测试与 QA

aspnet-core

遵循微软最新的 .NET Web 开发官方指南，进行 ASP.NET Core Web 应用的构建、代码审查、重构与架构设计。适用于开发或处理 Blazor Web Apps、Razor Pages、MVC、Minimal APIs、基于 Controller 的 Web API、SignalR、gRPC、中间件、依赖注入、配置、身份认证、授权、测试、性能优化、部署或 ASP.NET Core 版本升级等场景。

openai

mvcc

Overview of Experimental MVCC feature - snapshot isolation, versioning, limitations

tursodatabase

debugging

How to debug tursodb using Bytecode comparison, logging, ThreadSanitizer, deterministic simulation, and corruption analysis tools

tursodatabase

ce-test-xcode

使用 XcodeBuildMCP 在模拟器上构建并测试 iOS 应用。

everyinc

ce-test-browser

对当前分支或 PR 影响的页面运行浏览器测试。

everyinc

ce-debug

针对错误和失败行为的诊断循环。适用于错误、堆栈跟踪、回归、失败的测试、问题跟踪器中的 bug、修复失败后卡住的调查，或要求调试/修复 bug 的请求。

everyinc

context-mode-ops

20Ktesting-qa

Manage context-mode GitHub issues, PRs, releases, and marketing with parallel subagent army. Orchestrates 10-20 dynamic agents per task. Use when triaging issues, reviewing PRs, releasing versions, writing LinkedIn posts, announcing releases, fixing bugs, merging contributions, validating ENV vars, testing adapters, or syncing branches.

mksglu

shot

19Ktesting-qa

PUA Shot — compact all-in-one PUA reference for explicit injection into sub-agents or short sessions. Strong flavor, same evidence-first behavior.

tanweai

managed-airflow-migrations

19Ktesting-qa

Provides guidance for migrating Apache Airflow DAGs in Managed Service for Apache Airflow (MSAA; formerly Cloud Composer). Covers migration to Airflow 2.11.1 (MSAA Gen 2 and 3) and Airflow 3 (MSAA Gen 3), including environment inspection, GCS download/upload and scanning patterns for breaking changes. Use when migrating the DAG code to newer Airflow version. Don't use when checking DAG run failures unrelated to code migration.

google

pua

19Ktesting-qa

当用户表达沮丧、重复失败、质量投诉、被动行为，或提出重试、换个思路、别放弃，以及要求在完成前提供证据/完成度检查/运行测试，或者希望获得钉钉风格的职场提醒时，使用本 Skill 进行 PUA/高压提效指导。触发词包括：try harder, stop giving up, figure it out, again??, why still failing, change approach, no evidence, run tests, done without proof, 换个方法, 再试试, 别摆烂, 别偷懒, 为什么还不行, 又错了, 证据呢, 没跑测试别说完成, 验收, 闭环, 自嗨, 置身钉外, 无招, 老板体感。对于平静的首次请求，请勿使用。

tanweai

img2threejs

16Ktesting-qa

Turn an object or character reference image into a quality-gated, animation-ready procedural Three.js model built in code. Use for image-to-3D reconstruction, detail-accurate object rebuilds, stylized/likeness-maximized human characters, sculpt specs, and staged code generation.

img2threejs

agent-platform-skill-registry

15Ktesting-qa

与 Gemini Enterprise Agent 平台技能注册表交互，创建和搜索可用技能。使用此技能让代理注册功能或发现新能力。

google

react-native-dev

13Ktesting-qa

React Native and Expo development guide covering components, styling, animations, navigation, state management, forms, networking, performance optimization, testing, native capabilities, and engineering (project structure, deployment, SDK upgrades, CI/CD). Use when: building React Native or Expo apps, implementing animations or native UI, managing state, fetching data, writing tests, optimizing performance, deploying to App Store/Play Store, setting up CI/CD, upgrading Expo SDK, or configuring Tailwind/NativeWind.

minimax-ai

shader-dev

13Ktesting-qa

全面的 GLSL 着色器技术指南，助力打造惊艳的视觉特效 —— 涵盖光线步进 (Ray Marching)、SDF 建模、流体模拟、粒子系统、程序化生成、光照渲染、后处理等核心技术。

minimax-ai

dev

12Ktesting-qa

playwright-cli 仓库的开发与维护工作流。当用户询问依赖更新 (Rolling)、版本发布或其他仓库日常维护任务时使用。

microsoft

seo-schema

12Ktesting-qa

检测、验证并生成 Schema.org 结构化数据。优先使用 JSON-LD 格式。当用户提到“schema”、“结构化数据”、“富结果”、“JSON-LD”或“标记”时使用。

agricidaniel

playwright-cli

自动化浏览器交互、测试网页并处理 Playwright 测试。

microsoft

i-have-adhd

为患有ADHD的读者塑造输出：以下一步行动开头，对多步骤工作进行编号，在对话轮次间重述状态，抑制离题内容，给出具体时间估计，让成果可见。通过 /i-have-adhd 调用；持续生效直到说“stop adhd mode”。

ayghri

phoenix-evals

Build and run evaluators for AI/LLM applications using Phoenix.

arize-ai

huggingface-vision-trainer

Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.

huggingface

vue-expert-js

创建 Vue 3 组件、构建原生 JS 组合式函数、配置 Vite 项目，并使用纯 JavaScript（无 TypeScript）设置路由和状态管理。生成带有 @typedef、@param 和 @returns 注解的 JSDoc 类型代码，无需 TS 编译器即可实现完整类型覆盖。适用于仅使用 JavaScript（无 TypeScript）构建 Vue 3 应用、项目需要基于 JSDoc 的类型提示、从 Vue 2 Options API 迁移到 Composition API（JS 版）、团队偏好原生 JavaScript 和 .mjs 模块，或需要快速原型开发而无需 TypeScript 配置的场景。

jeffallan

swift-expert

构建 iOS/macOS/watchOS/tvOS 应用程序，实现 SwiftUI 视图和状态管理，设计面向协议的架构，处理 async/await 并发，实现 actor 保证线程安全，并调试 Swift 特定问题。在构建使用 Swift 5.9+、SwiftUI 或 async/await 并发的 iOS/macOS 应用程序时使用。适用于面向协议编程、SwiftUI 状态管理、actor、服务器端 Swift、UIKit 集成、Combine 或 Vapor。

jeffallan

legacy-modernizer

设计增量迁移策略，识别服务边界，生成依赖关系图和迁移路线图，并为老旧代码库生成API外观设计。适用于现代化遗留系统、实施绞杀者模式或分支抽象、分解单体应用、升级框架或语言、在不中断业务运营的情况下减少技术债务。

jeffallan