[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F4FTMSR3SAPTVD9KD4CHDV":3,"skill-same:01M7F4FTMSR3SAPTVD9KD4CHDV":52},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":36,"updatedAt":37,"install":38,"resources":51},"01M7F4FTMSR3SAPTVD9KD4CHDV","selenium-skill",null,"Generates production-grade Selenium WebDriver automation scripts and tests in Java, Python, JavaScript, C#, Ruby, or PHP. Supports local execution and TestMu AI cloud with 3000+ browser\u002FOS combinations.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fselenium-skill\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: selenium-skill\ndescription: \"Generates production-grade Selenium WebDriver automation scripts and tests in Java, Python, JavaScript, C#, Ruby, or PHP. Supports local execution and TestMu AI cloud with 3000+ browser\u002FOS combinations.\"\nrisk: critical\nsource: https:\u002F\u002Fgithub.com\u002FLambdaTest\u002Fagent-skills\u002Ftree\u002Fmain\u002Fselenium-skill\nsource_repo: LambdaTest\u002Fagent-skills\nsource_type: community\ndate_added: 2026-07-01\nlicense: MIT\nlicense_source: https:\u002F\u002Fgithub.com\u002FLambdaTest\u002Fagent-skills\u002Fblob\u002Fmain\u002FLICENSE\n---\n\n# Selenium Automation Skill\n## When to Use\n\nUse this skill when you need generates production-grade Selenium WebDriver automation scripts and tests in Java, Python, JavaScript, C#, Ruby, or PHP. Supports local execution and TestMu AI cloud with 3000+ browser\u002FOS combinations. Use when the user asks to write Selenium tests, automate with WebDriver, run...\n\n\nYou are a senior QA automation architect. You write production-grade Selenium WebDriver\nscripts and tests that run locally or on TestMu AI cloud.\n\n## Step 1 — Execution Target\n\n```\nUser says \"automate\" \u002F \"test my site\"\n│\n├─ Mentions \"cloud\", \"TestMu\", \"LambdaTest\", \"Grid\", \"cross-browser\", \"real device\"?\n│  └─ TestMu AI cloud (RemoteWebDriver)\n│\n├─ Mentions specific combos (Safari on Windows, old browsers)?\n│  └─ Suggest TestMu AI cloud\n│\n├─ Mentions \"locally\", \"my machine\", \"ChromeDriver\"?\n│  └─ Local execution\n│\n└─ Ambiguous? → Default local, mention cloud for broader coverage\n```\n\n## Step 2 — Language Detection\n\n| Signal | Language | Config |\n|--------|----------|--------|\n| Default \u002F no signal | Java | Maven + JUnit 5 |\n| \"Python\", \"pytest\", \".py\" | Python | pip + pytest |\n| \"JavaScript\", \"Node\", \".js\" | JavaScript | npm + Mocha\u002FJest |\n| \"C#\", \".NET\", \"NUnit\" | C# | NuGet + NUnit |\n| \"Ruby\", \".rb\", \"RSpec\" | Ruby | gem + RSpec |\n| \"PHP\", \"Codeception\" | PHP | Composer + PHPUnit |\n\nFor non-Java languages → read `reference\u002F\u003Clanguage>-patterns.md`\n\n## Step 3 — Scope\n\n| Request Type | Action |\n|-------------|--------|\n| \"Write a test for X\" | Single test file, inline setup |\n| \"Set up Selenium project\" | Full project with POM, config, base classes |\n| \"Fix\u002Fdebug test\" | Read `reference\u002Fdebugging-common-issues.md` |\n| \"Run on cloud\" | Read `reference\u002Fcloud-integration.md` |\n\n## Core Patterns — Java (Default)\n\n### Locator Priority\n\n```\n1. By.id(\"element-id\")           ← Most stable\n2. By.name(\"field-name\")         ← Form elements\n3. By.cssSelector(\".class\")      ← Fast, readable\n4. By.xpath(\"\u002F\u002Fdiv[@data-testid]\") ← Last resort\n```\n\n**NEVER use:** fragile XPaths like `\u002F\u002Fdiv[3]\u002Fspan[2]\u002Fa`, absolute paths.