Testing and QA: skills, plugins, subagents, slash commands and mcp servers

phoenix-evals official [email protected] skill Build and run evaluators for AI and LLM applications with Phoenix. Use it to investigate failures, evaluate RAG systems, and check model output. GitHub Copilot 1,000installs phoenix-cli official arize-ai skill A GitHub Copilot skill that drives the Phoenix CLI to pull traces, spans and sessions, then turns what it finds into a failure taxonomy for your LLM app. GitHub Copilot 1,000installs quantized-export Seth Hobson skill Exports promoted checkpoints and LoRA adapters as FP8, AWQ, GGUF, or merged safetensors. Use it before deploying a model. Claude Code CX Codex Cursor 2,600installs eval-harness-first Seth Hobson skill Sets up an evaluation harness before fine-tuning: builds golden sets and records base model baselines. Claude Code CX Codex Cursor 2,600installs checkpoint-promotion Seth Hobson skill Gates fine-tuned model checkpoints using drift budgets, paired arena comparisons, and forgetting checks before release. Produces promotion-report.md with a PROMOTE or REJECT verdict. Claude Code CX Codex Cursor 2,600installs penetration-tester VoltAgent Community subagent Runs authorized security tests, validates vulnerabilities and reports remediation steps. Use it to assess systems within an agreed scope. Claude Code 2,407installs pptx-quality-gates kimtth skill Checks and repairs editable PPTX decks for geometry, accessibility, native objects, source lineage, and OOXML package integrity before delivery. Claude Code CX Codex Cursor 2,500installs python-pypi-package-builder official github skill This skill guides Python package creation, testing, versioning, and PyPI publishing. Use it for libraries, SDKs, CLI tools, and framework plugins. GitHub Copilot 943installs salesforce-apex-quality official github skill Checks Apex for governor-limit risks, security gaps, and missing tests. Use it when GitHub Copilot reviews or generates Salesforce classes, triggers, and test code. GitHub Copilot 884installs salesforce-flow-design official github skill Reviews Salesforce Flow architecture, type selection, bulk safety, and fault handling. Use it before designing, reviewing, or activating a Flow. GitHub Copilot 839installs php-pro VoltAgent Community subagent Claude Code subagent for PHP 8.3+, Laravel, and Symfony projects requiring strict typing, PHPStan level 9 checks, and async patterns. Claude Code 2,019installs react18-dep-compatibility official github skill Checks minimum dependency versions for React 18.3.1 and React 19. Use it during React upgrades and when resolving peer dependency conflicts. GitHub Copilot 764installs react18-batching-patterns official github skill Diagnoses and fixes React 18 automatic batching bugs in class components. Useful when upgrading from React 17 breaks state assertions or async flows. GitHub Copilot 754installs react18-enzyme-to-rtl official github skill Provides Enzyme to React Testing Library migration patterns for React 18 upgrades. Useful when rewriting shallow renders, mount calls, and state assertions into user behavior checks. GitHub Copilot 739installs golang-pro Seth Hobson subagent This subagent helps design Go services, inspect concurrent code, and profile performance. Use it when a task calls for tested code and careful goroutine handling. Claude Code CX Codex Cursor 1,911installs engineering-skills Alireza Rezvani skill An engineering skill index for Claude Code that helps you select one specialist SKILL.md for the task at hand. It covers architecture, testing, DevOps, and data work. Claude Code 2,387installs migrate-to-rust official google skill Migrates legacy C++, Fortran, Java, and Python codebases to safe Rust with telemetry benchmarks. Claude Code Gemini CLI CX Codex 538installs dx-optimizer VoltAgent Community subagent This subagent reviews builds, tests, IDE setup, and developer workflows. Use it when you need to find DX bottlenecks and track changes. Claude Code 1,198installs coverage Alireza Rezvani skill This skill maps tested and untested parts of an application. Use it when you need a clear list of missing tests before planning the next checks. Claude Code 1,645installs report Alireza Rezvani skill Runs Playwright tests, parses JSON outputs, and sends test summaries to Slack, TestRail, or Markdown. Helpful