vibes-plug 2.11.0 → 2.14.1

package/skills/webxr-ar-vr-expert/SKILL.md

@@ -1,123 +1,162 @@
----
-name: webxr-ar-vr-expert
-description: "Expert guide for WebXR (Web-based Virtual and Augmented Reality) development using Babylon.js and Three.js. Covers device compatibility, immersive sessions, controllers, and hit-testing."
-author: "Roedy Rustam"
----
-
-# WebXR AR/VR Expert
-
-[English](#english) | [Bahasa Indonesia](#bahasa-indonesia)
-
----
-
-<a name="english"></a>
-## English
-
-### Orchestration & Integration
-Connects and orchestrates with relevant domain skills like `brainstorming`, `zero-to-prod-orchestrator`, and `project-context-mapper` to ensure cohesive execution.
-
-### Description
-Production-grade guidance for building immersive **Augmented Reality (AR)** and **Virtual Reality (VR)** experiences in the browser using the **WebXR Device API**. Focuses on implementation via **Babylon.js** (which has industry-leading WebXR support) and **Three.js** / React Three Fiber.
-
-### Trigger Conditions
-Activate this skill when the user is:
-- Building AR/VR experiences for Oculus/Meta Quest, Apple Vision Pro, or mobile AR devices.
-- Setting up an `immersive-vr` or `immersive-ar` WebXR session.
-- Implementing controller tracking, hand tracking, or teleportation in 3D space.
-- Using AR Hit-Testing to place digital objects on physical surfaces (floors/tables).
-
-### Core Concepts
-
-#### 1. Babylon.js WebXR Setup
-Babylon.js provides the most robust default WebXR experience.
-```typescript
-import { Scene, FreeCamera, Vector3, Engine } from '@babylonjs/core';
-
-async function setupXR(scene: Scene) {
-  // Initialize default WebXR experience
-  // This automatically adds the "Enter VR/AR" button, teleportation, and controller models
-  const xr = await scene.createDefaultXRExperienceAsync({
-    uiOptions: {
-      sessionMode: 'immersive-vr', // or 'immersive-ar'
-    },
-    optionalFeatures: true
-  });
-  
-  // Example: Listen for controller input
-  xr.input.onControllerAddedObservable.add((controller) => {
-    controller.onMotionControllerInitObservable.add((motionController) => {
-      // Handle button presses
-    });
-  });
-}
-```
-
-#### 2. Three.js / React Three Fiber Setup
-In R3F, use `@react-three/xr`.
-```tsx
-import { Canvas } from '@react-three/fiber';
-import { XR, createXRStore } from '@react-three/xr';
-
-const store = createXRStore();
-
-export default function App() {
-  return (
-    <>
-      <button onClick={() => store.enterVR()}>Enter VR</button>
-      <Canvas>
-        <XR store={store}>
-          <mesh>
-            <boxGeometry />
-            <meshBasicMaterial color="red" />
-          </mesh>
-        </XR>
-      </Canvas>
-    </>
-  );
-}
-```
-
-#### 3. AR Hit-Testing
-In AR mode, "Hit-Testing" allows you to detect real-world surfaces.
-- Ensure `immersive-ar` is used.
-- Request the `hit-test` feature when initializing the session.
-- Use the hit-test results (a matrix/position) to place a reticle or object.
-
-### Best Practices
-- **Performance is Critical:** VR requires a consistent 72 to 90 FPS (or 120 FPS on Apple Vision Pro). Dropped frames cause motion sickness.
-- **Polycount:** Keep polygon counts and draw calls low.
-- **UI in XR:** Standard HTML UI will not work in immersive mode. You must use 3D UI (e.g., Babylon's GUI 3D system or Three.js spatial HTML layers if supported).
-
----
-
-### Integration with Other Skills (MANDATORY)
-This skill works best when combined with:
-- `web-3d-graphics-expert` — For building the 3D scene that XR will visualize.