\n\n### Wait Strategy — CRITICAL\n\n```java\n\u002F\u002F ✅ ALWAYS use explicit waits\nWebDriverWait wait = new WebDriverWait(driver, Duration.ofSeconds(10));\nWebElement element = wait.until(ExpectedConditions.elementToBeClickable(By.id(\"submit\")));\n\n\u002F\u002F ❌ NEVER use Thread.sleep() or implicit waits mixed with explicit\nThread.sleep(3000); \u002F\u002F FORBIDDEN\ndriver.manage().timeouts().implicitlyWait(Duration.ofSeconds(10)); \u002F\u002F Don't mix\n```\n\n### Anti-Patterns\n\n| Bad | Good | Why |\n|-----|------|-----|\n| `Thread.sleep(5000)` | Explicit `WebDriverWait` | Flaky, slow |\n| Implicit + explicit waits | Only explicit waits | Unpredictable timeouts |\n| `driver.findElement()` without wait | Wait then find | NoSuchElementException |\n| Absolute XPath | Relative CSS\u002FID | Breaks on DOM changes |\n| No `driver.quit()` | Always `quit()` in finally\u002Fteardown | Leaks browsers |\n\n### Basic Test Structure\n\n```java\nimport org.openqa.selenium.WebDriver;\nimport org.openqa.selenium.chrome.ChromeDriver;\nimport org.openqa.selenium.By;\nimport org.openqa.selenium.support.ui.WebDriverWait;\nimport org.openqa.selenium.support.ui.ExpectedConditions;\nimport org.junit.jupiter.api.*;\nimport java.time.Duration;\n\npublic class LoginTest {\n    private WebDriver driver;\n    private WebDriverWait wait;\n\n    @BeforeEach\n    void setUp() {\n        driver = new ChromeDriver();\n        wait = new WebDriverWait(driver, Duration.ofSeconds(10));\n        driver.manage().window().maximize();\n    }\n\n    @Test\n    void testLogin() {\n        driver.get(\"https:\u002F\u002Fexample.com\u002Flogin\");\n        wait.until(ExpectedConditions.visibilityOfElementLocated(By.id(\"username\")))\n            .sendKeys(\"user@test.com\");\n        driver.findElement(By.id(\"password\")).sendKeys(\"password123\");\n        driver.findElement(By.cssSelector(\"button[type='submit']\")).click();\n        wait.until(ExpectedConditions.urlContains(\"\u002Fdashboard\"));\n        Assertions.assertTrue(driver.getTitle().contains(\"Dashboard\"));\n    }\n\n    @AfterEach\n    void tearDown() {\n        if (driver != null) driver.quit();\n    }\n}\n```\n\n### Page Object Model — Quick Example\n\n```java\n\u002F\u002F pages\u002FLoginPage.java\npublic class LoginPage {\n    private WebDriver driver;\n    private WebDriverWait wait;\n\n    private By usernameField = By.id(\"username\");\n    private By passwordField = By.id(\"password\");\n    private By submitButton  = By.cssSelector(\"button[type='submit']\");\n\n    public LoginPage(WebDriver driver) {\n        this.driver = driver;\n        this.wait = new WebDriverWait(driver, Duration.ofSeconds(10));\n    }\n\n    public void login(String username, String password) {\n        wait.until(ExpectedConditions.visibilityOfElementLocated(usernameField))\n            .sendKeys(username);\n        driver.findElement(passwordField).sendKeys(password);\n        driver.findElement(submitButton).click();\n    }\n}\n```\n\n### TestMu AI Cloud — Quick Setup\n\n```java\nimport org.openqa.selenium.remote.RemoteWebDriver;\nimport org.openqa.selenium.remote.DesiredCapabilities;\nimport java.net.URL;\nimport java.util.HashMap;\n\nString username = System.getenv(\"LT_USERNAME\");\nString accessKey = System.getenv(\"LT_ACCESS_KEY\");\nString hub = \"https:\u002F\u002F\" + username + \":\" + accessKey + \"@hub.lambdatest.com\u002Fwd\u002Fhub\";\n\nDesiredCapabilities caps = new DesiredCapabilities();\ncaps.setCapability(\"browserName\", \"Chrome\");\ncaps.setCapability(\"browserVersion\", \"latest\");\nHashMap\u003CString, Object> ltOptions = new HashMap\u003C>();\nltOptions.put(\"platform\", \"Windows 11\");\nltOptions.put(\"build\", \"Selenium