Testing commands

cklxx/elephant.ai

Command Claude Code

An end-to-end test command for Kaku, a tool that manages programming-agent panes, together with Feishu messages and runtime monitoring. It starts from a simulated Feishu message and checks the full agent-team workflow.

Lykhoyda/rn-dev-agent

Command

Part of rn-dev-agent

Execute a learned Maestro flow ("action") by name with optional -e KEY=VALUE parameters. Looks the flow up via packages/rn-dev-agent-core/dist/learned-actions.js (same inventory as /rn-dev-agent:list-learned-actions), then replays it via cdprunaction — auto-repair-aware orchestration with structured RunRecords (GH.

J0hnG4lt/metabase-flightsql-driver

Command Claude Code

Run end-to-end tests for the Metabase Arrow Flight SQL driver. Starts all services from scratch, runs setup, and validates the dashboard works.

kayac/nepp-chan

Command Claude Code

An interactive evaluation command for scoring and displaying the answer quality of a knowledge agent. An evaluation checks whether an agent gives useful and correct answers.

Ecro/embedeval

Command Claude Code

Sequentially author negatives.py for every case that lacks one, with interactive judgment gates where LLM cannot reliably decide.

trainual/tiptap-collaboration-mcp

Command Claude Code

Smoke test the tiptap-collaboration MCP tools against a live server. Use when user says "smoke test", "test tiptap", or "test mcp tools".

armoin2018/ai-ley

Command Claude Code

Generate comprehensive unit testing infrastructure including test configuration, health checks, regression tests, synthetic transactions, coverage dashboards, and CI/CD integration.

cognitive-fab/polygraph

Command

Part of polygraph

Run polygen — draft a contract from a feature description, author a verifiable SAM v2 strict-profile module against it, self-repair against reachable invariant violations, and synthesize a demo/regression trace corpus.

cognitive-fab/polygraph

Command

Part of polygraph

Run polyvers — classify a state-machine version change into compatibility lanes, run the gates those lanes require against fleet snapshots (shape round-trip, vocabulary, in-flight stimuli, migration validation, seeded model check), scaffold migrations, and check parent×child version matrices. No API key.

cognitive-fab/polygraph

Command

Part of polygraph

Run the Polygraph verification loop — generate N transition-function specs from a source file and replay real traces against them, reporting spec-errors vs code-findings.

avansaber/tailtest

Command

Part of tailtest

Run an adversarial pass on $ARGUMENTS -- explicitly try to break the source code.

avansaber/tailtest

Command

Part of tailtest

Generate or update tests for $ARGUMENTS.

let-sunny/canicode

Command Claude Code

Part of canicode

Run the calibration pipeline for a single fixture, all active fixtures, or resume a failed run.

let-sunny/canicode

Command Claude Code

Part of canicode

Review a completed /develop pipeline run and provide a structured QA assessment.

Caspian-Sun/claude-code-workflow

Command Claude Code

You are now acting as a Test Engineer. Generate comprehensive test cases for the specified components/functions.

zircote-plugins/sdlc-quality

Command Claude Code

Part of sdlc

Run automated functional tests using the hook-driven test framework. Execute the test suite to validate all project functionality.

afhverjuekki/claude-code-aristotle-plugin

Command

Part of aristotle

Verify algorithm correctness using Aristotle (96.8% VERINA benchmark accuracy).

rube-de/cc-skills

Command

TDD-driven bugfix workflow: tester writes failing test (RED) → developer fixes (GREEN) → developer refactors (REFACTOR) → reviewer validates. Accepts issue number, description, or both. Auto-creates PR unless --no-pr flag is passed.

ai-plugin-marketplace/template

Command

Part of skill-evaluator

Evaluate a skill across model tiers using blind testing.

paulbreuler/limps

Command Claude Code

Generate a TDD plan with verbose planning docs and minimal agent execution files using MCP planning tools.

codeready-toolchain/tarsy

Command Cursor

Command "create-python-tests" from codeready-toolchain/tarsy, covering writing tests for python llm service, running tests, from project root, from llm-service/ directory and critical rules.

sukirman1901/frontend-expert

Command Claude Code

Part of frontend-expert

Test user-facing UI — frontend-testing, states, a11y; invoke test-engineer.

jesus-seijas-sp/claude-node-setup

Command Claude Code

Run tests for a specific feature or pattern and summarize the results.

xiongchenyu6/dotfiles

Command Claude Code

A command that uses browser automation to run an experience check on the current application or game.