-- `apple-ecosystem-expert` — For optimizing WebXR compatibility with iOS (Safari) and visionOS.
-- `web-game-engine-expert` — For adding physics to VR interactions (e.g., throwing objects).
-
-### Referenced By Orchestrators (MANDATORY)
-- `brainstorming` — Add to "3D & Graphics" or "Spatial Computing".
-- `zero-to-prod-orchestrator` — Phase 5 (Frontend / XR Implementation).
-
----
-
-<a name="bahasa-indonesia"></a>
-## Bahasa Indonesia
-
-### Integrasi Orkestrasi
-Terhubung dan mengorkestrasi skill domain yang relevan seperti `brainstorming`, `zero-to-prod-orchestrator`, dan `project-context-mapper` untuk memastikan eksekusi yang kohesif.
-
-### Deskripsi
-Panduan ahli untuk pengembangan *Virtual Reality* (VR) dan *Augmented Reality* (AR) di web menggunakan **WebXR API**. Difokuskan pada implementasi menggunakan **Babylon.js** dan **Three.js** untuk ekosistem *Spatial Computing*.
-
-### Kondisi Pemicu
-- Mengembangkan aplikasi VR/AR untuk Meta Quest, Apple Vision Pro, atau Mobile AR.
-- Mengimplementasikan pelacakan pengontrol (controller), pelacakan tangan (hand tracking), atau teleportasi.
-- Menggunakan AR Hit-Testing untuk meletakkan objek 3D di permukaan dunia nyata.
-
-### Panduan Singkat
-- **Performa Mutlak:** Jaga FPS tetap stabil di angka 72-90 FPS. *Frame drop* pada VR menyebabkan rasa mual (motion sickness) pada pengguna. Batasi jumlah poligon dan *draw calls*.
-- **Babylon.js sebagai Prioritas:** Untuk proyek XR berskala besar, prioritaskan Babylon.js karena dukungan bawaannya untuk interaksi VR, fisika, dan UI 3D jauh lebih matang dibanding library lain.
-- **UI Spasial:** Ingat bahwa elemen HTML biasa tidak muncul di dalam sesi `immersive-vr` atau `immersive-ar`. Anda harus membuat UI berupa objek 3D (seperti panel yang melayang di udara).
-- **Hit-Testing:** Untuk AR, gunakan fitur *Hit-Test* yang disediakan WebXR API untuk mengenali lantai atau meja sebagai tempat menaruh objek.
+---
+name: webxr-ar-vr-expert
+description: "Expert guide for WebXR spatial computing, Web-based Virtual Reality (VR), Mixed Reality (MR), and Augmented Reality (AR) using Babylon.js and Three.js. Covers Apple Vision Pro, Meta Quest 3, hand tracking, and hit-testing / Panduan ahli WebXR spatial computing (VR/AR/MR)."
+author: "vibes-plug-swarm"
+---
+
+# WebXR Spatial Computing Expert (VR, AR & MR)
+
+[English](#english) | [Bahasa Indonesia](#bahasa-indonesia)
+
+---
+
+<a name="english"></a>
+## English
+
+### Orchestration & Integration
+Connects and orchestrates with relevant domain skills:
+- `web-3d-graphics-expert` — WebGPU/WebGL 3D scene rendering, lighting, and model optimization.
+- `web-game-engine-expert` — Spatial physics, grabbing interactions, and fixed-timestep motion.
+- `apple-ecosystem-expert` — Apple Vision Pro visionOS Safari WebXR features and spatial guidelines.
+- `glsl-shader-expert` — Passthrough blending and spatial holographic shaders.
+- `performance-web-vitals` — Maintaining rock-solid 72/90/120 FPS to prevent simulator sickness.
+
+### Description
+Production-grade guidance for architecting immersive **Virtual Reality (VR)**, **Mixed Reality (MR)**, and **Augmented Reality (AR)** in the browser via the **WebXR Device API**. Covers modern head-mounted displays (**Meta Quest 3/3S**, **Apple Vision Pro**) and mobile AR, focusing on Babylon.js and Three.js with `@react-three/xr`.