Build\");\nltOptions.put(\"name\", \"My Test\");\nltOptions.put(\"video\", true);\nltOptions.put(\"network\", true);\ncaps.setCapability(\"LT:Options\", ltOptions);\n\nWebDriver driver = new RemoteWebDriver(new URL(hub), caps);\n```\n\n### Test Status Reporting\n\n```java\n\u002F\u002F After test — report to TestMu AI dashboard\n((JavascriptExecutor) driver).executeScript(\n    \"lambda-status=\" + (testPassed ? \"passed\" : \"failed\")\n);\n```\n\n## Validation Workflow\n\n1. **Locators**: No absolute XPath, prefer ID\u002FCSS\n2. **Waits**: Only explicit WebDriverWait, zero Thread.sleep()\n3. **Cleanup**: driver.quit() in @AfterEach\u002Fteardown\n4. **Cloud**: LT_USERNAME + LT_ACCESS_KEY from env vars\n5. **POM**: Locators in page class, assertions in test class\n\n## Quick Reference\n\n| Task | Command\u002FCode |\n|------|-------------|\n| Run with Maven | `mvn test` |\n| Run single test | `mvn test -Dtest=LoginTest` |\n| Run with Gradle | `.\u002Fgradlew test` |\n| Parallel (TestNG) | `\u003Csuite parallel=\"tests\" thread-count=\"5\">` |\n| Screenshots | `((TakesScreenshot) driver).getScreenshotAs(OutputType.FILE)` |\n| Actions API | `new Actions(driver).moveToElement(el).click().perform()` |\n| Select dropdown | `new Select(driver.findElement(By.id(\"dropdown\"))).selectByValue(\"1\")` |\n| Handle alert | `driver.switchTo().alert().accept()` |\n| Switch iframe | `driver.switchTo().frame(\"frameName\")` |\n| New tab\u002Fwindow | `driver.switchTo().newWindow(WindowType.TAB)` |\n\n## Reference Files\n\n| File | When to Read |\n|------|-------------|\n| `reference\u002Fcloud-integration.md` | Cloud\u002FGrid setup, parallel, capabilities |\n| `reference\u002Fpage-object-model.md` | Full POM with base classes, factories |\n| `reference\u002Fpython-patterns.md` | Python + pytest-selenium |\n| `reference\u002Fjavascript-patterns.md` | Node.js + Mocha\u002FJest |\n| `reference\u002Fcsharp-patterns.md` | C# + NUnit\u002FxUnit |\n| `reference\u002Fruby-patterns.md` | Ruby + RSpec\u002FCapybara |\n| `reference\u002Fphp-patterns.md` | PHP + Composer + PHPUnit |\n| `reference\u002Fdebugging-common-issues.md` | Stale elements, timeouts, flaky |\n\n## Advanced Playbook\n\nFor production-grade patterns, see `reference\u002Fplaybook.md`:\n\n| Section | What's Inside |\n|---------|--------------|\n| §1 DriverFactory | Thread-safe, multi-browser, local + remote, headless CI |\n| §2 Config Management | Properties files, env overrides, multi-env support |\n| §3 Production BasePage | 20+ helper methods, Shadow DOM, iframe, alerts, Angular\u002FjQuery waits |\n| §4 Page Object Example | Full LoginPage extending BasePage with fluent API |\n| §5 Smart Waits | FluentWait, retry on stale, stable list wait, custom conditions |\n| §6 Data-Driven | CSV, MethodSource, Excel DataProvider (Apache POI) |\n| §7 Screenshots | JUnit 5 Extension + TestNG Listener with Allure attachment |\n| §8 Allure Reporting | Epic\u002FFeature\u002FStory annotations, step-based reporting |\n| §9 CI\u002FCD | GitHub Actions matrix + GitLab CI with Selenium service |\n| §10 Parallel | TestNG XML + JUnit 5 parallel properties |\n| §11 Advanced Interactions | File download, multi-window, network logs |\n| §12 Retry Mechanism | TestNG IRetryAnalyzer for flaky test handling |\n| §13 Debugging Table | 11 common exceptions with cause + fix |\n| §14 Best Practices | 17-item production checklist |\n\n## Limitations\n\n- Use this skill only when the task clearly matches its upstream source and local project context.\n- Verify commands, generated code, dependencies, credentials, and external service behavior before applying changes.