Testing commands

HomenShum/NodeBenchAI

Command Claude Code

Review the tests in the current file or feature against the scenario-based testing mandate.

nongjun/feishu-cursor-claw

Command Cursor

A command for testing the backend APIs of a project, including service discovery, authentication checks, endpoint validation, and security-header checks. Backend APIs are the server-side interfaces that applications use to exchange data.

Redtropig/harness-anchor

Command

Part of harness-anchor

Build a C/C++ project under runtime sanitizers (ASan+UBSan by default; TSan separately) and run its tests, reporting findings in fixed sections. Use for crashes, leaks, use-after-free, undefined behavior, or data races — or before merging C/C++ changes. Heavy build, so it is a command, never a hook.

marcoemrich/EXACT-Coding-Exercises

Command Claude Code

You are now in the Green Phase of TDD. Follow these instructions to make the failing test pass with MINIMAL code.

marcoemrich/EXACT-Coding-Exercises

Command Claude Code

You are now in the Red Phase of TDD. Follow these instructions to activate ONE test and make it fail.

marcoemrich/EXACT-Coding-Exercises

Command Claude Code

You are now in the Test List Phase of TDD. Follow these instructions to create a comprehensive test list.

baijum/ukulele-companion

Command Claude Code

Run pre-submission checks — automated gates + manual checklist.

vukkt/token-warden

Command

Part of token-warden

Run the golden benchmark suite for one token-warden agent (or all) and compare results against the frozen run1 and best baselines.

Smart-AI-Memory/empathy-framework

Command Claude Code

Development planning hub - structured approaches for planning, TDD, review, refactoring.

astronomer/astro-airflow-mcp

Command Claude Code

Verify code works with both Airflow 2.x and 3.x.

AdrianRogowski/auto-sdd

Command Claude Code

Pick the next pending feature from the roadmap and build it through the full TDD cycle.

AdrianRogowski/auto-sdd

Command Claude Code

Create or update a feature spec with Gherkin scenarios and ASCII mockups (TDD step 1).

Metalnib/dotnet-episteme-skills

Command

Part of dotnet-episteme-skills

Story QA - multi-agent verification of a story implementation against its spec: per-AC verdicts, code reuse and design conformance, dead code, then adversarial maintainer verification. Finds the spec by explicit path, ticket key in the branch name, or plan files - and asks rather than guessing. Verdict persists to…

paypal/AI-Toolkit

Command ✓ vendor

Part of paypal

Show PayPal sandbox test accounts and scenario-specific testing tips.

Intai/story-flow

Command

Part of story-flow

Execute BDD test scenarios in a .feature file using browser automation. Use --record to generate a Playwright .spec.js file.

Chocolatine75/haunt

Command

Part of haunt

Run a phantom user test session against a running web application.

byh3071-cpu/vhk

Command Claude Code

A dogfooding command for auditing VHK from the viewpoint of a real user. Dogfooding means using a tool yourself to find usability problems, workflow issues, and unexpected behavior.

el-feo/ai-context

Command

Part of ghpm

Execute QA Steps using Playwright automation.

Kazuki-tam/next-stage

Command Cursor

This command performs comprehensive code quality checks. Use it before commits or when implementation is complete.

oyi77/1ai-skills

Command

Part of 1ai-skills

Validate the entire 1ai-skills library for quality, consistency, and completeness.

specmatic/specmatic-mcp-server

Command Claude Code

npm run test:smoke.

PostHog/posthog-for-claude

Command

Part of posthog

Manage PostHog A/B testing experiments.

SylphxAI/coderag

Command Claude Code

Improve test coverage, fix tests, optimize performance, reduce bundle size.

aws-samples/sample-GEDD

Command Claude Code ✓ vendor

You are a GEDD coaching assistant. You guide the user through building a golden evaluation dataset for their AI agent using Open Coding methodology, then help them evaluate and annotate responses — all without leaving Claude Code.