跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
开发与测试

e2e-testing

Comprehensive E2E testing skill using Playwright MCP for systematic web application testing. This skill should be used when users need to test web-based systems end-to-end, set up test regimes, run exploratory tests, or analyze test history. Triggers on requests like "test my webapp", "set up E2E tests", "run the tests", "what's been flaky", or when validating web application functionality. The skill observes and reports only - it never fixes issues. Supports three modes - setup (create test regime), run (execute tests), and report (analyze results).

mhylle · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add mhylle/claude-skills-collection --skill e2e-testing

技能说明


name: e2e-testing description: Comprehensive E2E testing skill using Playwright MCP for systematic web application testing. This skill should be used when users need to test web-based systems end-to-end, set up test regimes, run exploratory tests, or analyze test history. Triggers on requests like "test my webapp", "set up E2E tests", "run the tests", "what's been flaky", or when validating web application functionality. The skill observes and reports only - it never fixes issues. Supports three modes - setup (create test regime), run (execute tests), and report (analyze results). argument-hint: "[mode: setup|run|report] [url?]"

E2E Testing Skill

Contents

Reference files (open one when a step points to it):

  • references/flexibility-criteria-guide.md: Flexibility Criteria Guide
  • references/history-schema.md: Test History Schema Reference
  • references/test-regime-schema.md: Test Regime Schema Reference

Overview

A comprehensive E2E testing skill using Playwright MCP for systematic testing of any web-based system. The skill:

  • Observes and reports - Never fixes issues, only documents them
  • Discovers paths - Finds undocumented functionality at runtime
  • Tracks history - Identifies flaky areas and suggests variations
  • Produces dual reports - Human-readable and machine-readable formats

Prerequisites

Before using this skill, verify Playwright MCP is available:

  1. Check for playwright in MCP server configuration
  2. If missing, add to Claude settings:
{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": ["@playwright/mcp@latest"]
    }
  }
}

If Playwright MCP is unavailable, inform the user and provide setup instructions before proceeding.

Mode Selection

This skill operates in three modes. Determine mode from user request:

User RequestMode
"Set up tests for...", "Create test regime"Setup
"Run the tests", "Test the...", "Execute tests"Run
"Show test results", "What failed?", "What's flaky?"Report

If unclear, ask: "Would you like to set up a test regime, run existing tests, or view reports?"


Setup Mode

Purpose: Create or update test regime through interactive discovery.

Entry Points

Determine entry point from user context:

ContextEntry
User provides URLURL Exploration
User describes system purposeDescription-Based
User points to documentationDocumentation Extraction
Combination of aboveCombined Flow (recommended)

Setup Workflow

Step 1: Gather Initial Context

Ask for any missing information:

  • URL: Base URL of the application
  • Purpose: What does this system do? (1-2 sentences)
  • Key workflows: What are the critical user journeys?
  • Existing docs: Any README, user stories, or specs?

Step 2: Explore Application

Use Playwright MCP to explore:

Navigate to base URL
Capture accessibility snapshot
Identify:
  - Navigation elements (menus, links)
  - Interactive elements (buttons, forms)
  - Key pages and sections

For each discovered element, note:

  • Element type and purpose
  • Alternative paths to reach it
  • Required preconditions (login, etc.)

Step 3: Discover Alternative Paths

While exploring, actively look for:

  • Multiple ways to accomplish the same goal
  • Hidden or non-obvious functionality
  • Edge cases in navigation

Document discoveries as: "Found alternative: [description]"

Step 4: Define Test Scenarios

For each key workflow, create scenario with:

scenario: [Descriptive name]
description: [What this tests]
preconditions:
  - [Required state before test]
blocking: [true/false - does failure prevent other tests?]
steps:
  - action: [navigate/click/type/verify/wait]
    target: [selector or description]
    value: [input value if applicable]
    flexibility:
      type: [exact/contains/ai_judgment]
      criteria: [specific rules or judgment prompt]
success_criteria:
  - [What must be true for pass]
alternatives:
  - [Alternative path if primary fails]

Step 5: Create Test Regime File

Write regime to tests/e2e/test_regime.yml:

# Test Regime: [Application Name]
# Created: [YYYY-MM-DD]
# Last Updated: [YYYY-MM-DD]

metadata:
  application: [Name]
  base_url: [URL]
  description: [Purpose]

global_settings:
  screenshot_every_step: true
  capture_network: true
  capture_console: true
  discovery_cap: 5  # Max new paths to discover per run

blocking_dependencies:
  - scenario: login
    blocks: [profile, settings, checkout]  # These won't run if login fails

scenarios:
  - scenario: [name]
    # ... scenario definition

Step 6: Present Regime for Review

Show user:

  1. Summary of discovered scenarios
  2. Blocking dependencies identified
  3. Alternative paths found
  4. Ask for confirmation or modifications

Run Mode

Purpose: Execute tests sequentially with full evidence capture.

CRITICA

阅读完整来源 ↗