TestMu AI Agent Skills
About 70 test automation skills: Selenium, Playwright, Cypress, Appium, JUnit, pytest and more, with runs on the TestMu AI cloud
- 390 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- For cloud runs, tests and page data go to the TestMu AI platform under your username and access key
- The agent writes tests and runs them on your machine, and the `agentskillsforall` installer runs through npx
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/testmu-ai-agent-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- For cloud runs, tests and page data go to the TestMu AI platform under your username and access key
- The agent writes tests and runs them on your machine, and the `agentskillsforall` installer runs through npx
This is third-party code. Review the repository files before installing.
What it does
The repository of the TestMu AI testing cloud vendor (formerly LambdaTest) collects skills that guide an agent in writing automated tests for the major frameworks. The index lists about 70 skills: Selenium, Playwright, Cypress, Puppeteer, WebdriverIO, Appium, Espresso, XCUITest, Detox, Flutter, Jest, Mocha, Vitest, pytest, JUnit 5, TestNG, NUnit, xUnit, RSpec, PHPUnit, Cucumber, Robot Framework and others. Separate skills cover API tests, accessibility, SmartUI visual checks, HyperExecute runs, CI/CD and migration between frameworks. The `selenium-skill` shows the logic: the agent first picks a run target, local or the TestMu AI cloud, then detects the project language (Java by default, also Python, JavaScript, C#, Ruby, PHP) and the scope, from a single test to a full project with page objects and base classes. For the cloud the skills feed `LT_USERNAME` and `LT_ACCESS_KEY` into the run and can turn on a tunnel for locally hosted apps. The skills install through the `agentskillsforall` installer, which can add one skill by name or list them.
Who it is for. QA engineers and developers who automate web and mobile testing and want Claude Code, Cursor or Copilot to write tests in the style of the chosen framework and, if wanted, run them in the cloud.
Good fit when
- A team writes tests in Selenium, Playwright or Cypress and wants a consistent locator and structure style
- A test has to pass in Chrome and Firefox on a cloud farm without an in-house device park
- A mobile app is checked through Appium, Espresso, XCUITest or Detox
- A suite moves from one framework to another and the agent needs migration rules
- A CI/CD pipeline or API tests get ready-made patterns
Not a fit when
- The TestMu AI cloud does not suit you: the skills point to it for broad coverage, although local execution stays the default
- You need one skill for one framework and would rather not install the whole repository: install by name with `--skill`
- Tests are written in a language with no skill in the list
- Data from the pages under test cannot go to an external cloud platform
Example request
Write Playwright tests for the login page and run them on the TestMu AI cloud in Chrome and FirefoxLimitations
Cloud runs need a TestMu AI account, with the username and access key in `LT_USERNAME` and `LT_ACCESS_KEY`. Node.js and npm are also required for the `agentskillsforall` installer. Testing locally hosted apps takes a tunnel, with separate guides for Windows, macOS and Linux, and `tunnel: true` in the test capabilities. The skill for testing AI agents, Rook, installs separately with `npx @testmuai/rook-skill` and needs Node.js 22 or newer. The skills hint patterns to the agent but do not guarantee a working test, so confirm the result by running it. The descriptions claim over 3000 browsers and over 10 thousand real devices; those figures describe the platform and have nothing to do with the skills.
How to disable. Delete the skill folders you added, for example `selenium-skill`, from your agent's skills directory. Remove `LT_USERNAME` and `LT_ACCESS_KEY` from the environment and, if you like, reissue the access key in your TestMu AI account. If you ran `git clone`, delete the clone folder.
FAQ
How do I install the TestMu AI skills in Claude Code?
Run `npx agentskillsforall add https://github.com/LambdaTest/agent-skills.git`, and to add one skill append `--skill selenium-skill`, `--skill playwright-skill` or `--skill cypress-skill`. Node.js and npm are required.
How do I see which skills exist?
`npx agentskillsforall list https://github.com/LambdaTest/agent-skills.git` prints the whole list. The same list sits in `skills_index.json` at the repository root.
Do I need a TestMu AI account?
For cloud runs, yes: set `LT_USERNAME` and `LT_ACCESS_KEY` in the environment. The skills also work with local runs and no cloud.
Which languages and frameworks are covered?
More than 15 languages, among them Java, Python, JavaScript, C#, Ruby and PHP. Frameworks: Selenium, Playwright, Cypress, Puppeteer, Appium, Jest, pytest, JUnit, TestNG, NUnit, RSpec and others, each in its own `*-skill` folder.
How do I test an app on my own machine in the cloud?
Start the TestMu AI tunnel following the guide for your system and add `tunnel: true` to the test capabilities. The cloud browser then opens the page from your local machine.
Discussion
No questions or reviews yet.
Related
SkillsSeven QA agents and ten skills for test automation: Playwright in TypeScript, Selenium in Java, API, accessibility and ISTQB.
Guides for agents writing and fixing Playwright tests, with advice on locators, waiting and diagnosing CI failures
MCP server, agent and skills for end-to-end UI tests where the agent drives the computer through vision on cloud machines
A skill that guides Claude Code and Codex through writing and fixing pytest API tests with a real-run verification loop.
An MCP server for end-to-end testing: the agent sees a running Flutter, React Native, Electron or other app and drives it
Validates Agent Skills packages: structure, links, token weight and instruction quality, with optional LLM-as-judge scoring
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| TestMu AI Agent Skills (this card) | yes | 390 | |
| QA Wolf CLI | no | 3,459 | a CLI that runs QA Wolf service scenarios; here skills for writing tests on open frameworks |
| TestDino Playwright Skill | no | 412 | guides for Playwright only; here about 70 skills for many frameworks and cloud runs |
README in short
The page introduces the TestMu AI platform, lists requirements and install steps, shows commands for individual skills and two example prompts for an agent. Next come a section on the tunnel for local apps, the Rook skill with its own installer and a note on the rename from LambdaTest to TestMu AI.
README badge
Original SKILL.md
--- name: selenium-skill description: > 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/OS combinations. Use when the user asks to write Selenium tests, automate with WebDriver, run cross-browser tests on Selenium Grid, or mentions "Selenium", "WebDriver", "RemoteWebDriver", "ChromeDriver", "GeckoDriver". Triggers on: "Selenium", "WebDriver", "browser automation", "Selenium Grid", "cross-browser", "TestMu", "LambdaTest". languages: - Java - Python - JavaScript - C# - Ruby category: e2e-testing license: MIT metadata: author: TestMu AI version: "1.0" --- # Selenium Automation Skill You are a senior QA automation architect. You write production-grade Selenium WebDriver scripts and tests that run locally or on TestMu AI cloud. ## Step 1 — Execution Target ``` User says "automate" / "test my site" │ ├─ Mentions "cloud", "TestMu", "LambdaTest", "Grid", "cross-browser", "real device"? │ └─ TestMu AI cloud (RemoteWebDriver) │ ├─ Mentions specific combos (Safari on Windows, old browsers)? │ └─ Suggest TestMu AI cloud │ ├─ Mentions "locally", "my machine", "ChromeDriver"? │ └─ Local execution │ └─ Ambiguous? → Default local, mention cloud for broader coverage ``` ## Step 2 — Language Detection | Signal | Language | Config | |--------|----------|--------| | Default / no signal | Java | Maven + JUnit 5 |