[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AB20EE24CDFKV0REE8HZ91":3,"skill-same:01M7AB20EE24CDFKV0REE8HZ91":71},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7AB20EE24CDFKV0REE8HZ91","reqnroll-skill",null,"Generates production-grade Reqnroll BDD automation scripts for web (Selenium 3\u002F4) and mobile (Appium 2) testing in C#. Supports parallel NUnit execution locally and on TestMu AI cloud. Use when the user asks to write BDD tests, automate with Reqnroll, create .feature files, write Gherkin scenarios, write step definitions, migrate from SpecFlow, or test on browsers\u002FAndroid\u002FiOS. Triggers on: \"Reqnroll\", \"BDD\", \"Gherkin\", \".feature file\", \"step definition\", \"SpecFlow migration\", \"Selenium C#\", \"Appium C#\", \"TestMu\", \"LambdaTest\", \"NUnit BDD\", \"reqnroll.actions.json\".","NeelakshSaxena\u002FVayu","NeelakshSaxena","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F87892838?v=4","01M7A3B9YFS6F6N9DD1787DT86","Neelaksh Saxena","01M7A3B9ZKBT09MNMPX2XN69BY",0,"MIT","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freqnroll-skill\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"Generates production-grade Reqnroll BDD automation scripts for web (Selenium 3\u002F4) and mobile (Appium 2) testing in C#. Supports parallel NUnit execution locally and on TestMu AI cloud. Use when the user asks to write BDD tests, automate with Reqnroll, create .feature files, write Gherkin scenarios, write step definitions, migrate from SpecFlow, or test on browsers\u002FAndroid\u002FiOS. Triggers on: \\\"Reqnroll\\\", \\\"BDD\\\", \\\"Gherkin\\\", \\\".feature file\\\", \\\"step definition\\\", \\\"SpecFlow migration\\\", \\\"Selenium C#\\\", \\\"Appium C#\\\", \\\"TestMu\\\", \\\"LambdaTest\\\", \\\"NUnit BDD\\\", \\\"reqnroll.actions.json\\\".\\n\"\nlicense: \"MIT\"\nmetadata: {\"author\":\"TestMu AI\",\"version\":\"1.0\"}\n---\n## Overview\n\nThis skill guides QA engineers and test architects in writing production-grade Reqnroll\nBDD tests for web and mobile automation in C#. It covers three execution paths — Selenium 4\nwith manual driver management, Selenium 3 via the `Reqnroll.Actions` plugin, and Appium 2\nfor Android mobile — all targeting TestMu AI (LambdaTest) cloud infrastructure.\n\nReqnroll is the actively maintained open-source successor to SpecFlow. Existing SpecFlow\nprojects can migrate by swapping the NuGet package and namespace — no step definition\nrewrites required.\n\n## Key Execution Pathways\n\n**Framework Selection:** Distinguishes between Selenium 4 (manual `DriverFactory`),\nSelenium 3 (`Reqnroll.SpecFlowCompatibility.Actions.LambdaTest` plugin with\n`IBrowserInteractions`), and Appium 2 (`Appium.WebDriver`, `AndroidDriver`).\n\n**Cloud vs Local:** Reads `LT_USERNAME` and `LT_ACCESS_KEY` environment variables;\nroutes to `hub.lambdatest.com` (web) or `mobile-hub.lambdatest.com` (mobile).\nReports pass\u002Ffail to LambdaTest via `lambda-status` JavaScript executor calls in\n`[AfterScenario]`.\n\n**Parallelism:** Uses `[assembly: Parallelizable(ParallelScope.Fixtures)]` with\n`[assembly: LevelOfParallelism(N)]` (NUnit). State is shared between step definition\nclasses via `ScenarioContext` (injected by Reqnroll's DI container), not static fields.\n\n## Core Technical Patterns\n\n### Feature Files (Gherkin)\nEach `.feature` file maps to one test class. Scenarios are tagged (`@tagName`) for\nselective filtering with `dotnet test --filter \"Category=tagName\"`. Background steps\nrun before every scenario in the file; Scenario Outlines drive data-driven testing via\n`Examples` tables.\n\n### Step Definitions\nClasses are decorated with `[Binding]`. Constructor injection (via Reqnroll's built-in\nDI) receives `ScenarioContext` or shared context objects. One `[Binding]` class per\nconcern keeps files small. Regex-based step patterns use `(.*)` or typed captures\n(`(\\d+)`) — no attribute-level type converters needed for primitives.