Testing & Quality skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding, open-ended work without a mechanical metric, or non-Git directories.
debug-pretty-printers
Debug and develop GDB and LLDB pretty printers for ezEngine C++ types. Use this skill when working with ezEngine debugger visualizers in ezEngine-gdb.py, ezEngine.py, or ezEngine.natvis. Covers testing with VisualizerZoo.cpp, common errors, and debugging techniques.
debug-gradient-flow
Diagnose gradient flow issues in training, especially for compiled models (torch.compile/make_fx). Systematically isolates which loss components (energy, force, virial) contribute gradients to which parameters, and identifies where the gradient chain breaks.
predictability
Use when `getX()`나 `fetchX()`에 숨은 부수 효과가 있거나, 같은 종류의 함수들이 서로 다른 반환 타입을 가지거나, 함수 이름과 실제 동작이 다를 때
debug-php-wasm-main-module
Debug PHP.wasm main module crashes including Asyncify errors (unreachable, memory access out of bounds), JSPI errors (SuspendError, trying to suspend JS frames), WASM memory growth bugs, and runtime traps. Use when investigating RuntimeError, null function or signature mismatch, or other WASM-related crashes in the main PHP binary.
debug-php-wasm-side-modules
Debug WASM side modules (dynamic PHP extensions) including dlopen failures, SIDE_MODULE loading, JSPI suspension crashes in extensions, C++ weak symbol issues, and extension runtime errors. Use when working with dynamic extensions like Xdebug, intl, or GD built as WASM side modules.
playground-website-debugging
Debug the WordPress Playground website by running the dev server from source and interacting with it via Playwright MCP. Use when investigating UI bugs, testing website features, checking for JavaScript errors, debugging hanging requests, or verifying WordPress behavior in the browser-based Playground.
opensquad-dev
opensquad development checklist — verifies templates sync, package integrity, and distribution correctness.