+
+### Trigger Conditions
+Activate this skill when the user is:
+- Developing spatial computing web applications or immersive web experiences.
+- Setting up WebXR sessions (`immersive-vr`, `immersive-ar`).
+- Implementing Hand Tracking (joint poses, pinch gestures) or spatial controller interactions.
+- Adding Mixed Reality passthrough or depth sensing.
+- Implementing AR Hit-Testing to snap 3D models onto real-world planes (floors, walls, tabletops).
+- Optimizing XR framerates (fixed foveated rendering) to eliminate motion sickness.
+
+---
+
+### Key Capabilities & Headset Targets (2026)
+
+| Target Platform | Session Mode | Key Features |
+| :--- | :--- | :--- |
+| **Meta Quest 3 / 3S** | `immersive-vr`, `immersive-ar` | Full-color stereo passthrough, high-precision hand tracking, fixed foveation levels 0-3. |
+| **Apple Vision Pro (visionOS)** | `immersive-vr`, `immersive-ar` | Eye-gaze + pinch interaction, 90/120Hz display refresh, strict privacy hand tracking. |
+| **Mobile AR (Android / iOS WebKit)** | `immersive-ar` | Surface hit-testing, ambient light estimation, instant plane detection. |
+
+---
+
+### 1. Babylon.js WebXR Setup (Gold Standard)
+
+Babylon.js provides the most comprehensive out-of-the-box WebXR implementation with integrated teleportation, controller profiles, and physics:
+
+```typescript
+import { Scene, WebXRExperienceHelper, WebXRFeatureName } from '@babylonjs/core';
+
+export async function initBabylonXR(scene: Scene) {
+  const xr = await scene.createDefaultXRExperienceAsync({
+    uiOptions: {
+      sessionMode: 'immersive-ar', // Fallback to 'immersive-vr' if AR is unsupported
+      referenceSpaceType: 'local-floor'
+    },
+    optionalFeatures: ['hit-test', 'hand-tracking', 'anchors', 'plane-detection']
+  });
+
+  // Enable Fixed Foveated Rendering to reclaim 20-30% GPU performance on Quest
+  const foveation = xr.baseExperience.featuresManager.enableFeature(
+    WebXRFeatureName.FOVEATION,
+    'latest',
+    { foveationLevel: 2 }
+  );
+
+  // Listen for Hand Tracking
+  const handTracking = xr.baseExperience.featuresManager.enableFeature(
+    WebXRFeatureName.HAND_TRACKING,
+    'latest',
+    { xrInput: xr.input }
+  );
+
+  return xr;
+}
+```
+
+---
+
+### 2. React Three Fiber Setup (`@react-three/xr`)
+
+```tsx
+import { Canvas } from '@react-three/fiber';
+import { XR, createXRStore, Hands, Controllers } from '@react-three/xr';
+
+const store = createXRStore({
+  foveation: 1,
+  handTracking: true
+});
+
+export function SpatialApp() {
+  return (
+    <>
+      <button className="xr-btn" onClick={() => store.enterAR()}>
+        Enter Mixed Reality
+      </button>
+      <Canvas>
+        <XR store={store}>
+          <ambientLight intensity={0.8} />
+          <directionalLight position={[5, 10, 5]} />
+          <Controllers />
+          <Hands />
+          {/* Spatial 3D Objects */}
+          <mesh position={[0, 1.2, -1]}>
+            <boxGeometry args={[0.3, 0.3, 0.3]} />
+            <meshStandardMaterial color="royalblue" />
+          </mesh>
+        </XR>
+      </Canvas>
+    </>
+  );
+}
+```
+
+---
+
+### Best Practices for Spatial Performance
+1. **Rock-Solid Framerates:** VR requires stable 72, 90, or 120 FPS. Any frame drop causes instant vestibular nausea.
