> Generates TestNG tests in Java with groups, data providers, parallel execution, XML suite configuration, and listeners. Use when user mentions "TestNG", "testng.xml", "TestNG suite", "parallel tests Java".
npx skills add https://github.com/LambdaTest/agent-skills --skill testng-skill
import org.testng.annotations.*;
import org.testng.Assert;
public class LoginTest {
@BeforeMethod
public void setUp() { /* setup */ }
@Test(groups = "smoke")
public void testLoginSuccess() {
Assert.assertTrue(loginService.login("[email protected]", "password123"));
}
@Test(groups = "regression", dependsOnMethods = "testLoginSuccess")
public void testAccessDashboard() {
Assert.assertNotNull(dashboard.getContent());
}
@Test(expectedExceptions = AuthenticationException.class)
public void testLoginInvalidPassword() {
loginService.login("[email protected]", "wrong");
}
@AfterMethod
public void tearDown() { /* cleanup */ }
}
@DataProvider(name = "loginData")
public Object[][] loginData() {
return new Object[][] {
{"[email protected]", "admin123", true},
{"[email protected]", "password", true},
{"[email protected]", "wrong", false},
};
}
@Test(dataProvider = "loginData")
public void testLogin(String email, String password, boolean expected) {
Assert.assertEquals(loginService.login(email, password), expected);
}
<!DOCTYPE suite SYSTEM "https://testng.org/testng-1.0.dtd">
<suite name="Regression" parallel="tests" thread-count="5">
<test name="Smoke">
<groups><run><include name="smoke"/></run></groups>
<classes><class name="tests.LoginTest"/></classes>
</test>
<test name="Full">
<groups><run><include name="regression"/><exclude name="flaky"/></run></groups>
<packages><package name="tests.*"/></packages>
</test>
</suite>
<suite parallel="methods" thread-count="5"> <!-- Method level -->
<suite parallel="classes" thread-count="5"> <!-- Class level -->
<suite parallel="tests" thread-count="5"> <!-- Test level -->
SoftAssert soft = new SoftAssert();
soft.assertEquals(user.getName(), "Alice");
soft.assertEquals(user.getAge(), 25);
soft.assertTrue(user.isActive());
soft.assertAll(); // Reports all failures at once
public class TestListener implements ITestListener {
@Override public void onTestFailure(ITestResult result) {
System.out.println("Failed: " + result.getName());
// Take screenshot, log, etc.
}
}
@Listeners(TestListener.class)
public class LoginTest { /* ... */ }
@BeforeSuite → @BeforeTest → @BeforeClass → @BeforeMethod → @Test → @AfterMethod → @AfterClass → @AfterTest → @AfterSuite
| Bad | Good | Why |
|-----|------|-----|
| dependsOnMethods everywhere | Independent tests | Cascading failures |
| No groups | @Test(groups = "smoke") | Can't run subsets |
| Hard-coded test data | @DataProvider | Reusable |
| Priority ordering | Independent tests | Fragile |
| Task | Command |
|------|---------|
| Run suite | mvn test -DsuiteXmlFile=testng.xml |
| Run group | mvn test -Dgroups=smoke |
| Run class | mvn test -Dtest=LoginTest |
| Reports | test-output/index.html |
reference/playbook.md| § | Section | Lines |
|---|---------|-------|
| 1 | Project Setup & Configuration | Maven + Surefire config |
| 2 | Suite XML Configuration | Multi-env, parallel, groups |
| 3 | BaseTest & Thread-Safe Driver | ThreadLocal, ConfigReader |
| 4 | Data Providers (Advanced) | Excel, JSON, CSV, parallel, cross-class |
| 5 | Factory Pattern | Cross-browser matrix |
| 6 | Listeners (Production Suite) | Retry, screenshot, timing |
| 7 | Soft Assertions & Dependencies | Groups, method deps |
| 8 | Page Object Integration | PageFactory, fluent POs |
| 9 | Parallel Execution Strategies | Method/class/test/mixed |
| 10 | Reporting Integration | Allure, ExtentReports |
| 11 | CI/CD Integration | GitHub Actions, Jenkins |
| 12 | Debugging Quick-Reference | 12 common problems |
| 13 | Best Practices Checklist | 14 items |
Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.
Use when working with error debugging multi agent review
Build evaluation frameworks for agent systems. Use when testing agent performance systematically, validating context engineering choices, or measuring improvements over time.
Diagnoses and debugs A2A agent communication issues including agent status, message routing, transport connectivity, and log analysis. Use when agents aren't responding, messages aren't being delivered, routing is incorrect, or when debugging orchestrator, coder-agent, tester-agent communication problems.
Use when working with error debugging multi agent review
Rapidly creates atomic, focused skills optimized with evidence-based prompting, specialist agents, and systematic testing. Each micro-skill does one thing exceptionally well using self-consistency, program-of-thought, and plan-and-solve patterns. Enhanced with agent-creator principles and functionality-audit validation. Perfect for building composable workflow components.
Ultimate multi-agent framework for Google Antigravity. Orchestrates specialized domain agents (PM, Frontend, Backend, Mobile, QA, Debug) via Serena Memory.
This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines.
Take lambdatest/testng-skill from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.