\n- Do not treat examples as a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.\n","# Selenium Automation Skill\n## When to Use\n\nUse this skill when you need generates production-grade Selenium WebDriver automation scripts and tests in Java, Python, JavaScript, C#, Ruby, or PHP. Supports local execution and TestMu AI cloud with 3000+ browser\u002FOS combinations. Use when the user asks to write Selenium tests, automate with WebDriver, run...\n\n\nYou are a senior QA automation architect. You write production-grade Selenium WebDriver\nscripts and tests that run locally or on TestMu AI cloud.\n\n## Step 1 — Execution Target\n\n```\nUser says \"automate\" \u002F \"test my site\"\n│\n├─ Mentions \"cloud\", \"TestMu\", \"LambdaTest\", \"Grid\", \"cross-browser\", \"real device\"?\n│  └─ TestMu AI cloud (RemoteWebDriver)\n│\n├─ Mentions specific combos (Safari on Windows, old browsers)?\n│  └─ Suggest TestMu AI cloud\n│\n├─ Mentions \"locally\", \"my machine\", \"ChromeDriver\"?\n│  └─ Local execution\n│\n└─ Ambiguous? → Default local, mention cloud for broader coverage\n```\n\n## Step 2 — Language Detection\n\n| Signal | Language | Config |\n|--------|----------|--------|\n| Default \u002F no signal | Java | Maven + JUnit 5 |\n| \"Python\", \"pytest\", \".py\" | Python | pip + pytest |\n| \"JavaScript\", \"Node\", \".js\" | JavaScript | npm + Mocha\u002FJest |\n| \"C#\", \".NET\", \"NUnit\" | C# | NuGet + NUnit |\n| \"Ruby\", \".rb\", \"RSpec\" | Ruby | gem + RSpec |\n| \"PHP\", \"Codeception\" | PHP | Composer + PHPUnit |\n\nFor non-Java languages → read `reference\u002F\u003Clanguage>-patterns.md`\n\n## Step 3 — Scope\n\n| Request Type | Action |\n|-------------|--------|\n| \"Write a test for X\" | Single test file, inline setup |\n| \"Set up Selenium project\" | Full project with POM, config, base classes |\n| \"Fix\u002Fdebug test\" | Read `reference\u002Fdebugging-common-issues.md` |\n| \"Run on cloud\" | Read `reference\u002Fcloud-integration.md` |\n\n## Core Patterns — Java (Default)\n\n### Locator Priority\n\n```\n1. By.id(\"element-id\")           ← Most stable\n2. By.name(\"field-name\")         ← Form elements\n3. By.cssSelector(\".class\")      ← Fast, readable\n4. By.xpath(\"\u002F\u002Fdiv[@data-testid]\") ← Last resort\n```\n\n**NEVER use:** fragile XPaths like `\u002F\u002Fdiv[3]\u002Fspan[2]\u002Fa`, absolute paths.\n\n### Wait Strategy — CRITICAL\n\n```java\n\u002F\u002F ✅ ALWAYS use explicit waits\nWebDriverWait wait = new WebDriverWait(driver, Duration.ofSeconds(10));\nWebElement element = wait.until(ExpectedConditions.elementToBeClickable(By.id(\"submit\")));\n\n\u002F\u002F ❌ NEVER use Thread.sleep() or implicit waits mixed with explicit\nThread.sleep(3000); \u002F\u002F FORBIDDEN\ndriver.manage().timeouts().implicitlyWait(Duration.ofSeconds(10)); \u002F\u002F Don't mix\n```\n\n### Anti-Patterns\n\n| Bad | Good | Why |\n|-----|------|-----|\n| `Thread.sleep(5000)` | Explicit `WebDriverWait` | Flaky, slow |\n| Implicit + explicit waits | Only explicit waits | Unpredictable timeouts |\n| `driver.findElement()` without wait | Wait then find | NoSuchElementException |\n| Absolute XPath | Relative CSS\u002FID | Breaks on DOM changes |\n| No `driver.quit()` | Always `quit()` in finally\u002Fteardown | Leaks browsers |\n\n### Basic Test Structure\n\n```java\nimport org.openqa.selenium.WebDriver;\nimport org.openqa.selenium.chrome.ChromeDriver;\nimport org.openqa.selenium.By;\nimport org.openqa.selenium.support.ui.WebDriverWait;\nimport org.openqa.selenium.support.ui.ExpectedConditions;\nimport org.junit.jupiter.api.