NeVibeCode · 81 items
Subagents for Testing and QA
Subagents for Testing and QA: what each one does, an install command and example prompts.
pr-test-analyzer
official subagent This subagent checks whether pull request tests cover changed behavior, edge cases, and error paths. Run it after a PR update or before sending the PR for review.
★ 44,635repo stars
scaffolder
official subagent Builds a single service skeleton from an approved architecture document and specification. Generates domain models, API stubs, and acceptance tests.
★ 44,635repo stars
agent-sdk-verifier-ts
official subagent Verifies @anthropic-ai/claude-agent-sdk applications before release. It detects type errors, misconfigured TypeScript settings, and exposed credentials.
★ 44,635repo stars
agent-sdk-verifier-py
official subagent Checks a Python Agent SDK application for configuration issues, SDK usage, security gaps, and readiness for testing or deployment.
★ 44,635repo stars
web-accessibility-checker subagent A subagent that checks markup against WCAG, reviews HTML semantics and keyboard access, and returns a report listing violations.
1,438installs
Expert Vue.js Frontend Engineer
official subagent GitHub Copilot subagent specialized in Vue 3, Composition API, TypeScript, and component architecture. Builds frontends, migrates from Vue 2, and optimizes rendering.
★ 40,418repo stars
Software Engineer Agent
official subagent Autonomously writes code to specification, executes tests, and resolves ambiguities without asking for manual confirmations.
★ 40,418repo stars
Salesforce UI Development (Aura & LWC)
official subagent A GitHub Copilot subagent that builds Lightning Web Components and Aura components with accessibility and SLDS in mind.
★ 40,418repo stars
Research Harness Engineer
official subagent A subagent for experiment campaigns: it builds an evaluation harness that is hard to fool and keeps every reported number honest.
★ 40,418repo stars
react19-dep-surgeon
official subagent Walks a project's dependencies up to React 19 step by step: core, testing-library, Apollo and Emotion, then peer conflicts, ending in a GO/NO-GO verdict.
★ 40,418repo stars
react18-test-guardian
official subagent A subagent that fixes failing tests after the move to React 18.3.1 and keeps looping until nothing fails.
★ 40,418repo stars
quality-playbook
official subagent Runs a six-phase quality audit over a codebase, each phase in its own context window. Useful when a normal review stops finding bugs.
★ 40,418repo stars
Playwright Tester Mode
official subagent A GitHub Copilot subagent that walks the site through Playwright MCP first, then writes and runs TypeScript tests.
★ 40,418repo stars
Expert Nuxt Developer
official subagent Guides Nuxt 3 and Nitro development with TypeScript typing. Helps configure data fetching via useFetch, resolve hydration issues, and structure server routes.
★ 40,418repo stars
Laravel Expert Agent
official subagent A GitHub Copilot subagent for Laravel 12+ work: Eloquent, Artisan, routes, PHPUnit tests. Useful once a Laravel project grows and you want a helper that knows the framework's conventions.
★ 40,418repo stars
gem-reviewer
official subagent Runs independent reviews of plans, tasks, code, configs, and integrations. Emits strict JSON validation reports for orchestrators without touching source files.
★ 40,418repo stars
gem-mobile-tester
official subagent A subagent that runs E2E tests on iOS and Android simulators and emulators through Detox and Maestro. It does not write code — it executes checks and returns a report.
★ 40,418repo stars
gem-code-simplifier
official subagent A refactoring subagent that removes dead code and drops complexity. Handy when cleaning up messy logic without altering existing behavior.
★ 40,418repo stars
Frontend Performance Investigator
official subagent Diagnoses runtime web performance issues, layout shifts, and Core Web Vitals regressions by connecting browser traces directly to your code.
★ 40,418repo stars
C++ Expert
official subagent Provides guidance on modern C++ following ISO standards and C++ Core Guidelines. It helps write clean architecture, refactor legacy code, and set up testing.