+2. **Fixed Foveated Rendering (FFR):** Reduces fragment shader resolution in the user's peripheral vision, freeing substantial GPU overhead.
+3. **No 2D DOM Overlays in VR:** Standard HTML elements cannot render inside an immersive session. Render spatial 3D UI panels using world-space 3D meshes or canvas textures.
+
+---
+
+<a name="bahasa-indonesia"></a>
+## Bahasa Indonesia
+
+### Integrasi Orkestrasi
+Terhubung dan mengorkestrasi skill domain yang relevan:
+- `web-3d-graphics-expert` — Rendering scene 3D WebGPU/WebGL, pencahayaan, dan optimasi model.
+- `web-game-engine-expert` — Fisika spasial, interaksi menggenggam objek, dan pergerakan fixed-timestep.
+- `apple-ecosystem-expert` — Fitur WebXR Safari di Apple Vision Pro visionOS dan pedoman spasial.
+- `glsl-shader-expert` — Shader hologram dan blending passthrough AR.
+- `performance-web-vitals` — Menjaga kestabilan 72/90/120 FPS demi mencegah *motion sickness*.
+
+### Deskripsi
+Panduan produksi untuk membangun aplikasi spasial imersif **Virtual Reality (VR)**, **Mixed Reality (MR)**, dan **Augmented Reality (AR)** di browser melalui **WebXR Device API**. Mencakup headset modern (**Meta Quest 3/3S**, **Apple Vision Pro**) serta perangkat mobile AR.
+
+### Kondisi Pemicu
+Aktifkan skill ini ketika pengguna:
+- Mengembangkan aplikasi web *Spatial Computing* (VR/AR/MR).
+- Menginisialisasi sesi WebXR (`immersive-vr`, `immersive-ar`).
+- Mengimplementasikan *Hand Tracking* (pelacakan sendi tangan, gerakan cubit/pinch) atau kontroler spasial.
+- Mengaktifkan *Passthrough* warna Mixed Reality.
+- Menggunakan AR *Hit-Testing* untuk menempatkan objek 3D di lantai atau meja fisik.
+- Mengoptimalkan performa VR dengan *Fixed Foveated Rendering* (FFR).
+
+---
+
+### Panduan Inti Pengembangan Spasial
+
+1. **Stabilitas Frame Rate Mutlak**:
+   - Targetkan 72–90 FPS tanpa toleransi *stutter*. Pada kacamata VR, keterlambatan frame (*latency hitch*) langsung memicu rasa mual (*motion sickness*).
+2. **Fixed Foveated Rendering (FFR)**:
+   - Aktifkan fitur foveation pada Meta Quest untuk menurunkan resolusi tepi lensa (periferi mata), menghemat 20-30% daya GPU.
+3. **Antarmuka 3D Spasial (Bukan HTML DOM)**:
+   - Elemen HTML standar tidak dapat ditampilkan di dalam sesi imersif. Buat UI berupa panel 3D melayang (*world-space meshes*).
+4. **Hit-Testing untuk AR**:
+   - Manfaatkan *Hit-Test API* bawaan WebXR untuk mendeteksi bidang nyata permukaan meja atau lantai secara instan sebelum meletakkan objek 3D.

package/skills/zero-to-prod-orchestrator/SKILL.md

@@ -14,7 +14,7 @@ author: "Roedy Rustam"
 ## English
 
 ### Orchestration & Integration
-Connects and orchestrates with relevant domain skills like `brainstorming`, `zero-to-prod-orchestrator`, and `project-context-mapper` to ensure cohesive execution.
+Connects and orchestrates with relevant domain skills like `brainstorming`, `zero-to-prod-orchestrator`, and `session-memory-manager` to ensure cohesive execution.