\n\n### Hooks\n`[BeforeScenario]` initialises the driver (stored in `ScenarioContext[\"driver\"]`) and\nnavigates to the base URL. `[AfterScenario]` reads `_scenarioContext.TestError` (web) or\n`TestContext.CurrentContext.Result.Outcome.Status` (mobile) to emit\n`lambda-status=passed\u002Ffailed` before `driver.Quit()`.\n\n### ScenarioContext Driver Sharing\nDrivers are stored as `_scenarioContext[\"driver\"] = driver` and retrieved with\n`scenarioContext[\"driver\"] as IWebDriver`. This is required for parallel execution —\n`static` driver fields cause race conditions.\n\n### Explicit Waits\n`WebDriverWait` with `Until(d => d.FindElement(locator))` replaces `ImplicitWait`\nfor dynamic content. A `WaitAndFind(By)` helper method encapsulates the 10-second\ndefault; a `WaitAndClick(By, int timeout)` variant handles clickability.\n\n## Cloud Integration (TestMu \u002F LambdaTest)\n\n### Web (Selenium 4)\n```csharp\nvar ltOptions = new Dictionary\u003Cstring, object>\n{\n    { \"build\", \"Build Name\" },\n    { \"project\", \"Project Name\" },\n    { \"w3c\", true },\n    { \"selenium_version\", \"4.38.0\" },\n    { \"sessionName\", scenarioName },\n    { \"platformName\", \"Windows 11\" }\n};\nvar options = new ChromeOptions();\noptions.BrowserVersion = \"latest\";\noptions.AddAdditionalOption(\"LT:Options\", ltOptions);\nvar driver = new RemoteWebDriver(\n    new Uri($\"https:\u002F\u002F{userName}:{accessKey}@hub.lambdatest.com\u002Fwd\u002Fhub\"), options);\n```\n\n### Mobile (Appium 2)\n```csharp\nvar ltOptions = new Dictionary\u003Cstring, object>\n{\n    { \"build\", \"Build Name\" },\n    { \"project\", \"Project Name\" },\n    { \"w3c\", true },\n    { \"app\", \"proverbial-android\" },         \u002F\u002F lt:\u002F\u002F URI or pre-uploaded alias\n    { \"platformName\", \"android\" },\n    { \"deviceName\", \"Galaxy.*\" },\n    { \"platformVersion\", \"14\" },\n    { \"isRealMobile\", true },\n    { \"autoAcceptAlerts\", true },\n    { \"autoGrantPermissions\", true },\n    { \"sessionName\", scenarioName }\n};\nvar appiumOptions = new AppiumOptions();\nappiumOptions.AddAdditionalAppiumOption(\"LT:Options\", ltOptions);\nvar driver = new AndroidDriver(\n    new Uri($\"https:\u002F\u002F{userName}:{accessKey}@mobile-hub.lambdatest.com\u002Fwd\u002Fhub\"),\n    appiumOptions);\n```\n\n### Reporting Pass\u002FFail\n```csharp\n\u002F\u002F Web (AfterScenario)\nif (_scenarioContext.TestError == null)\n    ((IJavaScriptExecutor)driver).ExecuteScript(\"lambda-status=passed\");\nelse\n    ((IJavaScriptExecutor)driver).ExecuteScript(\"lambda-status=failed\");\n\n\u002F\u002F Mobile (AfterScenario)\nbool passed = TestContext.CurrentContext.Result.Outcome.Status == TestStatus.Passed;\n((IJavaScriptExecutor)driver).ExecuteScript(\"lambda-status=\" + (passed ? \"passed\" : \"failed\"));\n```\n\n## Quality Checkpoints\n\n- Feature files use descriptive scenario names that double as the LambdaTest session name\n- `ScenarioContext` used for driver sharing — never static fields in parallel runs\n- `[assembly: Parallelizable(ParallelScope.Fixtures)]` declared once in any `.cs` file\n- `LT_USERNAME` and `LT_ACCESS_KEY` read from environment — never hardcoded\n- `lambda-status=passed\u002Ffailed` emitted in every `[AfterScenario]` for cloud runs\n- `WebDriverWait` used throughout — no unconditional `Thread.Sleep` except transient Appium delays\n- Appium locators use `MobileBy.Id` (resource-id) or `MobileBy.AccessibilityId` before XPath\n- `driver.Quit()` always called in `[AfterScenario]` to free cloud device slots\n- `dotnet test --logger \"console;verbosity=detailed\"` surfaces per-scenario pass\u002Ffail\n\n## Reference Structure\n\nThe `reference\u002F` directory contains detailed playbook sections:\n\n| File | Contents |\n|------|----------|\n| `playbook.md` | Full implementation guide: project setup, all three driver modes, parallel execution, CI\u002FCD, debugging table, best