when you need quick test feedback. Claude Code 1,639installs fix Alireza Rezvani skill Sorts a failing or flaky Playwright test into a category, applies the matching fix, then proves it holds. Useful when a test fails in CI but passes locally. Claude Code 1,638installs senior-frontend Alireza Rezvani skill Scaffolds Next.js and React projects, generates components with tests, and audits bundle size to replace heavy dependencies. Claude Code 1,630installs generate Alireza Rezvani skill The generate skill writes Playwright tests from a user story, URL, component name or feature description. Useful when an e2e scenario needs covering and you would rather not hand-write it. Claude Code 1,624installs browserstack Alireza Rezvani skill Runs Playwright tests on the BrowserStack cloud grid and pulls execution logs with videos. Helpful for verifying cross-browser builds. Claude Code 1,614installs migrate Alireza Rezvani skill Moves Cypress or Selenium tests to Playwright. Use it when an existing test suite needs file-by-file conversion and checks after each change. Claude Code 1,586installs testrail Alireza Rezvani skill Syncs Playwright tests with TestRail by importing cases, creating runs, and pushing results. Use it when test code and test management need to stay linked. Claude Code 1,581installs setup Alireza Rezvani skill Sets up an autoresearch experiment by collecting its target file, evaluation command, metric, and optimization direction. Use it before starting an optimization loop. Claude Code 1,480installs spawn Alireza Rezvani skill Runs parallel subagents in isolated git worktrees to compete on a session task. Helpful when you want multiple implementation strategies tested at once. Claude Code 1,431installs eval Alireza Rezvani skill Evaluates and ranks agent results from an AgentHub session using test metrics or an LLM judge. Helps select the winning branch. Claude Code 1,408installs qa-expert VoltAgent Community subagent Plans test strategies, analyzes coverage gaps, and tracks quality metrics across development lifecycles in Claude Code. Claude Code 980installs ai-team-orchestration official github skill Bootstraps a lightweight multi-agent team inside your editor. It helps plan features, coordinate code changes, and preserve context across chat sessions. GitHub Copilot 381installs harness-engineering official github skill Turns repeated coding agent mistakes into repository rules, drift checks, and regression tests. Use it when Copilot keeps repeating the same errors in your project. GitHub Copilot 366installs senior-qa Alireza Rezvani skill This skill creates unit, integration, and E2E test stubs for React and Next.js. Use it to inspect coverage and set up a testing workflow. Claude Code 1,178installs legacy-modernizer VoltAgent Community subagent Assesses aging codebases and breaks modernization into migration steps with tests and rollback planning. Use it when changes need to happen incrementally. Claude Code 826installs react-specialist VoltAgent Community subagent A subagent for improving existing React code, from performance and state flow to architecture and tests. Use it when a project needs focused technical changes. Claude Code 815installs refactoring-specialist VoltAgent Community subagent Transforms messy, duplicated code into clean structures while keeping existing behavior intact. Ideal for legacy refactoring and reducing cyclomatic complexity. Claude Code 784installs ios-memgraph-leaks official OpenAI skill Captures and inspects iOS leaks from a simulator process or .memgraph. Useful for tracing retained objects and checking a fix with before-and-after evidence. CX Codex GP ChatGPT 1,054installs cpp-pro Seth Hobson subagent Writes modern C++ from C++11 to C++23 using RAII, smart pointers, and STL algorithms. Helps with C++ refactoring and template design. Claude Code CX Codex Cursor 781installs tdd-guide Alireza Rezvani skill Guides test-driven development, builds unit tests, and detects test coverage gaps. It supports Jest, Pytest, JUnit, and Vitest projects. Claude Code 1,017installs senior-prompt-engineer Alireza Rezvani skill Tests prompts against baselines, measures RAG retrieval metrics, and validates agent configs using three Python stdlib tools. Useful for disciplined prompt iteration without guess-driven edits. Claude Code 970installs