 
 ### Overview
 The **Zero to Production Orchestrator** is the ultimate master skill designed to orchestrate the entire `vibes-plug` ecosystem as a highly interconnected **engineering swarm**. By acting as the central conductor, it ensures that no sub-skill is executed in isolation. It guides fullstack developers through the complete software engineering lifecycle — from concept discovery to AI integration, multi-platform backend architecture, design systems, automated testing, GEO/AEO optimization, and production deployment.
@@ -26,10 +26,10 @@ The **Zero to Production Orchestrator** is the ultimate master skill designed to
 
 ### Core Principles & Hard Gates
 1. **Never Skip Phases**: Each phase must be completed and validated before advancing to the next.
-2. **Continuous Auto-Documentation**: Invoke `auto-doc-updater` to log changes in `CHANGELOG.md` and `BLUEPRINT.md` after every major milestone.
+2. **Continuous Auto-Documentation**: Invoke `prd-architect` to log changes in `CHANGELOG.md` and `BLUEPRINT.md` after every major milestone.
 3. **Strict Progress Tracking**: Maintain a `PROGRESS.md` checklist in the repository root.
-4. **State Preservation & Context**: Utilize `session-handoff-resume` when pausing work, and `session-context-loader` on every new session to preserve full context.
-5. **Efficiency**: Keep `token-saver` active during large refactors to maintain a lean, powerful execution loop.
+4. **State Preservation & Context**: Utilize `session-memory-manager` when pausing work or starting a new session to preserve full context.
+5. **Efficiency**: Keep `anti-slop` active during large refactors to maintain a lean, powerful, and zero-placeholder execution loop.
 
 ---
 
@@ -45,7 +45,7 @@ Launch/Deploy <--- Security/GEO <--- Testing/QA  <--- Frontend/UI
 ```
 
 #### PHASE 1: Discovery & AI PRD Architectural Planning
-**Orchestrates:** `prd-architect`, `brainstorming`, `mcp-server-architect`, `session-context-loader`, `dependency-upgrade-migrator`, `app-analyzer-optimizer`, `seo`, `project-context-mapper`, `self-evolving-memory-graph`, `saas-mvp-launcher`, `web-scraper`, `website-design-cloner`, `headless-cms-expert`, `wordpress-headless-expert`, `documentation-site-expert`, `asisten-ramah`, `skill-baru`
+**Orchestrates:** `prd-architect`, `brainstorming`, `deep-research-analyst`, `mcp-server-architect`, `session-memory-manager`, `dependency-upgrade-migrator`, `app-analyzer-optimizer`, `seo`, `saas-architect`, `web-scraper`, `website-design-cloner`, `headless-cms-expert`, `wordpress-headless-expert`, `documentation-site-expert`, `anti-slop`
 - [ ] Conduct structured dialogue to clarify product intent, target audience, and non-functional goals.
 - [ ] Automatically draft a comprehensive Product Requirements Document (PRD.md), Entity Relationship Diagram (ERD.md), and Documentation (DOKUMENTASI.md) alongside the Roadmap (ROADMAP.md).
 - [ ] Plan AI/LLM integration strategy (Vercel AI SDK, MCP Server tools, or Multi-Agent Graph).
@@ -60,14 +60,14 @@ Launch/Deploy <--- Security/GEO <--- Testing/QA  <--- Frontend/UI
 - [ ] Setup initial CI/CD pipeline template (GitHub Actions, Docker).
 
 #### PHASE 3: Database & Multi-Tenant Core Architecture
-**Orchestrates:** `fullstack-expert`, `database-migration-versioning-expert`, `database-orm-expert`, `domain-driven-design-expert`, `saas-multi-tenant`, `supabase-migration`, `supabase-security-expert`, `edge-serverless-db-expert`, `data-pipeline-etl-expert`, `search-engine-expert`, `geospatial-maps-expert`, `graph-rag-knowledge-expert`
+**Orchestrates:** `fullstack-expert`, `database-orm-expert`, `domain-driven-design-expert`, `saas-multi-tenant`, `supabase-security-expert`, `data-pipeline-etl-expert`, `search-engine-expert`, `geospatial-maps-expert`, `graph-rag-knowledge-expert`
 - [ ] Design normalized relational schemas, document models, and geospatial PostGIS structures.
