测试与 QA

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

git-worktrees

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.

plan-do-check-act

Iterative PDCA cycle for systematic experimentation and continuous improvement

analyse

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

fix-tests

Systematically fix all failing tests after business logic changes or refactoring

write-tests

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.

add-task

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

validate-evaluator

Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before trusting its outputs. Do NOT use for code-based evaluators (those are deterministic; test with standard unit tests).

hamelsmu

subagent-driven-development

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

root-cause-tracing

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

memorize

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

test-driven-development

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

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

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

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

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

web-cache-deception

1.5Ktesting-qa

Web 缓存欺骗与缓存污染实战手册。适用于因路径混淆或缓存键（Cache Key）篡改，导致 CDN、反向代理或应用层缓存可能将已认证用户的敏感内容分发给其他用户的场景。

yaklang

windows-remote-desktop-connection-doctor

Diagnoses Windows App (Remote Desktop / AVD / W365 / direct PC) connection problems on macOS: transport selection (UDP Shortpath vs WebSocket), VPN/proxy interference, and stuck "Configuring remote PC..." dialogs. Use when a VDI connection is slow/stuck, transport shows WebSocket not UDP, or Windows App freezes at a progress dialog. Not for general network diagnosis (use debugging-network-issues or tunnel-doctor).

daymade

validate-evaluator

ai-evals-course

m13-domain-error

Use when designing domain error handling. Keywords: domain error, error categorization, recovery strategy, retry, fallback, domain error hierarchy, user-facing vs internal errors, error code design, circuit breaker, graceful degradation, resilience, error context, backoff, retry with backoff, error recovery, transient vs permanent error, 领域错误, 错误分类, 恢复策略, 重试, 熔断器, 优雅降级

rust-trait-explorer

Explore Rust trait implementations using LSP. Triggers on: /trait-impl, find implementations, who implements, trait 实现, 谁实现了, 实现了哪些trait

meta-cognition-parallel

EXPERIMENTAL: Three-layer parallel meta-cognition analysis. Triggers on: /meta-parallel, 三层分析, parallel analysis, 并行元认知

domain-fintech

Use when building fintech apps. Keywords: fintech, trading, decimal, currency, financial, money, transaction, ledger, payment, exchange rate, precision, rounding, accounting, 金融, 交易系统, 货币, 支付

rust-refactor-helper

Safe Rust refactoring with LSP analysis. Triggers on: /refactor, rename symbol, move function, extract, 重构, 重命名, 提取函数, 安全重构