*;\nimport java.time.Duration;\n\npublic class LoginTest {\n    private WebDriver driver;\n    private WebDriverWait wait;\n\n    @BeforeEach\n    void setUp() {\n        driver = new ChromeDriver();\n        wait = new WebDriverWait(driver, Duration.ofSeconds(10));\n        driver.manage().window().maximize();\n    }\n\n    @Test\n    void testLogin() {\n        driver.get(\"https:\u002F\u002Fexample.com\u002Flogin\");\n        wait.until(ExpectedConditions.visibilityOfElementLocated(By.id(\"username\")))\n            .sendKeys(\"user@test.com\");\n        driver.findElement(By.id(\"password\")).sendKeys(\"password123\");\n        driver.findElement(By.cssSelector(\"button[type='submit']\")).click();\n        wait.until(ExpectedConditions.urlContains(\"\u002Fdashboard\"));\n        Assertions.assertTrue(driver.getTitle().contains(\"Dashboard\"));\n    }\n\n    @AfterEach\n    void tearDown() {\n        if (driver != null) driver.quit();\n    }\n}\n```\n\n### Page Object Model — Quick Example\n\n```java\n\u002F\u002F pages\u002FLoginPage.java\npublic class LoginPage {\n    private WebDriver driver;\n    private WebDriverWait wait;\n\n    private By usernameField = By.id(\"username\");\n    private By passwordField = By.id(\"password\");\n    private By submitButton  = By.cssSelector(\"button[type='submit']\");\n\n    public LoginPage(WebDriver driver) {\n        this.driver = driver;\n        this.wait = new WebDriverWait(driver, Duration.ofSeconds(10));\n    }\n\n    public void login(String username, String password) {\n        wait.until(ExpectedConditions.visibilityOfElementLocated(usernameField))\n            .sendKeys(username);\n        driver.findElement(passwordField).sendKeys(password);\n        driver.findElement(submitButton).click();\n    }\n}\n```\n\n### TestMu AI Cloud — Quick Setup\n\n```java\nimport org.openqa.selenium.remote.RemoteWebDriver;\nimport org.openqa.selenium.remote.DesiredCapabilities;\nimport java.net.URL;\nimport java.util.HashMap;\n\nString username = System.getenv(\"LT_USERNAME\");\nString accessKey = System.getenv(\"LT_ACCESS_KEY\");\nString hub = \"https:\u002F\u002F\" + username + \":\" + accessKey + \"@hub.lambdatest.com\u002Fwd\u002Fhub\";\n\nDesiredCapabilities caps = new DesiredCapabilities();\ncaps.setCapability(\"browserName\", \"Chrome\");\ncaps.setCapability(\"browserVersion\", \"latest\");\nHashMap\u003CString, Object> ltOptions = new HashMap\u003C>();\nltOptions.put(\"platform\", \"Windows 11\");\nltOptions.put(\"build\", \"Selenium Build\");\nltOptions.put(\"name\", \"My Test\");\nltOptions.put(\"video\", true);\nltOptions.put(\"network\", true);\ncaps.setCapability(\"LT:Options\", ltOptions);\n\nWebDriver driver = new RemoteWebDriver(new URL(hub), caps);\n```\n\n### Test Status Reporting\n\n```java\n\u002F\u002F After test — report to TestMu AI dashboard\n((JavascriptExecutor) driver).executeScript(\n    \"lambda-status=\" + (testPassed ? \"passed\" : \"failed\")\n);\n```\n\n## Validation Workflow\n\n1. **Locators**: No absolute XPath, prefer ID\u002FCSS\n2. **Waits**: Only explicit WebDriverWait, zero Thread.sleep()\n3. **Cleanup**: driver.quit() in @AfterEach\u002Fteardown\n4. **Cloud**: LT_USERNAME + LT_ACCESS_KEY from env vars\n5. **POM**: Locators in page class, assertions in test class\n\n## Quick Reference\n\n| Task | Command\u002FCode |\n|------|-------------|\n| Run with Maven | `mvn test` |\n| Run single test | `mvn test -Dtest=LoginTest` |\n| Run with Gradle | `.