Testing commands

polygraphso/litmus

Command

Part of polygraph

Grade an MCP server A–F with the open polygraph litmus (runs the harness).

Infopibe/everything-claude-code

Command

Part of everything-claude-code

Generate and run E2E tests with Playwright.

Infopibe/everything-claude-code

Command

Part of everything-claude-code

Go TDD workflow with table-driven tests.

zotoio/CRUX-Compress

Command Cursor

Run comprehensive tests on all CRUX features via LLM interaction and produce a markdown test report.

geoffjay/claude-plugins

Command

Generate comprehensive tests including unit tests, table-driven tests, benchmarks, and examples with high coverage.

geoffjay/claude-plugins

Command

Generate comprehensive tests for Sinatra routes, middleware, and helpers using RSpec or Minitest.

Harddiikk/dograh-voicelink-plugin

Command

Part of dograh-voicelink-plugin

Verify a VoiceLink ↔ Dograh install — API health, the single WSS endpoint upgrade probe, and (with a token) that voicelink appears in the telephony providers metadata. Read-only.

aaddrick/gh-cli-search

Command

Part of gh-cli-search

Execute comprehensive test suite for all gh CLI search skills.

elmochilyas/laraskills

Command

Enforce TDD workflow with Pest 4 for Laravel 13.

vepo/issues

Command Cursor

Walk every feature-catalog row against routes, roles, and happy paths; report compliance gaps and backlog suggestions.

OXI-717/ai-native-toolkit

Command

Lightweight HTTP load test with Locust. Generates scenario, runs for the duration, outputs markdown report with p50/p95/p99 and error rate.

Kripu77/software-factory

Command

Part of software-factory

Reproduce then TDD-fix a ready-for-agent bug ticket in this checkout. Web bugs get a browser repro first.

skullninja/coco-workflow

Command

Part of coco

Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.

skullninja/coco-workflow

Command

Part of coco

Autonomous execution loop. Runs the TDD cycle repeatedly until all tasks in an epic are complete, with circuit breaker protection and PR workflow.

Justdvp/claude-code-templates

Command Claude Code

Comprehensive testing setup for FastAPI applications with pytest and async support.

raunakkathuria/buildwright

Command

Implement bug fixes, refactors, and features with research, Red-Green-Refactor, docs, verification, security review, and code review.

peterblazejewicz/claude-plugins

Command

Part of dotnet-skills

Implement tasks incrementally in .NET — RED/GREEN/REFACTOR, dotnet build, dotnet test, commit. Add "auto" to run the whole plan in one approved pass.

peterblazejewicz/claude-plugins

Command

Part of dotnet-skills

List the .NET skills, subagents, and lifecycle commands shipped by this plugin (adapted from addyosmani/agent-skills — spec-driven development, TDD, code review, security audit, test engineering, and more with .NET 8+, C# 12+, xUnit/MSTest, EF Core, Avalonia framing).

DanaSandman/claude-code-plugins

Command

Part of accessibility-plugin

Quick accessibility check on a specific file or directory.

Consiliency/Flutter-Structurizr

Command Claude Code

Provide a comprehensive testing report after completion, including.

zhouziyue233/great-econometrics

Command

Part of great-econometrics

Phase 8 Robustness, Heterogeneity & Mechanism Tests. Reads model-spec.md, diagnosticreport.md, and results-memo.md to build a personalised checklist, then runs method-specific robustness checks, heterogeneity analysis, and mechanism tests; generates code; and produces robustness-report.md.

michael-denyer/memory-mcp

Command Claude Code

Part of memory-mcp

Comprehensive interactive testing of all Memory MCP features.

Amey-Thakur/AI-SKILLS

Command

Design an evaluation for an AI agent or LLM feature: what to test, how to grade it, and how to catch regressions.

DYAI2025/Plumbline

Command

Orchestrate an autonomous, defense-in-depth TDD multi-agent team (requirements → spec-sanity gate → planner → coder/reviewer loop → verification/security/validation/judgment gates → human acceptance → retrospective) to build a feature end-to-end against fully verified, independently validated requirements.