Testing commands

jamesbrink/mcp-coroot

Command Claude Code

This directory contains custom slash commands for testing the Coroot MCP server integration.

jamesbrink/mcp-coroot

Command Claude Code

Perform a comprehensive test of the Coroot integration using natural language to verify all functionality works correctly.

jamesbrink/mcp-coroot

Command Claude Code

Execute a comprehensive test of all Coroot MCP tools in a safe, non-destructive manner.

ducpm2303/claude-java-plugins

Command

Part of java-quality

Full quality audit — runs security scan, performance check, and test coverage analysis in sequence and produces a combined report.

alex-feel/claude-code-toolbox

Command

This is a mock slash command file for E2E testing.

dotcommander/cclint

Command

Lint and validate skill definition files.

Evaluris-Solutions/claude-active-directory

Command

Active Directory offensive phase — credential attacks (spray if allowed), AS-REP and Kerberoast workflows, NTLM relay opportunities, delegation abuse paths, ACL-based escalation, AD CS template abuse, lateral movement within ROE. Usage: /hunt corp.local.

appsec-foundry/appsec-advisor

Command Claude Code

Part of appsec-advisor

Manual full-run E2E check — runs the threat-model pipeline against the bundled synthetic-repo fixture and validates 25 structural assertions. Costs 30–50% of a Pro 5h-window; never auto-triggered.

Benkapner/claude-code-basecamp

Command Claude Code

Test LLM prompts against sample inputs. Shows outputs, checks for regressions when prompts change, and compares different prompt versions side-by-side.

Benkapner/claude-code-basecamp

Command Claude Code

Analyze test coverage, identify gaps, and generate missing tests to reach 80%+ coverage.

openva/richmondsunlight.com

Command Claude Code

Re-apply test user fixtures to the Docker database. Run this after a Docker volume reset or if test users are missing.

openva/richmondsunlight.com

Command Claude Code

Run the Playwright browser test suite inside Docker.

JavanC/Homunculus

Command

Run scenario-based tests on a skill to measure its quality.

Parslee-ai/neo

Command Claude Code

Part of neo

Fast implementation with neo protocol gates. Takes a pre-written plan and implements it with strategic review, economic analysis, risk assessment, code review, and testing. Skips research/analysis phases.

namastexlabs/automagik-tools

Command Claude Code

This document integrates the comprehensive QA Director Agent instructions from /commands/qa.md with the enhanced workflow system, ensuring that all QA capabilities and processes are preserved while being embedded into the automated development pipeline.

namastexlabs/automagik-tools

Command Claude Code

You are the TESTER workflow for automagik-tools. Your role is to create comprehensive test suites for MCP tools, ensuring quality, reliability, and MCP protocol compliance.

motlin/claude-code-plugins

Command

Part of code

Rewrite tests to use strict deep equality assertions.

DauQuangThanh/hanoi-rainbow

Command

Execute end-to-end tests based on the E2E test plan and generate detailed test result reports.

redker56/auto-harness

Command

Part of auto-harness

Advance parallel Evaluator-side actions only. Auto-selects review, QA, retest, or final report from status.md. /auto-harness:qa-parallel [sprint].

SiniyaYousuf/everything_claudecode

Command

Part of everything-claude-code

Generate and run E2E tests with Playwright.

SiniyaYousuf/everything_claudecode

Command

Part of everything-claude-code

Go TDD workflow with table-driven tests.

devobsessed/code-captain

Command

Execute a specific task and its sub-tasks systematically following a Test-Driven Development (TDD) workflow. This command reads task specifications from .code-captain/specs/ directories and implements features with comprehensive testing, following established code standards and best practices.

andikarachman/data-science-plugin

Command

Part of ds

Run data quality validation using formal expectation suites, dbt tests, or data contracts.

humanbound/plugins

Command

Part of humanbound-test

Run an adversarial test against the local agent (full flow).