qas-agent-quality-assurance-security
Creates comprehensive test suites including unit, integration, E2E, and security tests
Creates comprehensive test suites including unit, integration, E2E, and security tests
Activates when generating unit tests, integration tests, or test cases for code
Generate comprehensive unit tests for source files with 100% coverage target. Use when writing tests for React components, utility functions, hooks, or API routes. Supports Jest and Vitest frameworks following Pandora coding standards.
TDD for process documentation - test with subagents before writing, iterate until bulletproof
Next.js/TypeScriptプロジェクト向けGherkinシナリオ自動生成スキル。 以下の場合に使用: (1) ユーザーストーリーからBDDシナリオ作成時 (2) PRD/仕様書からテストシナリオ生成時 (3) APIエンドポイントの振る舞い定義時 (4) ページ遷移・UIインタラクションのシナリオ化時
Use this skill when working with SkylineTester or the test list file.
This skill should be used when the user asks about "shared examples", "shared contexts", "spec structure", "test organization", "describe blocks", "RSpec tagging", "spec file layout", or needs guidance on organizing and structuring RSpec test suites.
Reviews test code for assertion quality including precision levels, property coverage, and validation patterns. Use as part of parallel test review execution.
Testing patterns for Jest, Vitest, and Pytest. Covers test structure (AAA pattern), mocking strategies, fixtures, assertions, and testing best practices. Trigger: When writing tests, when setting up test frameworks, when implementing mocks, when creating test fixtures, when following TDD practices.
Comprehensive guide for debugging failing Playwright tests in this Cucumber project. Use this when tests are failing, elements are not found, or timeouts occur.
This skill should be used when the user needs to 'debug web applications', 'test UI interactions', 'capture screenshots or network requests', 'test desktop automation', or needs to select between testing tools. Routes to platform-specific E2E testing skills: Chrome MCP for debugging, Playwright for CI/CD, Hammerspoon for macOS, Linux for X11/Wayland.
Clean up test sessions - kill browsers, stop dev servers, free ports, and optionally remove test data. Use this BEFORE starting new tests or AFTER completing tests.
Generates comprehensive BDD/Gherkin tests for features. Triggers when user needs to write tests, create test scenarios, add test coverage, or verify feature completeness.
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Audits the TDD implementation plan (Common Implementation Plan & Draft Issues) before execution. Ensures alignment with Specs, Architecture, and TDD principles.
Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization
Stabilize Playwright codegen recordings into reliable, maintainable automations. Use when a Playwright script recorded via codegen is flaky, fails when replayed, or requires frequent edits due to unstable locators, timing issues, popups/dialogs, multi-window flows, or dynamic DOM. Provides a repeatable workflow: convert recordings into intent-based locators, centralize selectors and tunables in config, add step contracts and diagnostics (trace/screenshot/HTML/a11y dumps), and use Playwright MCP (if available) to debug failures and validate fixes.
Create functional test for HTTP controllers and LiveComponents. Use when testing web endpoints, form submissions, API responses, or LiveComponent interactions. Tests make HTTP requests and verify responses/DOM.
Run tests and systematically fix all failing tests using smart error grouping. Use when user asks to fix failing tests, mentions test failures, runs test suite and failures occur, or requests to make tests pass.