skills.rest
BMS-kmusial
BMS-kmusialCOMMUNITY
Explore all skills by this author →
GitHub

10x-e2e

Generates and verifies risk-driven Playwright E2E tests against a running application.

Updated May 23, 2026
Search Tags:#anti-patterns#test generation#browser automation#playwright#e2e testing#test verification#risk-driven
One-click install
npx skills add https://github.com/BMS-kmusial/bms-stream-monitor --skill 10x-e2e-bms-kmusial
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: 10x-e2e
Source: https://github.com/BMS-kmusial/bms-stream-monitor/tree/main/.claude/skills/10x-e2e
Command: npx skills add https://github.com/BMS-kmusial/bms-stream-monitor --skill 10x-e2e-bms-kmusial

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Agent-generated E2E tests often pass today but break on the first refactor or fail to catch real regressions. This Skill drives an approved plan's browser-level phases one risk at a time, ensuring each Playwright test actually protects a named risk and fails when that risk materializes. ## Core Features & Use Cases - Risk-driven test generation: Picks browser-level risks from the plan and test-plan, then runs a plan → generate → review → verify loop per risk, producing one hardened test per risk rather than coverage-per-page. - Quality levers and anti-pattern review: Creates a seed spec and E2E rules file, then reviews every generated test against five agent anti-patterns (hallucinated assertion, brittle selector, shared state, wait-for-time, no cleanup) and re-prompts by name. - Deliberate-break verification: Confirms each test goes red when the protected behavior is broken, then reverts the break before committing. - Use Case: After building a flashcard save feature, run the Skill on the plan's E2E phase to generate a Playwright test proving data survives a page reload, verified by temporarily breaking the save behavior. ## Quick Start Run /10x-e2e with a change-id like "save-session phase 6" to drive that plan's browser-level E2E phases against the running app.

Frequently Asked Questions about 10x-e2e

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate Playwright E2E tests from an implementation plan?▼

Invoke the Skill with a change-id or plan path, and it resolves the plan, gates each phase for browser-level fit, then runs a plan → generate → review → verify loop per risk. Each risk produces one reviewed Playwright spec tied to a named test-plan risk.

What makes an AI-generated E2E test reliable instead of flaky?▼

Reliable E2E tests use role-based locators like getByRole, run independently with their own setup and cleanup, wait for state instead of time, and assert business outcomes. This Skill enforces these through a seed spec, an E2E rules file, and a five anti-pattern review.

When should I use E2E tests versus unit tests?▼

Use E2E when a risk crosses several system boundaries such as auth, routing, API, and database, or exists only in the rendered UI. Pure functions, endpoint contracts, and business logic are better covered by unit or integration tests, and this Skill redirects those phases to TDD workflows.

Does this workflow work with Cypress or Selenium instead of Playwright?▼

The shipped seed, rules, and prompt template are tuned for Playwright, but the principles transfer. For Cypress, WebdriverIO, or Selenium you encode equivalent idioms for locators, wait-for-state, and data isolation into your own levers and drive that tool's runner.

Why does the Skill verify tests by deliberately breaking the app?▼

The deliberate-break check confirms a test actually fails when the protected risk materializes, proving the assertion is not decorative. The break is reverted immediately and never committed, so only genuinely protective tests reach the codebase.

What are the prerequisites for running browser-driven E2E generation?▼

Playwright must already be installed with a config, a single-spec run command, an auth pattern like storageState, and a way to start the app. The feature under test must also be built, since E2E drives a running application rather than absent code.

Related Skills

Explore More Software Engineering Skills→
Kuba312Kuba312

10x-e2e

Execute browser-level E2E test phases for identified application risks.

Community
Advanced
HHU3637krHHU3637kr
140

spec-end

Consolidate phase documents, capture lessons, and archive completed Specs.

Community
Advanced
cfrs2005cfrs2005
1.4k

tdd-workflow (测试驱动开发工作流)

Enforces test-driven development with unit, integration, and E2E tests targeting 80% coverage.

Community
Intermediate
hideki5123hideki5123
2

playwright-codegen

Record browser interactions with Playwright codegen and generate structured test suites.

Community
Advanced