BryantChi

完整的網站開發指南，涵蓋 UI/UX 設計、React/Vue/Next.js 前端框架、Laravel/Node.js 後端、Coding Style 與互動式選擇精靈

Web 動畫（Framer Motion、GSAP、View Transitions API、Lottie）。CSS 動畫見 ui/no-ai-feel.md

REST API 與 GraphQL 設計規範指南

認證授權（Auth.js、Clerk、JWT/Cookie 安全、RBAC/ABAC）。不含 OAuth provider 細節

Laravel、Node.js、Django、FastAPI 後端框架指南

JavaScript、TypeScript、PHP、Python、CSS 代碼規範

元件組合模式（Compound Component、Slot Props、Headless UI）。取代 boolean prop 暴衝

Tailwind、Bootstrap、SCSS、Vanilla CSS 方案指南

Android 17 個技能的導航中樞 — 依場景路由到 2-3 個技能組合，含 Skill Dependency Graph、易混淆 skill 邊界對照表、2026-04 重構說明

Kotlin 程式碼規範 — 命名、Detekt 1.25+ / Ktlint 1.4+ 配置、Compose Stability/Compiler Metrics、SuppressLint 多模組策略、KDoc 與 Code Review Checklist，產出可在 CI 強制的風格基線

Android Crash/ANR/結構化日誌的「實作層」 — Firebase Crashlytics 33.x、Custom Signals/OnFatalException、Android 14 ANR Watchdog（含 foreground threshold）、Memory Warning、Timber、Play Console + Firebase 警報聯動，產出可定位的事件流

Android 資料層 — Room 2.7+ Migration / Paging 3 / FTS、Retrofit + OkHttp 統一錯誤處理、Offline-First SSOT、Sync Manager + WorkManager、Protobuf DataStore、Room vs SQLDelight 決策矩陣，產出可離線可同步的資料層

Android 效能定位與優化（數據驅動） — Macrobenchmark / Baseline Profiles / Startup Profiles、Perfetto trace、JankStats 量化門檻、Memory Profiler / Native Profiler / Flame Graph、R8 優化、Play Console App Quality Insights，產出可進 CI gate 的效能基線

Hilt 2.52+ 進階用法 — Assisted Injection、Custom Components/Scopes、Multi-binding、EntryPoint 跨模組安全、KSP2 取代 kapt、@UninstallModules 測試策略，產出可測試的多模組 DI 架構

KMP 跨平台架構（2026-04） — 共享邊界決策、Kotlin 2.1 + Ktor 3.x + SQLDelight 2.x、iOS Interop（SPM、Shared ViewModel）、Compose Multiplatform 策略、平台 Dispatcher 差異、Serialization 選型、Room→SQLDelight 遷移路徑

在無法全面重構的舊 Android 專案中，以 Islanding 策略快速建立新功能 — Bridge Pattern、Hybrid Theming（XML↔Material 3）、Wrapper Activities、Remote Config 控制 Feature Toggle、Hybrid 過渡期效能監控

Walk through stale or conflicting memory entries and routing-table drift. Use when the user runs /sustain:audit, asks "is my memory store healthy?", or before a major release of personal rules.

Search persistent memory across mempalace MCP, claude-mem MCP, and the structured filesystem fallback. Use when the user asks "how did we solve X before?", "what did we decide about Y?", or anything that implies recalling prior-conversation context.

Decide whether and where to persist a learning. Use at phase boundaries when something seems worth long-term memory — a rule, a non-obvious decision, an external resource, or a project-state change. Picks the right wing (feedback / project / reference / user) and routes through the user's active memory backend.

Interpret session token statistics and recommend the next move — /compact, delegate to a subagent, switch to a smaller model, or stop and persist learnings. Use after `/sustain:status`, when the session feels long, or when context-window pressure is showing up in degraded responses.

Run the 6-question phase-end checklist when a logical phase completes (after a feature, before a context switch, or when the Stop hook prompts you). Use to surface skipped Iron Rules, missed memory writes, and overdue /compact opportunities.

Establish Iron Rules (3+1) and R1–R5 token-saving rules at session start or whenever the rules feel forgotten. Use when user asks about token efficiency, when rules need re-grounding, or proactively at the start of complex multi-turn work.