★ 40,418repo stars
Doublecheck
official subagent Verifies AI-generated text by finding web sources and highlighting hallucination risks. Useful before publishing content containing legal citations, statistics, or API syntax.
★ 40,418repo stars
DiffblueCover
official subagent Generates Java unit tests using Diffblue Cover and commits verified tests to Git. Helps write unit test suites for entire projects, packages, or individual methods.
★ 40,418repo stars
DevTools Regression Investigator
official subagent Reproduces UI regressions in the browser and pinpoints root causes using network and console evidence.
★ 40,418repo stars
Delphi Expert
official subagent Assists with Object Pascal development in Delphi projects. It covers VCL, FMX, FireDAC data access, memory safety, and unit registration in project files.
★ 40,418repo stars
Debug Mode Instructions
official subagent A GitHub Copilot subagent that walks debugging in phases: reproduce the bug, find the root cause, patch it, verify. Useful when a failure is flaky and you don't know where to start.
★ 40,418repo stars
C#/.NET Janitor
official subagent Cleans up and modernizes C# and .NET codebases by resolving technical debt, adding tests, and applying modern language features.
★ 40,418repo stars
Clojure Interactive Programming
official subagent Clojure pair-programming agent enforcing REPL-first workflows before saving files. It prevents silent fallbacks and protects pure functional architecture.
★ 40,418repo stars
CAST Imaging Impact Analysis Agent
official subagent This subagent assesses code change risks and ripple effects using CAST Imaging. It maps affected dependencies and helps design targeted test scenarios.
★ 40,418repo stars
Blueprint Mode
official subagent Executes strict workflows (Debug, Express, Main, Loop) to deliver clean fixes without guesses or conversational fluff. Best for disciplined code changes.
★ 40,418repo stars
ai-team-qa
official subagent Acts as a dedicated QA engineer named Ivy to run exploratory checks and report bugs. Validates changes before release without modifying your code.
★ 40,418repo stars
Universal PR Comment Addresser
official subagent Handles pull request review comments one by one. The subagent applies minimal edits and covers changes with tests.
★ 40,418repo stars
Accessibility Expert
official subagent A GitHub Copilot subagent that audits your UI against WCAG 2.1/2.2 and points at what to fix. Useful when forms, dialogs and SPA routes misbehave with a keyboard or screen reader.
★ 40,418repo stars
Accessibility Runtime Tester
official subagent Tests web apps for keyboard operability, focus traps, form error states, and live region updates in runtime. Useful for catching WCAG regressions before deploy.
★ 40,418repo stars
Thinking Beast Mode
official subagent A GitHub Copilot subagent prompt configured for fully autonomous task resolution, recursive online documentation lookups, and strict testing.
★ 40,418repo stars
C# Expert
official subagent Guides the assistant through .NET and C# tasks. It enforces framework conventions, safe async/await patterns, and clean test structure.
★ 40,418repo stars
eval-orchestrator subagent Coordinates plugin and skill quality checks: static analysis, LLM judge, then a composite score and badge.
CX Codex
★ 41,729repo stars
code-review-preshipment subagent A subagent that walks every change since the last deploy through ten review sections and ends with a SHIP, SHIP WITH FIXES or DO NOT SHIP verdict.
CX Codex
★ 41,729repo stars
incident-response-test-automator subagent Writes unit, integration, regression and security tests around a bug fix, then runs the whole suite and reports coverage.
CX Codex
★ 41,729repo stars
codebase-cleanup-test-automator subagent A testing subagent that runs the TDD loop, writes tests and wires them into CI. Useful when coverage is thin or failures keep repeating.
CX Codex
★ 41,729repo stars
backend-development-tdd-orchestrator subagent A subagent that runs the red-green-refactor loop: test first, then code, then cleanup. Useful when a project needs test discipline kept in place.
CX Codex
★ 41,729repo stars
41–80 of 81
