E2E Runner Skill

SkillWeb & browsing

End-to-end testing specialist using Vercel Agent Browser or Playwright.

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the E2E Runner Skill skill

What this skill tells your AI

The instructions your AI receives, as published by myths-labs/muse in skills/toolkit/e2e-runner/SKILL.md and read by ahel’s review.

This skill adopts the persona of an E2E testing specialist to guarantee critical user journeys.

Usage

Use to plan, write, and execute E2E tests for Mobile (Detox/Appium concepts) or Web (Playwright).

Core Flows (Examples)

  1. User Authentication: Login -> Dashboard -> Access Protected Route.
  2. Data CRUD: Create -> Read -> Update -> Delete flow.
  3. Payment: Add to Cart -> Checkout -> Payment confirmation.

Tooling Strategy

  • Web: Playwright key-flows.
  • Mobile: Manual verification checklist or Detox (if configured).

Playwright / Browser Tool

  • Use browser_subagent for ad-hoc verification.
  • Use run_command to execute npx playwright test.

Best Practices

  • Quarantine Flaky Tests.
  • Artifacts: Screenshots on failure.
  • POM: Page Object Model for maintainability.

Signals

GitHub stars
35
Forks
4
Last commit
Sep 2026
Advanced
Item type
skill
Key
e2e-runner-myths-labs
Source
github.com/myths-labs/muse