AGENT SKILL

gauge-skill

Generates Gauge test specifications in Markdown with step implementations in Java, Python, JS, or Ruby. ThoughtWorks' test automation framework. Use when user mentions "Gauge", "spec file", "## Scenario", "step implementation". Triggers on: "Gauge", "Gauge spec", "Gauge framework", "ThoughtWorks test".

License 许可
MIT
最近更新
2026-09-11
Stars
★ 0
Forks
0

01 前言 Front Matter

license
MIT
metadata
{ "author": "TestMu AI", "version": "1.0" }
description
Generates Gauge test specifications in Markdown with step implementations in Java, Python, JS, or Ruby. ThoughtWorks' test automation framework. Use when user mentions "Gauge", "spec file", "## Scenario", "step implementation". Triggers on: "Gauge", "Gauge spec", "Gauge framework", "ThoughtWorks test".

02 资源文件 2

03 SKILL.md 正文

Gauge Automation Skill

Core Patterns

Specification (specs/login.spec)

# Login Feature

## Successful Login
* Navigate to login page
* Enter email "user@test.com"
* Enter password "password123"
* Click login button
* Verify dashboard is displayed
* Verify welcome message contains "Welcome"

## Invalid Credentials
* Navigate to login page
* Enter email "wrong@test.com"
* Enter password "wrong"
* Click login button
* Verify error message "Invalid credentials" is shown

## Login with multiple users
|email             |password |expected  |
|-----------------|---------|----------|
|admin@test.com   |admin123 |Dashboard |
|user@test.com    |pass123  |Dashboard |
|bad@test.com     |wrong    |Error     |

* Login as <email> with <password>
* Verify <expected> page is shown

Step Implementation — Java

import com.thoughtworks.gauge.Step;
import com.thoughtworks.gauge.Table;

public class LoginSteps {
    WebDriver driver;

    @Step("Navigate to login page")
    public void navigateToLogin() {
        driver.get("http://localhost:3000/login");
    }

    @Step("Enter email <email>")
    public void enterEmail(String email) {
        driver.findElement(By.id("email")).sendKeys(email);
    }

    @Step("Enter password <password>")
    public void enterPassword(String password) {
        driver.findElement(By.id("password")).sendKeys(password);
    }

    @Step("Click login button")
    public void clickLogin() {
        driver.findElement(By.cssSelector("button[type='submit']")).click();
    }

    @Step("Verify dashboard is displayed")
    public void verifyDashboard() {
        assertTrue(driver.getCurrentUrl().contains("/dashboard"));
    }
}

Step Implementation — Python

from getgauge.python import step
from selenium import webdriver

@step("Navigate to login page")
def navigate_to_login():
    driver.get("http://localhost:3000/login")

@step("Enter email <email>")
def enter_email(email):
    driver.find_element_by_id("email").send_keys(email)

@step("Click login button")
def click_login():
    driver.find_element_by_css_selector("button[type='submit']").click()

Concepts (Reusable Step Groups — specs/concepts/login.cpt)

# Login as <email> with <password>
* Navigate to login page
* Enter email <email>
* Enter password <password>
* Click login button

Setup: gauge install java (or python, js, ruby)

Init: gauge init java

Run: gauge run specs/ or gauge run specs/login.spec

Cloud Execution on TestMu AI

Set environment variables: LT_USERNAME, LT_ACCESS_KEY

// StepImplementation.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", "Gauge Build");
ltOptions.put("platformName", "Windows 11");
ltOptions.put("video", true);
ltOptions.put("console", true);
browserOptions.setCapability("LT:Options", ltOptions);
Driver.setWebDriver(new RemoteWebDriver(
    new URL("https://hub.lambdatest.com/wd/hub"), browserOptions));

Tags: gauge run --tags "smoke" (use Tags: smoke in spec)

Deep Patterns

See reference/playbook.md for production-grade patterns:

Section What You Get
§1 Project Setup Installation, project structure, environment properties
§2 Spec Files Markdown scenarios, data tables, concepts (.cpt)
§3 Step Implementations Java steps, table-driven steps, assertions
§4 Hooks & Execution BeforeSuite/Scenario/Step, screenshots, browser logs
§5 Page Objects BasePage, concrete pages, usage in steps
§6 Data Management ScenarioDataStore, SpecDataStore, CSV data
§7 LambdaTest Integration Remote driver factory with LT:Options
§8 CI/CD Integration GitHub Actions with parallel execution, XML reports
§9 Debugging Table 12 common problems with causes and fixes
§10 Best Practices 14-item Gauge testing checklist

04 同仓库更多 Skills

NeelakshSaxena
NeelakshSaxena/Vayu

runpodctl

Runpod CLI for managing GPU/CPU workloads from the terminal — pods, serverless endpoints, templates, network volumes, Hub deploys, models, SSH, and file transfer (send/receive). Use for terminal/CI/scripting, Hub browse/deploy, SSH setup, `doctor`, or when the Runpod MCP tools are not connected. For structured tool calls in an MCP-enabled session, prefer runpod-mcp.

★ 0
NeelakshSaxena
NeelakshSaxena/Vayu

runpod

Start here for any Runpod task — running GPU/CPU pods, deploying serverless endpoints, templates, network volumes, building images, or understanding how Runpod works. Routes to the right skill (runpod-mcp, runpodctl, flash, companion-clis, runpod-usage, runpod-templates, runpod-migrate) and indexes two dozen live-verified end-to-end examples (golden paths) — use it when the lane is unclear, and for any multi-step or provisioning task even when it is not.

★ 0
NeelakshSaxena
NeelakshSaxena/Vayu

runpod-usage

How Runpod works and how to work it — pods vs serverless, GPU/VRAM selection, storage, building a container, networking, plus the agentic pod development loop (provision → ssh-exec → set up → poll readiness) and on-pod install hygiene (uv/apt). Use to answer "how does X work", "which GPU", "how do I build a container", or "how do I stand up a workload on a pod". Guidance, not a tool — execute with runpodctl, runpod-mcp, or flash.

★ 0
NeelakshSaxena
NeelakshSaxena/Vayu

runpod-templates

Runpod's official prebuilt pod templates (ComfyUI, PyTorch, and others): what each image ships, which ports and paths it uses, how to pick one, how to pin a version, and what is missing on first boot. Use when a task says "run <X> on a pod" and an official template already covers it, instead of building an image — and when a user needs help with or wants to fix something about a Runpod template they are already running (won't boot, can't reach the UI, missing models, wrong CUDA line, broken ComfyUI workflow metadata on imported workflows): start here and route onward. Deploy with runpodctl or runpod-mcp; end-to-end walkthroughs live in the runpod router's golden paths.

★ 0
NeelakshSaxena
NeelakshSaxena/Vayu

runpod-migrate

Migrate a codebase from the Runpod GraphQL API or REST v1 to REST v2 — inventory which parts use which API version, rewrite the call sites, flag breaking changes, and verify. Use when someone asks to move to v2, asks what v2 would change, or asks which Runpod API their code is on. For managing infrastructure rather than migrating code, use runpod-mcp or runpodctl.

★ 0
NeelakshSaxena
NeelakshSaxena/Vayu

runpod-mcp

Manage Runpod infrastructure — pods, serverless endpoints, jobs, templates, network volumes, container-registry auth, GPU/CPU catalog, and billing — via the Runpod MCP server's structured tool calls. Use when the Runpod MCP tools (create-pod, list-endpoints, …) are connected in this session, or to connect them (hosted OAuth or local npx). Prefer this over runpodctl for plain infra CRUD when MCP is available; use runpodctl for the terminal, file transfer, or SSH setup.

★ 0