 - [ ] Configure ORM layer (Drizzle ORM / Prisma 6 / SQLx / sqlc) and full-text search indexing (Typesense/Meilisearch).
 - [ ] Implement Row-Level Security (RLS) policies and tenant isolation.
 - [ ] Apply initial database migrations and connection poolers (PgBouncer/Supavisor/Neon).
 
 #### PHASE 4: Backend APIs, Microservices & AI Agents
-**Orchestrates:** `js-backend-expert`, `go-programming-expert`, `graphql-apollo-expert`, `openapi-swagger-codegen-expert`, `ai-llm-integration-expert`, `ai-prompt-engineering-expert`, `ai-media-generation-expert`, `multi-agent-orchestration`, `mcp-server-architect`, `authentication-identity-expert`, `email-notification-expert`, `cron-scheduler-expert`, `rate-limit-abuse-prevention`, `file-upload-media-expert`, `async-queue-temporal-expert`, `background-jobs-queue-expert`, `doku-mcp-server`, `event-driven-architect`, `gemini-agent-booster`, `mobile-push-notification-expert`, `realtime-collaboration-expert`, `api-gateway-proxy-expert`, `wasm-edge-computing-expert`, `sse-websocket-streaming-expert`, `n8n-automation-expert`, `chatbot-messaging-expert`, `pdf-document-generation-expert`, `ecommerce-expert`, `blockchain-web3-expert`, `local-slm-edge-ai-expert`, `voice-ai-realtime-agent`, `graph-rag-knowledge-expert`
+**Orchestrates:** `js-backend-expert`, `go-programming-expert`, `pydantic-ai-expert`, `vercel-ai-sdk-expert`, `synthetic-data-finetuning-expert`, `graphql-apollo-expert`, `openapi-swagger-codegen-expert`, `ai-llm-integration-expert`, `ai-prompt-engineering-expert`, `ai-media-generation-expert`, `multi-agent-orchestration`, `mcp-server-architect`, `authentication-identity-expert`, `email-notification-expert`, `cron-scheduler-expert`, `rate-limit-abuse-prevention`, `file-upload-media-expert`, `saas-billing`, `payment-gateway-expert`, `vector-db-rag-expert`, `async-queue-temporal-expert`, `doku-mcp-server`, `event-driven-architect`, `gemini-agent-booster`, `realtime-collaboration-expert`, `api-gateway-proxy-expert`, `wasm-edge-computing-expert`, `sse-websocket-streaming-expert`, `n8n-automation-expert`, `chatbot-messaging-expert`, `pdf-document-generation-expert`, `ecommerce-expert`, `blockchain-web3-expert`, `local-slm-edge-ai-expert`, `voice-ai-realtime-agent`, `graph-rag-knowledge-expert`
 - [ ] Build high-throughput REST / GraphQL / gRPC APIs using Fastify 5, NestJS, Hono, Gin, or Axum.
 - [ ] Implement authentication (Clerk, Auth.js, Supabase Auth) and RBAC middleware.
 - [ ] Build MCP Server tools or stateful LangGraph multi-agent workflows with human-in-the-loop gates.
@@ -77,7 +77,7 @@ Launch/Deploy <--- Security/GEO <--- Testing/QA  <--- Frontend/UI
 - [ ] Implement file upload with presigned URLs (S3/R2) and media processing.