practices checklist |\n| `cloud-integration.md` | LambdaTest capability reference, `LT:Options` fields, tunnel setup, build\u002Fsession naming, test observability |\n| `selenium-4-patterns.md` | Selenium 4 patterns: `DriverFactory`, multi-browser, `ChromeOptions`\u002F`FirefoxOptions`\u002F`EdgeOptions`, screenshot on failure |\n| `selenium-3-patterns.md` | Selenium 3 patterns: `Reqnroll.SpecFlowCompatibility.Actions.LambdaTest`, `IBrowserInteractions`, `reqnroll.actions.json` config |\n| `appium-patterns.md` | Appium 2 patterns: `AndroidDriver`, `AppiumOptions`, gesture helpers, `MobileBy` locators, app lifecycle |\n","## Overview\n\nThis skill guides QA engineers and test architects in writing production-grade Reqnroll\nBDD tests for web and mobile automation in C#. It covers three execution paths — Selenium 4\nwith manual driver management, Selenium 3 via the `Reqnroll.Actions` plugin, and Appium 2\nfor Android mobile — all targeting TestMu AI (LambdaTest) cloud infrastructure.\n\nReqnroll is the actively maintained open-source successor to SpecFlow. Existing SpecFlow\nprojects can migrate by swapping the NuGet package and namespace — no step definition\nrewrites required.\n\n## Key Execution Pathways\n\n**Framework Selection:** Distinguishes between Selenium 4 (manual `DriverFactory`),\nSelenium 3 (`Reqnroll.SpecFlowCompatibility.Actions.LambdaTest` plugin with\n`IBrowserInteractions`), and Appium 2 (`Appium.WebDriver`, `AndroidDriver`).\n\n**Cloud vs Local:** Reads `LT_USERNAME` and `LT_ACCESS_KEY` environment variables;\nroutes to `hub.lambdatest.com` (web) or `mobile-hub.lambdatest.com` (mobile).\nReports pass\u002Ffail to LambdaTest via `lambda-status` JavaScript executor calls in\n`[AfterScenario]`.\n\n**Parallelism:** Uses `[assembly: Parallelizable(ParallelScope.Fixtures)]` with\n`[assembly: LevelOfParallelism(N)]` (NUnit). State is shared between step definition\nclasses via `ScenarioContext` (injected by Reqnroll's DI container), not static fields.\n\n## Core Technical Patterns\n\n### Feature Files (Gherkin)\nEach `.feature` file maps to one test class. Scenarios are tagged (`@tagName`) for\nselective filtering with `dotnet test --filter \"Category=tagName\"`. Background steps\nrun before every scenario in the file; Scenario Outlines drive data-driven testing via\n`Examples` tables.\n\n### Step Definitions\nClasses are decorated with `[Binding]`. Constructor injection (via Reqnroll's built-in\nDI) receives `ScenarioContext` or shared context objects. One `[Binding]` class per\nconcern keeps files small. Regex-based step patterns use `(.*)` or typed captures\n(`(\\d+)`) — no attribute-level type converters needed for primitives.\n\n### Hooks\n`[BeforeScenario]` initialises the driver (stored in `ScenarioContext[\"driver\"]`) and\nnavigates to the base URL. `[AfterScenario]` reads `_scenarioContext.TestError` (web) or\n`TestContext.CurrentContext.Result.Outcome.Status` (mobile) to emit\n`lambda-status=passed\u002Ffailed` before `driver.Quit()`.\n\n### ScenarioContext Driver Sharing\nDrivers are stored as `_scenarioContext[\"driver\"] = driver` and retrieved with\n`scenarioContext[\"driver\"] as IWebDriver`. This is required for parallel execution —\n`static` driver fields cause race conditions.\n\n### Explicit Waits\n`WebDriverWait` with `Until(d => d.FindElement(locator))` replaces `ImplicitWait`\nfor dynamic content. A `WaitAndFind(By)` helper method encapsulates the 10-second\ndefault; a `WaitAndClick(By, int timeout)` variant handles clickability.