Testing agents

devdavv/unity-ai-workflow

Agent Claude Code

Compare two outputs WITHOUT knowing which skill produced them.

DollhouseMCP/mcp-server

Agent

Automated unit test generation for code with comprehensive coverage.

ncoevoet/claude-markdown-health-check

Agent Claude Code

Analyzes logs for anomalies. Use when investigating errors or unexpected behavior in application logs.

ncoevoet/claude-markdown-health-check

Agent Claude Code

Deploys the application to staging. Use when the user asks to push a build to the staging environment.

ncoevoet/claude-markdown-health-check

Agent Claude Code

Reviews diffs for correctness and security issues. Use after code edits to verify quality before a commit.

sandialabs/atlas-ui-3

Agent Claude Code

Use this agent when the user wants to check out a branch or PR in a separate git worktree, set up alongside the current repository. This includes when the user mentions a branch name, PR number, or asks to 'check out', 'review', or 'test' a branch/PR in isolation. The agent creates the worktree as a sibling directory…

sandialabs/atlas-ui-3

Agent Claude Code

Use this agent when code changes have been made and tests need to be executed to verify correctness. This agent should be invoked after completing a logical chunk of work such as implementing a feature, fixing a bug, or refactoring code. Examples:\n\n \nContext: User has just implemented a new WebSocket message…

codeoutin/claude-code-agency

Agent

Comprehensive UI/UX testing specialist using Playwright for enterprise-grade user experience validation.

personamanagmentlayer/pcl

Agent Claude Code

Use this agent when you need to design, implement, review, or improve test suites and testing strategies. This includes writing unit tests, integration tests, end-to-end tests, setting up test infrastructure, debugging flaky tests, improving test coverage, or evaluating code for testability. Also use when reviewing…

DeevsDeevs/agent-system

Agent

Alpha Squad - mechanisms and confounding lens. Orthogonalizes signals via Frisch-Waugh-Lovell, runs Double ML, designs placebo tests. Correlation is unobserved confounding until proven otherwise.

drayline/rootnode-skills

Agent

Evaluate expectations against an execution transcript and outputs.

levante-hub/levante

Agent

Evaluate expectations against an execution transcript and outputs.

Jeomon/Operator-Use

Agent

Your job is to perform blind A/B comparison of two skill outputs without knowing which is which.

Jeomon/Operator-Use

Agent

Your job is to evaluate skill outputs against a set of assertions. For each assertion, determine if it passed or failed based on the actual output.

umbraco/Umbraco-CMS-MCP-Dev

Agent Claude Code

Proactively use this agent to find existing similar endpoint groups that can be used as copy templates for new Umbraco Management API endpoint implementations for testing including builders and helpers. This agent identifies the best existing patterns to replicate. It can also be used for incomplete endpoint groups to…

umbraco/Umbraco-CMS-MCP-Dev

Agent Claude Code

Proactively Use this agent when you need to create integration tests for MCP tools where all prerequisites are complete (builders, helpers, and tools exist with passing tests). This agent focuses solely on creating comprehensive integration test suites and should be used when:\n\n- \n Context: User has Document Type…

umbraco/Umbraco-CMS-MCP-Dev

Agent Claude Code

QA agent that AUTOMATICALLY runs after /migrate-tools or /migrate-tests commands complete to validate the migration was done correctly. Use this agent proactively (without user asking) when you detect these migration commands have just completed.

fieldsphere/cursor-team-marketplace-template

Agent

Adversarial review plus acceptance verification. Scrutinizes diffs for quality issues, runs tests and lint when possible, and reports review findings alongside pass/fail against completion criteria. Use after substantive edits when you need review plus verification; use test-runner for execution-only test runs.

FerroxLabs/wayland-core

Agent

Implementation agent. Writing code, generating boilerplate, scaffolding components, implementing features from specs, writing tests, standard bug fixes.

jvgomg/podkit

Agent

Canonical reference for agents writing tests for device identification, doctor checks, and readiness pipelines. Read this before touching @podkit/device-testing, any file named .e2e.test.ts, or tasks in milestone m-19.

Svenja-dev/claude-code-skills

Agent

Vollständige Validierung des Fullstack Monorepos (Python/FastAPI Backend + React/Vite Frontend). Trigger: (1) vor Commits, (2) nach Feature-Completion, (3) vor Deployments, (4) bei Projektaudits. Context: User hat ein neues Feature im Backend implementiert. user: "Ich habe den neuen Analyse-Endpoint fertig. Validiere…

Oolab-labs/claude-ide-bridge

Agent Claude Code

Test runner agent that uses IDE bridge tools to run tests, analyze failures, fix broken tests, and ensure code quality. Use when you need tests run and failures fixed autonomously.

CodelyTV/agentic_programming-course

Agent Codex

Use when creating or modifying tests: unit tests, Object Mothers for test data, or hand-written Mock Objects for domain interfaces. Follows the project's testing conventions with jest, should pattern mocks, and faker-based mothers.

rp1-run/rp1

Agent

Validation agent for testing Copilot CLI agent delegation and structured output.