 
 #### PHASE 5: Frontend, Design Systems & Mobile Apps
-**Orchestrates:** `modern-web-guidance`, `design-system-architect`, `senior-frontend`, `nextjs-app-router-expert`, `vue-frontend-expert`, `astro-framework-expert`, `svelte-sveltekit-expert`, `solidjs-expert`, `angular-expert`, `tailwind-expert`, `tanstack-query-expert`, `spa-orchestrator`, `mobile-expo-expert`, `apple-ecosystem-expert`, `tauri-expert`, `desktop-electron-expert`, `form-validation-expert`, `ui-components-expert`, `svg-animation-motion-expert`, `web-3d-graphics-expert`, `web-game-engine-expert`, `glsl-shader-expert`, `webxr-ar-vr-expert`, `visual-qa-vision-agent`, `hig`, `global-a11y-i18n-expert`, `bootstrap-to-modern`, `monday-design-aesthetic`, `state-management-expert`, `ui-ux-pro-max`, `data-visualization-expert`, `rich-text-editor-expert`, `documentation-site-expert`, `blockchain-web3-expert`, `modern-css-native-expert`, `pwa-offline-first-expert`
+**Orchestrates:** `modern-web-guidance`, `design-system-architect`, `senior-frontend`, `vercel-ai-sdk-expert`, `nextjs-app-router-expert`, `vue-frontend-expert`, `astro-framework-expert`, `svelte-sveltekit-expert`, `solidjs-expert`, `angular-expert`, `tailwind-expert`, `tanstack-query-expert`, `spa-orchestrator`, `mobile-expo-expert`, `apple-ecosystem-expert`, `tauri-expert`, `desktop-electron-expert`, `form-validation-expert`, `svg-animation-motion-expert`, `web-3d-graphics-expert`, `web-game-engine-expert`, `glsl-shader-expert`, `webxr-ar-vr-expert`, `visual-qa-vision-agent`, `hig`, `global-a11y-i18n-expert`, `bootstrap-to-modern`, `state-management-expert`, `ui-ux-pro-max`, `data-visualization-expert`, `rich-text-editor-expert`, `documentation-site-expert`, `blockchain-web3-expert`, `modern-css-native-expert`, `pwa-offline-first-expert`
 - [ ] **MANDATORY**: Run `modern-web-guidance` FIRST before implementing any frontend HTML/CSS/JS features to ensure compliance with modern Google standards.
 - [ ] Implement design tokens (OKLCH) and Tailwind CSS v4 `@theme` directive tokens.
 - [ ] Construct accessible component primitives using Radix UI / Base UI and CVA variants.
@@ -85,28 +85,29 @@ Launch/Deploy <--- Security/GEO <--- Testing/QA  <--- Frontend/UI
 - [ ] Build React 19 / Next.js 15, Vue 3, Astro 5, Svelte 5, SolidJS 2, or Angular 19+ apps with state management and Web3 wallets.
 - [ ] **MANDATORY**: Automatically scaffold standard pages: About, Profile, Contact, Terms of Reference/Service, and Privacy Policy.
 - [ ] Implement complex forms with React Hook Form + Zod validation.
+- [ ] If 3D Web or Web Games: architect with WebGPU (`WebGPURenderer`, PlayCanvas, or Babylon.js), KTX2 Basis Universal texture compression, Meshopt geometry, fixed-timestep physics loops, zero-GC object pooling, and 3D spatial audio.
 - [ ] If SPA architecture — coordinate with `spa-orchestrator` for routing (TanStack Router), state (TanStack Query v5), and decoupled API layer.
 - [ ] Integrate frontend state management with TanStack Query v5.
 
 #### PHASE 6: Automated Testing, Error Resilience & Security Audit
-**Orchestrates:** `e2e-testing-expert`, `accessibility-testing-expert`, `secure-fuzz-testing`, `firebase-security-expert`, `error-resilience-expert`, `logging-error-tracking-expert`, `vibe-code-gardener`, `coderabbit`, `autonomous-tdd-debugger`, `browser-automation-expert`, `zero-trust-secret-vault`, `autonomous-red-teamer`, `post-quantum-crypto-migrator`, `compliance-gdpr-privacy-expert`, `ai-evals-benchmark-expert`
+**Orchestrates:** `e2e-testing-expert`, `accessibility-testing-expert`, `secure-fuzz-testing`, `firebase-security-expert`, `error-resilience-expert`, `logging-error-tracking-expert`, `anti-slop`, `coderabbit`, `autonomous-tdd-debugger`, `browser-automation-expert`, `zero-trust-secret-vault`, `autonomous-red-teamer`, `post-quantum-crypto-migrator`, `compliance-gdpr-privacy-expert`
 - [ ] Write unit and integration tests with Vitest and pytest.
