Back to Skills

generating-end-to-end-tests

jeremylongshore
Updated Today
33 views
409
51
409
View on GitHub
Metaaitestingautomation

About

This skill generates end-to-end tests for web applications using Playwright, Cypress, or Selenium. It automates browser interactions to validate critical user workflows like login, registration, and shopping cart processes. Use it when you need to create comprehensive E2E tests or perform cross-browser and responsive testing.

Documentation

Overview

This skill automates the creation of end-to-end tests, which simulate real user interactions with a web application. By generating tests using Playwright, Cypress, or Selenium, Claude ensures comprehensive coverage of critical user workflows.

How It Works

  1. Identify User Workflow: Claude analyzes the user's request to determine the specific user workflow to be tested (e.g., user registration, product checkout).
  2. Generate Test Script: Based on the identified workflow, Claude generates a test script using Playwright, Cypress, or Selenium. The script includes steps to navigate the web application, interact with elements, and assert expected outcomes.
  3. Configure Test Environment: Claude configures the test environment, including browser selection (Chrome, Firefox, Safari, Edge) and any necessary dependencies.

When to Use This Skill

This skill activates when you need to:

  • Create end-to-end tests for a specific user flow (e.g., "create e2e tests for user login").
  • Generate browser-based tests for a web application.
  • Automate testing of multi-step processes in a web application (e.g., "generate end-to-end tests for adding an item to a shopping cart and completing the checkout process").

Examples

Example 1: Testing User Registration

User request: "Create E2E tests for the user registration workflow on my website."

The skill will:

  1. Generate a Playwright script that automates the user registration process, including filling out the registration form, submitting it, and verifying the successful registration message.
  2. Configure the test to run in Chrome and Firefox.

Example 2: Testing Shopping Cart Functionality

User request: "Generate end-to-end tests for adding an item to a shopping cart and completing the checkout process."

The skill will:

  1. Create a Cypress script that simulates adding a product to the shopping cart, navigating to the checkout page, entering shipping and payment information, and submitting the order.
  2. Include assertions to verify that the correct product is added to the cart, the order total is accurate, and the order confirmation page is displayed.

Best Practices

  • Specificity: Provide clear and specific instructions regarding the user workflow to be tested.
  • Framework Choice: If you have a preference for Playwright, Cypress, or Selenium, specify it in your request. Otherwise, Playwright will be used by default.
  • Environment Details: Specify any relevant environment details, such as the target browser and the URL of the web application.

Integration

This skill can be used in conjunction with other plugins to set up the web application, deploy it to a testing environment, and report test results.

Quick Install

/plugin add https://github.com/jeremylongshore/claude-code-plugins-plus/tree/main/e2e-test-framework

Copy and paste this command in Claude Code to install this skill

GitHub 仓库

jeremylongshore/claude-code-plugins-plus
Path: backups/skills-migration-20251108-070147/plugins/testing/e2e-test-framework/skills/e2e-test-framework
aiautomationclaude-codedevopsmarketplacemcp

Related Skills

sglang

Meta

SGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.

View skill

llamaguard

Other

LlamaGuard is Meta's 7-8B parameter model for moderating LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and can be deployed using vLLM, Hugging Face, or Amazon SageMaker. Use this skill to easily integrate content filtering and safety guardrails into your AI applications.

View skill

evaluating-llms-harness

Testing

This Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.

View skill

langchain

Meta

LangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.

View skill