AI Skills

测试与 QA

测试、调试、验证和质量工作流

844 个 Skills 可用

Skills 列表

mom-test

mom-test

1.7Ktesting-qa

使用“妈妈测试”规则与客户交谈，避免引导他们：讨论他们的生活而非你的想法，询问过去的细节，少说多听。当用户提到“客户访谈”、“验证我的想法”、“用户说想要但不购买”、“引导性问题”、“妈妈测试”、“客户反馈偏差”或“访谈脚本”时使用。在准备用户研究问题、解读模糊反馈或设计避免假阳性的客户发现时也触发。涵盖承诺与推进、避免赞美以及从噪音中提取信号。关于产品-市场匹配，请参见“待办任务”。关于快速原型测试，请参见“设计冲刺”。

wondelai avatarwondelai
获取
ab-test-store-listing

ab-test-store-listing

1.7Ktesting-qa

当用户需要对 App Store 产品页元素进行 A/B 测试以提升下载转化率时使用。当用户提到“A/B 测试”、“产品页优化”、“测试截图”、“测试 Icon”、“转化率优化”、“CPP”或“自定义产品页”时同样适用。关于截图设计，请参阅 screenshot-optimization；关于元数据优化，请参阅 metadata-optimization。

eronred avatareronred
获取
git-notes

git-notes

1.7Ktesting-qa

Use when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc - provides git notes commands and patterns for attaching non-invasive metadata to Git objects.

neolabhq avatarneolabhq
获取
hooked-ux

hooked-ux

1.7Ktesting-qa

使用钩子模型（触发、行动、可变奖励、投入）设计养成习惯的产品循环。当用户提到“用户不回来”、“习惯养成”、“参与循环”、“习惯区”或“操纵矩阵”时使用。在设计通知或重新参与策略、构建连续打卡或进度系统、或分析用户注册后为何停止使用时也可触发。涵盖伦理评估和习惯引导。关于减少摩擦和B=MAP，请参见improve-retention。关于病毒式传播，请参见contagious。

wondelai avatarwondelai
获取
refactoring-patterns

refactoring-patterns

1.7Ktesting-qa

应用命名的重构转换来改善代码结构，同时不改变其行为。当用户提到“重构这个”、“代码坏味”、“提取方法”、“替换条件”、“技术债务”、“移动方法”、“内联变量”、“分解条件”或“清理这段混乱的代码”时使用。同样适用于清理遗留代码、通过重构为新增功能做准备，或识别适合特定代码坏味的转换。涵盖坏味驱动的重构、安全转换序列和测试保护。关于代码质量基础，请参见 clean-code。关于管理复杂性，请参见 software-design-philosophy。

wondelai avatarwondelai
获取
clean-code

clean-code

1.7Ktesting-qa

通过规范的命名、短小的函数和清晰的错误处理，编写可读、可维护的代码。当用户提到“清理这段代码”、“这个函数太长了”、“代码坏味道”、“命名规范”、“童子军规则”、“单一职责”或“单元测试质量”时使用。在审查拉取请求的可读性、梳理混乱的函数、讨论注释风格或改进错误处理模式时也会触发。涵盖SRP、注释纪律、格式化和单元测试。有关重构技术，请参见refactoring-patterns。有关架构和依赖规则，请参见clean-architecture。

wondelai avatarwondelai
获取
decay

decay

1.7Ktesting-qa

Manage evidence freshness by identifying stale decisions and providing governance actions

neolabhq avatarneolabhq
获取
cause-and-effect

cause-and-effect

1.7Ktesting-qa

Systematic Fishbone analysis exploring problem causes across six categories

neolabhq avatarneolabhq
获取
analyze-issue

analyze-issue

1.7Ktesting-qa

Analyze a GitHub issue and create a detailed technical specification

neolabhq avatarneolabhq
获取
create-hook

create-hook

1.7Ktesting-qa

Create and configure git hooks with intelligent project analysis, suggestions, and automated testing

neolabhq avatarneolabhq
获取
git-worktrees

git-worktrees

1.7Ktesting-qa

Use when working on multiple branches simultaneously, context switching without stashing, reviewing PRs while developing, testing in isolation, or comparing implementations across branches - provides git worktree commands and workflow patterns for parallel development with multiple working directories.

neolabhq avatarneolabhq
获取
plan-do-check-act

plan-do-check-act

1.7Ktesting-qa

Iterative PDCA cycle for systematic experimentation and continuous improvement

neolabhq avatarneolabhq
获取
analyse

analyse

1.7Ktesting-qa

Auto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target

neolabhq avatarneolabhq
获取
fix-tests

fix-tests

1.7Ktesting-qa

Systematically fix all failing tests after business logic changes or refactoring

neolabhq avatarneolabhq
获取
write-tests

write-tests

1.7Ktesting-qa

Add missing test coverage for your local code changes by generating new test files (covers uncommitted and untracked changes, or the latest commit if everything is committed). Use when you want write tests for new logic or increase test coverage.

neolabhq avatarneolabhq
获取
add-task

add-task

1.7Ktesting-qa

creates draft task file in .specs/tasks/draft/ with original user intent

neolabhq avatarneolabhq
获取
subagent-driven-development

subagent-driven-development

1.7Ktesting-qa

Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates

neolabhq avatarneolabhq
获取
root-cause-tracing

root-cause-tracing

1.7Ktesting-qa

Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior

neolabhq avatarneolabhq
获取
memorize

memorize

1.7Ktesting-qa

Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering

neolabhq avatarneolabhq
获取
test-driven-development

test-driven-development

1.7Ktesting-qa

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first

neolabhq avatarneolabhq
获取
assess-react-native-migration

assess-react-native-migration

1.6Ktesting-qa

评估现有移动端产品是否以及如何迁移到 React Native。适用于审计一个或多个产品代码库的迁移就绪度（包括 iOS、Android 及其他客户端分布在不同目录或独立仓库的情况）；选择 Brownfield（混合/渐进式）、Greenfield（全新重构）或基于 Checkpoint（关键验证点）的路线；定义具有代表性的试跑方案；以及在正式实施前制定基线与 ROI 决策。当缺少产品范围或关键事实依据时，不会一次性发问卷，而是每轮严格追问干系人一个关键问题。

callstackincubator avatarcallstackincubator
获取
swift-concurrency

swift-concurrency

1.6Ktesting-qa

诊断 Swift 并发问题，将基于回调的代码重构为 async/await，并在处理任务、Actor、@MainActor、Sendable、数据竞争、线程安全或与并发相关的编译器和 linter 警告时指导 Swift 6 迁移。

avdlee avataravdlee
获取
upgrading-react-native

upgrading-react-native

1.5Ktesting-qa

通过应用 rn-diff-purge 模板 diff、更新 package.json 依赖、迁移 iOS 及 Android 原生配置、处理 CocoaPods 和 Gradle 变更，以及应对 Breaking Change（破坏性 API 更新），将 React Native 应用平滑升级到更高版本。适用于升级 React Native、提升 RN 版本、从 RN 0.x 跨版本升级到 0.y，或在升级 React Native 时同步迁移 Expo SDK 等场景。

callstackincubator avatarcallstackincubator
获取
dependency-confusion

dependency-confusion

1.5Ktesting-qa

通过包管理器依赖混淆（Dependency Confusion）开展供应链安全测试：当内部私有包名被解析到攻击者控制的公共注册表时，会导致恶意代码被安装并执行脚本。适用于 npm/pip/gem/Maven/Composer/Docker 等配置清单（manifest）审查及获授权的红队供应链演练。

yaklang avataryaklang
获取