测试
单元测试、集成测试与测试自动化
sd-tdd
platypeeps
Write the test before the code and watch it fail, so that a passing test is evidence rather than agreement.
sd-tutorial
platypeeps
Use when the user wants a checkpoint-driven technical tutorial that moves a defined audience from a known starting state to an observable result with honest execution status, verification, recovery, and cleanup.
sd-evaluate
platypeeps
Use when the user wants one defined subject assessed against an explicit rubric with criterion-level evidence, uncertainty, sensitivity, deficiencies, and prioritized improvements.
test-validate
tomevault-io
运行项目测试（涵盖 Python 后端、Vue 前端及多语言校验） Use when this capability is needed.
dragon-wars-cht-remake
wicanr2
推進《火龍之戰》(Dragon Wars, Interplay 1989)的繁體中文化 + C++20/SDL2 現代重寫(opendw_remake)。涵蓋:用 opendw(Devin Smith 的 C 反組譯)當正確性 oracle 做 byte-for-byte / 逐指令差異測試;從 DATA1/DATA2 萃取資產(5-bit 文字、Huffman 解壓、res31 怪物名、sprite、全螢幕場景圖 title_adjust 去交錯);Read Paragraph 防拷段落內嵌顯示;CJK 24×24 渲染進 320×200 framebuffer;手冊/軟體世界攻略以視覺轉寫 OCR;docker 工具鏈。觸發條件:使用者提到「火龍之戰」「Dragon Wars」「opendw」「opendw_remake」「火龍之戰中文化」,或要求接續萃取/翻譯/重寫/驗證該遊戲。repo:github.com/wicanr2/opendw_dragon_wars_cht。
money-change
Munyon-Canyon
Checklist for any backend change that moves or records money, including ledgers, shares, swaps, transfers and balances. Use before writing or reviewing code that touches USDC, token amounts, share math, the relayer or Privy signing.
lunarunes-semantic-group-classifier
EsotericVerse
Use the current LunaRunes governance/Canon documents as the governing specification for LunaRunes classification. If a referenced historical document conflicts with current Canon or an explicit later governance decision, current governance takes precedence.
ios-verify
Munyon-Canyon
Verify the Monaco iOS app. Use when asked to verify the app, run MonacoTests, or check the iOS build.
testing-expert
Munyon-Canyon
Expert-level TypeScript testing skill focused on writing high-quality tests that find bugs, ensure intended functionality, serve as documentation, and prevent regressions. Use when writing service code, unit tests, integration tests, and E2E tests.
verify-backend
Munyon-Canyon
Explains what monacoctl verify checks, how to read a failed ci / e2e job and its verify-evidence artifact, and what counts as a pass. Use when the E2E job fails in stage 1, when a flow moves to verified, or when reproducing an end-to-end failure.
react-testing
gagandeepgill
React component testing with React Testing Library, Vitest/Jest, MSW for network mocking, accessibility assertions with axe, and the decision boundary between component tests and Playwright/Cypress end-to-end runs. Use when writing or fixing tests for React components, hooks, or pages.
waves-test-audit
wavespestcontrolfl
Audit Waves portal tests for redundant or brittle coverage. Use when assessing test value, consolidating tests, or planning test pruning.
ios-simslim-fast-qa
Munyon-Canyon
Fast-pass iOS simulator QA loop with SimSlim (RAM-thin simulators) and MobAI (tap/observe automation). Covers repo discovery, slim profiles, build/install, claim/bridge/drive/release. Use when the user wants fast iOS QA, sim smoke tests, agent-driven tap-through, SimSlim, MobAI, or slim-simulator QA — not full device farms or multi-sim regression at scale.
tdd
CartmanFatass
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
ml-failfast-validation
terrylica
POC validation patterns to catch issues before committing to long-running ML experiments. TRIGGERS - fail-fast, POC validation, preflight check
create-evlog-enricher
HugoRCD
Create a new built-in evlog enricher to add derived context to wide events. Use when adding a new enricher (e.g., for deployment metadata, tenant context, feature flags, etc.) to the evlog package. Covers source code, tests, and all documentation.
moai-workflow-testing
modu-ai
Comprehensive testing and development workflow specialist combining DDD testing, characterization tests, performance profiling, code review, and quality assurance. Use when writing tests, measuring coverage, creating characterization tests, performing TDD, running CI/CD quality checks, or reviewing pull requests. Do NOT use for debugging runtime errors (use expert-debug agent instead) or code refactoring (use moai-workflow-ddd instead).
mvcc
tursodatabase
Overview of Experimental MVCC feature - snapshot isolation, versioning, limitations
moai-lang-javascript
modu-ai
JavaScript ES2024+ development specialist covering Node.js 22 LTS, Bun 1.x (serve, SQLite, S3, shell, test), Deno 2.x, testing (Vitest, Jest), linting (ESLint 9, Biome), and backend frameworks (Express, Fastify, Hono). Use when developing JavaScript APIs, web applications, or Node.js projects.
moai-lang-rust
modu-ai
Rust 1.92+ development specialist covering Axum, Tokio, SQLx, and memory-safe systems programming. Use when building high-performance, memory-safe applications or WebAssembly.
planned-content
tin-computer
Assess current coverage, then draft only useful, fact-grounded planned content.
moai-lang-flutter
modu-ai
Flutter 3.24+ / Dart 3.5+ development specialist covering Riverpod, go_router, and cross-platform patterns. Use when building cross-platform mobile apps, desktop apps, or web applications with Flutter.
moai-foundation-quality
modu-ai
Code quality orchestrator enforcing TRUST 5 validation, proactive code analysis, linting standards, and automated best practices. Use when performing code review, quality gate checks, lint configuration, TRUST 5 compliance validation, or establishing coding standards. Do NOT use for writing tests (use moai-workflow-testing instead) or debugging runtime errors (use expert-debug agent instead).
unocss
antfu
UnoCSS instant atomic CSS engine, superset of Tailwind CSS. Use when configuring UnoCSS, writing utility rules, shortcuts, or working with presets like Wind, Icons, Attributify.