LambdaTest/agent-skills

AI agent skills for TestMu AI (Formerly LambdaTest).

TestMu AI Agent Skills (formerly LambdaTest)

What it is – A small Node‑based library that ships “skills” (plug‑in modules) for AI coding assistants such as Claude Code, GitHub Copilot, Cursor or Gemini CLI. The skills teach those assistants how to write test‑automation code for popular frameworks (Selenium, Playwright, Cypress, etc.) and then run the generated tests on the TestMu AI cloud platform.

Core idea

TestMu AI is an agentic quality‑engineering platform. The agent‑skills repository contains the concrete pieces that let a language‑model‑driven assistant understand the TestMu AI API and the syntax of a given test framework, so the assistant can answer natural‑language prompts like:

"Write Playwright tests for the login page and run them on TestMu AI cloud (Chrome + Firefox)"

The assistant uses the installed skill to:

  1. Generate the test code in the requested framework.
  2. Add the required TestMu AI capabilities (e.g., authentication, tunnel flag).
  3. Submit the test to the TestMu AI execution cloud and return the result URL.

What’s inside the repo

Item Purpose
agentskillsforall CLI (installed via npx) A thin wrapper that downloads a skill from this repo and registers it with the user’s AI assistant.
Individual skill packages (e.g., selenium-skill, playwright-skill, cypress-skill) JSON/JS definitions that map natural‑language intents to concrete code snippets and TestMu AI configuration.
Documentation links Guides for installing the CLI, setting environment variables (LT_USERNAME, LT_ACCESS_KEY), and using the skills.
Integration notes for the Rook tool A separate terminal‑based tester for AI agents; its own skill (@testmuai/rook-skill) is installed via a dedicated CLI.

Getting started (as described in the README)

  1. Prerequisites – Node ≥ stable, npm, a TestMu AI account, and an AI coding assistant.
  2. Clone & install
    git clone https://github.com/LambdaTest/agent-skills && cd agent-skills
npx agentskillsforall add https://github.com/LambdaTest/agent-skills.git
  3. Expose credentials
    export LT_USERNAME="your_user"
export LT_ACCESS_KEY="your_key"
  4. Add a skill (example for Playwright)
    npx agentskillsforall add https://github.com/LambdaTest/agent-skills.git --skill playwright-skill
  5. Ask your assistant – type a natural‑language request; the assistant will generate the test and trigger it on the TestMu AI cloud.

Typical use cases

  • Rapid test authoring – developers describe a UI flow in plain English and get a ready‑to‑run Playwright or Selenium test.
  • Cross‑browser/cloud execution – the generated test automatically includes the TestMu AI tunnel flag and runs on the platform’s 10 K+ real devices.
  • CI/CD integration – skills can produce JUnit 5 or Cypress scripts that are then committed and executed via GitHub Actions or other pipelines.
  • Agent evaluation – using the companion Rook skill, teams can automatically generate scenarios, invoke their own AI agents, and grade the output.

Who might benefit

  • QA engineers looking to offload boilerplate test writing to an LLM.
  • Developers who want to prototype end‑to‑end tests without learning the full framework API.
  • Teams already on TestMu AI (or the legacy LambdaTest) that want a seamless AI‑first workflow.
  • Organizations building their own AI coding agents and needing a reference implementation for test‑automation tasks.

Limitations & scope (as per the repo)

  • The repository only provides the skill definitions; the heavy lifting (LLM inference, code generation) is done by the external assistant (Claude Code, Copilot, etc.).
  • It requires a paid TestMu AI account for actual cloud execution.
  • Skills are distributed via the agentskillsforall CLI; there is no separate npm package published to the public registry.

Community & support

TL;DR

TestMu AI Agent Skills is a Node‑based plug‑in collection that teaches AI coding assistants how to write and run test‑automation scripts on the TestMu AI cloud. Install the CLI, add the desired framework skill, and then ask your LLM to generate tests in plain language.

Related

  • Project
    sanjay3290/ai-skills

    A collection of portable, standardized skills for AI coding assistants that enable them to interact with databases, productivity tools, and cloud infrastructure.

  • Project
    google/agents-cli

    A CLI and skill set that enables developers and AI coding assistants to build, evaluate, and deploy enterprise-grade agents on the Gemini Enterprise Agent Platform.

  • Project
    addyosmani/agent-skills

    Agent Skills is a library of 25 Markdown‑based engineering workflows (spec, plan, build, test, review, ship, etc.) that can be installed into many AI coding agents via a simple CLI. It provides slash commands, auto‑build mode, specialist personas, and reference checklists to make AI‑generated code follow senior‑engineer best practices across the entire development lifecycle.

  • Project
    Owl-Listener/designer-skills

    A comprehensive library of design skills and workflows for AI agents, enabling assistants like Claude Code and Gemini CLI to perform professional UX/UI research, strategy, and delivery.

  • Project
    Aaronontheweb/dotnet-skills

    A library of 30 skills and 5 specialized agents for AI coding assistants to ensure .NET development follows production-tested patterns and best practices.