\n\n## Cloud Integration (TestMu \u002F LambdaTest)\n\n### Web (Selenium 4)\n```csharp\nvar ltOptions = new Dictionary\u003Cstring, object>\n{\n    { \"build\", \"Build Name\" },\n    { \"project\", \"Project Name\" },\n    { \"w3c\", true },\n    { \"selenium_version\", \"4.38.0\" },\n    { \"sessionName\", scenarioName },\n    { \"platformName\", \"Windows 11\" }\n};\nvar options = new ChromeOptions();\noptions.BrowserVersion = \"latest\";\noptions.AddAdditionalOption(\"LT:Options\", ltOptions);\nvar driver = new RemoteWebDriver(\n    new Uri($\"https:\u002F\u002F{userName}:{accessKey}@hub.lambdatest.com\u002Fwd\u002Fhub\"), options);\n```\n\n### Mobile (Appium 2)\n```csharp\nvar ltOptions = new Dictionary\u003Cstring, object>\n{\n    { \"build\", \"Build Name\" },\n    { \"project\", \"Project Name\" },\n    { \"w3c\", true },\n    { \"app\", \"proverbial-android\" },         \u002F\u002F lt:\u002F\u002F URI or pre-uploaded alias\n    { \"platformName\", \"android\" },\n    { \"deviceName\", \"Galaxy.*\" },\n    { \"platformVersion\", \"14\" },\n    { \"isRealMobile\", true },\n    { \"autoAcceptAlerts\", true },\n    { \"autoGrantPermissions\", true },\n    { \"sessionName\", scenarioName }\n};\nvar appiumOptions = new AppiumOptions();\nappiumOptions.AddAdditionalAppiumOption(\"LT:Options\", ltOptions);\nvar driver = new AndroidDriver(\n    new Uri($\"https:\u002F\u002F{userName}:{accessKey}@mobile-hub.lambdatest.com\u002Fwd\u002Fhub\"),\n    appiumOptions);\n```\n\n### Reporting Pass\u002FFail\n```csharp\n\u002F\u002F Web (AfterScenario)\nif (_scenarioContext.TestError == null)\n    ((IJavaScriptExecutor)driver).ExecuteScript(\"lambda-status=passed\");\nelse\n    ((IJavaScriptExecutor)driver).ExecuteScript(\"lambda-status=failed\");\n\n\u002F\u002F Mobile (AfterScenario)\nbool passed = TestContext.CurrentContext.Result.Outcome.Status == TestStatus.Passed;\n((IJavaScriptExecutor)driver).ExecuteScript(\"lambda-status=\" + (passed ? \"passed\" : \"failed\"));\n```\n\n## Quality Checkpoints\n\n- Feature files use descriptive scenario names that double as the LambdaTest session name\n- `ScenarioContext` used for driver sharing — never static fields in parallel runs\n- `[assembly: Parallelizable(ParallelScope.Fixtures)]` declared once in any `.cs` file\n- `LT_USERNAME` and `LT_ACCESS_KEY` read from environment — never hardcoded\n- `lambda-status=passed\u002Ffailed` emitted in every `[AfterScenario]` for cloud runs\n- `WebDriverWait` used throughout — no unconditional `Thread.Sleep` except transient Appium delays\n- Appium locators use `MobileBy.Id` (resource-id) or `MobileBy.AccessibilityId` before XPath\n- `driver.Quit()` always called in `[AfterScenario]` to free cloud device slots\n- `dotnet test --logger \"console;verbosity=detailed\"` surfaces per-scenario pass\u002Ffail\n\n## Reference Structure\n\nThe `reference\u002F` directory contains detailed playbook sections:\n\n| File | Contents |\n|------|----------|\n| `playbook.md` | Full implementation guide: project setup, all three driver modes, parallel execution, CI\u002FCD, debugging table, best practices checklist |\n| `cloud-integration.md` | LambdaTest capability reference, `LT:Options` fields, tunnel setup, build\u002Fsession naming, test observability |\n| `selenium-4-patterns.md` | Selenium 4 patterns: `DriverFactory`, multi-browser, `ChromeOptions`\u002F`FirefoxOptions`\u002F`EdgeOptions`, screenshot on failure |\n| `selenium-3-patterns.md` | Selenium 3 patterns: `Reqnroll.SpecFlowCompatibility.Actions.LambdaTest`, `IBrowserInteractions`, `reqnroll.actions.json` config |\n| `appium-patterns.md` | Appium 2 patterns: `AndroidDriver`, `AppiumOptions`, gesture helpers, `MobileBy` locators, app lifecycle |\n",{"license":15,"metadata":24,"description":27},{"author":25,"version":26},"TestMu AI","1.0","Generates production-grade Reqnroll BDD automation scripts for web (Selenium 3\u002F4) and mobile (Appium 2) testing in C#. Supports parallel NUnit execution locally and on TestMu AI cloud. Use when the user asks to write BDD tests, automate with Reqnroll, create .feature files, write Gherkin scenarios, write step definitions, migrate from SpecFlow, or test on browsers\u002FAndroid\u002FiOS. Triggers on: \"Reqnroll\", \"BDD\", \"Gherkin\", \".feature file\", \"step definition\", \"SpecFlow migration\", \"Selenium C#\", \"Appium C#\", \"TestMu\", \"LambdaTest\", \"NUnit BDD\", \"reqnroll.actions.json\".