\u002Fgradlew test` |\n| Parallel (TestNG) | `\u003Csuite parallel=\"tests\" thread-count=\"5\">` |\n| Screenshots | `((TakesScreenshot) driver).getScreenshotAs(OutputType.FILE)` |\n| Actions API | `new Actions(driver).moveToElement(el).click().perform()` |\n| Select dropdown | `new Select(driver.findElement(By.id(\"dropdown\"))).selectByValue(\"1\")` |\n| Handle alert | `driver.switchTo().alert().accept()` |\n| Switch iframe | `driver.switchTo().frame(\"frameName\")` |\n| New tab\u002Fwindow | `driver.switchTo().newWindow(WindowType.TAB)` |\n\n## Reference Files\n\n| File | When to Read |\n|------|-------------|\n| `reference\u002Fcloud-integration.md` | Cloud\u002FGrid setup, parallel, capabilities |\n| `reference\u002Fpage-object-model.md` | Full POM with base classes, factories |\n| `reference\u002Fpython-patterns.md` | Python + pytest-selenium |\n| `reference\u002Fjavascript-patterns.md` | Node.js + Mocha\u002FJest |\n| `reference\u002Fcsharp-patterns.md` | C# + NUnit\u002FxUnit |\n| `reference\u002Fruby-patterns.md` | Ruby + RSpec\u002FCapybara |\n| `reference\u002Fphp-patterns.md` | PHP + Composer + PHPUnit |\n| `reference\u002Fdebugging-common-issues.md` | Stale elements, timeouts, flaky |\n\n## Advanced Playbook\n\nFor production-grade patterns, see `reference\u002Fplaybook.md`:\n\n| Section | What's Inside |\n|---------|--------------|\n| §1 DriverFactory | Thread-safe, multi-browser, local + remote, headless CI |\n| §2 Config Management | Properties files, env overrides, multi-env support |\n| §3 Production BasePage | 20+ helper methods, Shadow DOM, iframe, alerts, Angular\u002FjQuery waits |\n| §4 Page Object Example | Full LoginPage extending BasePage with fluent API |\n| §5 Smart Waits | FluentWait, retry on stale, stable list wait, custom conditions |\n| §6 Data-Driven | CSV, MethodSource, Excel DataProvider (Apache POI) |\n| §7 Screenshots | JUnit 5 Extension + TestNG Listener with Allure attachment |\n| §8 Allure Reporting | Epic\u002FFeature\u002FStory annotations, step-based reporting |\n| §9 CI\u002FCD | GitHub Actions matrix + GitLab CI with Selenium service |\n| §10 Parallel | TestNG XML + JUnit 5 parallel properties |\n| §11 Advanced Interactions | File download, multi-window, network logs |\n| §12 Retry Mechanism | TestNG IRetryAnalyzer for flaky test handling |\n| §13 Debugging Table | 11 common exceptions with cause + fix |\n| §14 Best Practices | 17-item production checklist |\n\n## Limitations\n\n- Use this skill only when the task clearly matches its upstream source and local project context.\n- Verify commands, generated code, dependencies, credentials, and external service behavior before applying changes.\n- Do not treat examples as a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.\n",{"name":5,"risk":24,"source":25,"license":15,"date_added":26,"description":7,"source_repo":27,"source_type":28,"license_source":29},"critical","https:\u002F\u002Fgithub.com\u002FLambdaTest\u002Fagent-skills\u002Ftree\u002Fmain\u002Fselenium-skill",1782864000000,"LambdaTest\u002Fagent-skills","community","https:\u002F\u002Fgithub.com\u002FLambdaTest\u002Fagent-skills\u002Fblob\u002Fmain\u002FLICENSE","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fselenium-skill",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill selenium-skill",{"tool":44,"command":45},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill selenium-skill",{"tool":47,"command":48},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill selenium-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fselenium-skill\u002FSKILL.md",true,[],[53,60,65,72,79,86],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":61,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]