracle runs structured multi-branch scenario analyses (including Best, Worst, Wild Card, and Second-Order effects). It is ideal for stress-testing major decisions, performing contingency planning, and analyzing potential consequences when facing strategic forks or high-stakes uncertainty.

This comprehensive guide provides minimal working examples for key Adobe APIs: Firefly AI image generation, PDF content extraction, and Photoshop background removal. It serves as a practical quickstart for developers starting new Adobe integrations, testing API connectivity, or learning basic API calling patterns using TypeScript and Node.js.

This guide details setting up a robust, local development loop for Adobe integrations (Firefly, PDF, Photoshop). It covers using the `aio` CLI for App Builder, implementing hot reload, and establishing unit/integration testing with mocking to ensure rapid, reliable iteration cycles for Adobe APIs.

A comprehensive guide to setting up a full-cycle local Web3 development workflow. This skill utilizes Alchemy as the RPC provider, Hardhat for local unit testing, and integrates Mainnet forking and Sepolia testnet deployment. It covers initializing the project, configuring smart contract interactions, and implementing advanced testing patterns.