\n","main","7540bbccf0c1ded6156a467b02c95b61ad62413f",".agents\u002Fskills\u002Freqnroll-skill","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena","Currently exploring the intersection of tech","2026-09-11 03:02:31",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add NeelakshSaxena\u002FVayu --skill reqnroll-skill",{"tool":41,"command":42},"bunx","bunx skills add NeelakshSaxena\u002FVayu --skill reqnroll-skill",{"tool":44,"command":45},"pnpm","pnpm dlx skills add NeelakshSaxena\u002FVayu --skill reqnroll-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freqnroll-skill\u002FSKILL.md",true,[49,55,59,63,67],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"reference\u002Fappium-patterns.md","REFERENCE","参考文档",10130,"https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freqnroll-skill\u002Freference\u002Fappium-patterns.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"reference\u002Fcloud-integration.md",5388,"https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freqnroll-skill\u002Freference\u002Fcloud-integration.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"reference\u002Fplaybook.md",17809,"https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freqnroll-skill\u002Freference\u002Fplaybook.md",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"reference\u002Fselenium-3-patterns.md",5759,"https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freqnroll-skill\u002Freference\u002Fselenium-3-patterns.md",{"path":68,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":69,"sourceHtmlUrl":70},"reference\u002Fselenium-4-patterns.md",7492,"https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freqnroll-skill\u002Freference\u002Fselenium-4-patterns.md",[72,80,87,94,101,108],{"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":76,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7ACCCVNCFKMA9X6D15X6G98","runpodctl","Runpod CLI for managing GPU\u002FCPU workloads from the terminal — pods, serverless endpoints, templates, network volumes, Hub deploys, models, SSH, and file transfer (send\u002Freceive). Use for terminal\u002FCI\u002Fscripting, Hub browse\u002Fdeploy, SSH setup, `doctor`, or when the Runpod MCP tools are not connected. For structured tool calls in an MCP-enabled session, prefer runpod-mcp.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frunpodctl\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7ACC63SRHEA5KMCHSMZK2TC","runpod","Start here for any Runpod task — running GPU\u002FCPU 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.","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frunpod\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7ACC0Q1C89N9BZBV91CTQTF","runpod-usage","How Runpod works and how to work it — pods vs serverless, GPU\u002FVRAM 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\u002Fapt). 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.","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frunpod-usage\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7ACBRPE345GF5GM5B8P8RRC","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 \u003CX> 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.","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frunpod-templates\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M7ACBJATHKVX1TWES2F44GY8","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.","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frunpod-migrate\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":76,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":19},"01M7ACBC7GHVH6T9YEAPCG2AP8","runpod-mcp","Manage Runpod infrastructure — pods, serverless endpoints, jobs, templates, network volumes, container-registry auth, GPU\u002FCPU 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.","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frunpod-mcp\u002FSKILL.md",[],[]]