Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Execute a structured test plan and emit a concise, comprehensive results document (JSON + Markdown). Use when running test plans, executing QA workflows, verifying acceptance criteria systematically, or producing test results documentation.
Executes test cases from a TestLink plan using browser automation and records pass/fail results per case. Use when a QA engineer wants to execute tests, run tests, execute a test plan, or run test cases against an application.
Diagnose and fix Expo/React Native Android Gradle build failures, especially Kotlin metadata/version mismatches (e.g., "Module was compiled with an incompatible version of Kotlin" / metadata 2.1.0 vs expected 1.9.0) when running `npx expo run:android`, `./android/gradlew assembleDebug`, or EAS local Android builds.
Triage extension for Java findings during plan-finalize phase
Triage extension for JavaScript/TypeScript findings during plan-finalize phase
Triage extension for marketplace plugin findings during plan-finalize phase
Debug browser extension behavior. Use when asked to debug/reproduce extension issues in Chrome/Firefox, or mentions content script/popup/service worker/manifest/permissions.
Review and score engineering specs against a startup-focused quality rubric. Penalize over-engineering and reward simplicity.
System diagnosis skill (READ-ONLY). Verifies feature behavior through code analysis, data validation, and Codex deep confirmation. All operations are strictly read-only - NO data modification allowed.
Use when creating, maintaining, debugging, or reviewing real-browser end-to-end tests with Playwright or Cypress, including Page Object models, CI artifacts, traces, flaky tests, cross-page visual regression, and critical user journeys such as login, payment, permissions, or CRUD. For layer planning or tests close to UI components, choose the matching testing workflow first; Chinese triggers include E2E, 端到端测试, Playwright, Cypress.