> Generates Cucumber BDD tests with Gherkin feature files and step definitions in Java, JavaScript, or Ruby. Use when user mentions "Cucumber", "Gherkin", "Gherkin", "BDD", "Feature file", "Given/When/Then", "step definitions".
npx skills add https://github.com/LambdaTest/agent-skills --skill cucumber-skill
Feature: User Login
As a registered user
I want to log into the application
So that I can access my dashboard
Background:
Given I am on the login page
Scenario: Successful login
When I enter "[email protected]" in the email field
And I enter "password123" in the password field
And I click the login button
Then I should be redirected to the dashboard
And I should see "Welcome" on the page
Scenario: Invalid credentials
When I enter "[email protected]" in the email field
And I enter "wrongpass" in the password field
And I click the login button
Then I should see an error message "Invalid credentials"
Scenario Outline: Login with various users
When I enter "<email>" in the email field
And I enter "<password>" in the password field
And I click the login button
Then I should see "<result>"
Examples:
| email | password | result |
| [email protected] | admin123 | Dashboard |
| [email protected] | password | Dashboard |
| [email protected] | wrong | Error |
import io.cucumber.java.en.*;
import static org.junit.jupiter.api.Assertions.*;
public class LoginSteps {
private LoginPage loginPage;
private DashboardPage dashboardPage;
@Given("I am on the login page")
public void iAmOnTheLoginPage() {
loginPage = new LoginPage(driver);
loginPage.navigate();
}
@When("I enter {string} in the email field")
public void iEnterEmail(String email) {
loginPage.enterEmail(email);
}
@When("I enter {string} in the password field")
public void iEnterPassword(String password) {
loginPage.enterPassword(password);
}
@When("I click the login button")
public void iClickLogin() {
dashboardPage = loginPage.clickLogin();
}
@Then("I should be redirected to the dashboard")
public void iShouldBeOnDashboard() {
assertTrue(driver.getCurrentUrl().contains("/dashboard"));
}
@Then("I should see {string} on the page")
public void iShouldSeeText(String text) {
assertTrue(dashboardPage.getPageSource().contains(text));
}
}
const { Given, When, Then } = require('@cucumber/cucumber');
const { expect } = require('chai');
Given('I am on the login page', async function() {
await this.page.goto('/login');
});
When('I enter {string} in the email field', async function(email) {
await this.page.fill('#email', email);
});
When('I click the login button', async function() {
await this.page.click('button[type="submit"]');
});
Then('I should see {string} on the page', async function(text) {
const content = await this.page.textContent('body');
expect(content).to.include(text);
});
import io.cucumber.java.*;
public class Hooks {
@Before
public void setUp(Scenario scenario) {
driver = new ChromeDriver();
}
@After
public void tearDown(Scenario scenario) {
if (scenario.isFailed()) {
byte[] screenshot = ((TakesScreenshot) driver).getScreenshotAs(OutputType.BYTES);
scenario.attach(screenshot, "image/png", "failure-screenshot");
}
driver.quit();
}
}
@smoke
Feature: Login
@critical @fast
Scenario: Quick login
...
@slow @regression
Scenario: Full login flow
...
# Run by tag
mvn test -Dcucumber.filter.tags="@smoke"
mvn test -Dcucumber.filter.tags="@smoke and not @slow"
| Bad | Good | Why |
|-----|------|-----|
| UI details in Gherkin | Business language | Readability |
| One step per line of code | Meaningful business steps | Abstraction |
| No Background for shared steps | Use Background | DRY |
| Imperative steps | Declarative steps | Maintainable |
Set environment variables: LT_USERNAME, LT_ACCESS_KEY
Java:
// CucumberHooks.java
ChromeOptions browserOptions = new ChromeOptions();
HashMap<String, Object> ltOptions = new HashMap<>();
ltOptions.put("user", System.getenv("LT_USERNAME"));
ltOptions.put("accessKey", System.getenv("LT_ACCESS_KEY"));
ltOptions.put("build", "Cucumber Build");
ltOptions.put("name", scenario.getName());
ltOptions.put("platformName", "Windows 11");
ltOptions.put("video", true);
browserOptions.setCapability("LT:Options", ltOptions);
driver = new RemoteWebDriver(new URL("https://hub.lambdatest.com/wd/hub"), browserOptions);
JavaScript:
const driver = new Builder()
.usingServer(`https://${process.env.LT_USERNAME}:${process.env.LT_ACCESS_KEY}@hub.lambdatest.com/wd/hub`)
.withCapabilities({ browserName: 'chrome', 'LT:Options': {
user: process.env.LT_USERNAME, accessKey: process.env.LT_ACCESS_KEY,
build: 'Cucumber Build', platformName: 'Windows 11', video: true
}}).build();
| Task | Command |
|------|---------|
| Run all (Java) | mvn test with cucumber-junit-platform-engine |
| Run all (JS) | npx cucumber-js |
| Run tagged | --tags "@smoke" |
| Dry run | --dry-run |
| Generate snippets | Run undefined steps |
reference/playbook.md| § | Section | Lines |
|---|---------|-------|
| 1 | Project Setup & Configuration | Maven, runner, rerun |
| 2 | Feature Writing Patterns | Background, outlines, DataTable |
| 3 | Step Definitions | Typed steps, DI injection |
| 4 | Dependency Injection & Shared State | PicoContainer, ScenarioContext |
| 5 | Hooks (Lifecycle Management) | Before/After ordering, screenshots |
| 6 | Custom Parameter Types | Transformers, DocString |
| 7 | Parallel Execution | Thread-safe, TestNG parallel |
| 8 | Reporting | Allure, masterthought, JSON |
| 9 | CI/CD Integration | GitHub Actions, tag matrix |
| 10 | Debugging Quick-Reference | 10 common problems |
| 11 | Best Practices Checklist | 13 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/cucumber-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.
The instructions reference npx.
Without those the skill loads but fails at the first command.