测试与 QA

swift-concurrency-expert

3.9Ktesting-qa

Swift Concurrency review and remediation for Swift 6.2+. Use when asked to review Swift Concurrency usage, improve concurrency compliance, or fix Swift concurrency compiler errors in a feature or file. Concrete actions include adding Sendable conformance, applying @MainActor annotations, resolving actor isolation warnings, fixing data race diagnostics, and migrating completion handlers to async/await.

dimillian

sigma

3.8Ktesting-qa

使用布鲁姆2-Sigma掌握学习法的个性化1对1 AI导师。通过苏格拉底式提问、自适应节奏和丰富的视觉输出（HTML仪表盘、Excalidraw概念图、生成图像）引导用户学习任何主题。当用户想学习某内容、研究主题、理解概念、请求辅导、说“教我”、“我想学”、“逐步解释X”、“帮我理解”或调用/sigma时使用。触发词：学习、研究、教学、辅导、理解、掌握、逐步解释。

sanyuan0704

ui-test

3.7Ktesting-qa

基于 browse CLI 的 AI 驱动对抗性 UI 测试。通过分析 git diff 仅测试变更部分，或探索整个应用以发现缺陷。测试功能正确性、可访问性、响应式布局和 UX 启发式规则。适用于用户要求测试 UI 变更、QA 拉取请求、审计可访问性或进行探索性测试的场景。支持本地浏览器（localhost）和远程 Browserbase（已部署站点）。

browserbase

earth2studio-create-datasource

Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores. Do NOT use for fetching data with existing sources, model inference, or installation tasks.

earth2studio-create-prognostic

Create Earth2Studio prognostic (time-stepping forecast) model wrappers. Do NOT use for diagnostic models, data sources, or installation.

deepstream-generate-pipeline

Build DeepStream GStreamer pipelines interactively. Use when the user asks about pipelines for video/image inference, detection, tracking, or streaming — including natural phrases like 'pipeline to infer on image', 'run inference on video', 'detect objects in stream', 'save inference output', 'deepstream pipeline', 'gst-launch pipeline', 'process video with detection', 'build a pipeline', or any request involving GStreamer/DeepStream elements (nvinfer, nvstreammux, nvtracker, etc.).

deepstream-sop

Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the user does not name it: verify operator step sequence, detect missing or out-of-order SOP steps, score factory/work-cell video for procedure compliance, run VLM-based SOP checking on industrial cameras, or call /v1/chat/completions with a file, RTSP, or Basler camera. Also trigger for its internals: SOPVideoProcessor, DeepStream GEBD model (e.g. DDM) via Triton CAPI, nvds_custom_postprocess, Cosmos Reason 1/2 vLLM, SSE streaming, Kafka NvProto/JSON output, Basler/Pylon camera + emulation, Docker compose, chunk-level latency. Do NOT trigger for generic DeepStream pipelines, object detection/tracking, NIM imports, or video summarization.

dogfood

使用 agent-device 在 iOS/Android 上系统性地探索和测试移动应用，以发现错误、用户体验问题及其他问题。当被要求进行内部测试、质量保证、探索性测试、查找问题、错误排查或测试此移动应用时使用。

callstackincubator

react-native-testing

3.4Ktesting-qa

使用 React Native Testing Library (RNTL) v13 和 v14 (`@testing-library/react-native`) 编写组件测试。适用于编写、评审或修复 React Native 组件测试场景。覆盖核心 API 与模式：render、screen、各种查询方法 (getBy/getAllBy/queryBy/findBy)、Jest matchers、userEvent、fireEvent、waitFor 以及异步测试模式。支持 v13（React 18，同步渲染）和 v14（React 19+，异步渲染）。触发场景：React Native 组件测试文件、导入了 RNTL，或提及“testing library”、“write tests”、“component tests”、“RNTL”等。

callstack