 - [ ] Write resilient E2E browser tests with Playwright and automated WCAG 2.2 accessibility tests with `@axe-core/playwright` and Pa11y.
 - [ ] Execute security fuzz testing (Atheris / cargo-fuzz / native Go fuzzing).
 - [ ] Implement Error Boundaries, retry patterns, circuit breakers, and graceful degradation.
 - [ ] Set up structured logging (Pino) and error tracking (Sentry) with source map uploads.
 - [ ] Audit CORS, CSP headers, rate-limiting, and input sanitization.
-- [ ] Run code quality audit to purge AI slop and architectural decay.
+- [ ] Run code quality audit to purge AI slop and architectural decay with anti-slop.
 
 #### PHASE 7: DevOps, Deployment & Proactive Monitoring
-**Orchestrates:** `ci-cd-devops-architect`, `cloud-hosting-expert`, `performance-web-vitals`, `logging-error-tracking-expert`, `production-ready-hardener`, `proactive-background-watcher`, `ai-cost-token-optimizer`, `data-telemetry-expert`, `feature-flag-analytics-expert`, `autonomous-chaos-monkey`, `self-healing-cloud-orchestrator`
+**Orchestrates:** `ci-cd-devops-architect`, `cloud-hosting-expert`, `performance-web-vitals`, `logging-error-tracking-expert`, `production-ready-hardener`, `proactive-background-watcher`, `data-telemetry-expert`, `feature-flag-analytics-expert`, `error-resilience-expert`, `self-healing-cloud-orchestrator`
 - [ ] Perform pre-launch audit across Core Web Vitals (LCP, INP, CLS) and bundle sizes.
 - [ ] Configure production monitoring, alerting rules, and on-call notifications.
 - [ ] Optimize Generative Engine Optimization (GEO) for AI Overviews, Perplexity, ChatGPT Search, and deploy `/llms.txt`.
 - [ ] Generate structured Schema.org JSON-LD markup and AEO conversion landing pages.
 
 #### PHASE 8: Launch, Deployment & Handover
-**Orchestrates:** `cloud-hosting-expert`, `saas-billing`, `saas-transformer`, `auto-doc-updater`, `ci-cd-devops-architect`, `doku-payment-gateway`
+**Orchestrates:** `cloud-hosting-expert`, `saas-billing`, `saas-architect`, `prd-architect`, `ci-cd-devops-architect`, `doku-payment-gateway`, `payment-gateway-expert`
 - [ ] Deploy backend and edge services to Vercel, Cloudflare, AWS, or Railway.
 - [ ] For SaaS applications: deploy Super Admin dashboard on a **separate subdomain** (e.g., `admin.yourdomain.com`) with strict role-based access (`isSuperAdmin` flag).
 - [ ] Configure Stripe / Polar.sh / LemonSqueezy billing and webhooks.
@@ -119,7 +120,7 @@ Launch/Deploy <--- Security/GEO <--- Testing/QA  <--- Frontend/UI
 ## Bahasa Indonesia
 
 ### Integrasi Orkestrasi
-Terhubung dan mengorkestrasi skill domain yang relevan seperti `brainstorming`, `zero-to-prod-orchestrator`, dan `project-context-mapper` untuk memastikan eksekusi yang kohesif.
+Terhubung dan mengorkestrasi skill domain yang relevan seperti `brainstorming`, `zero-to-prod-orchestrator`, dan `session-memory-manager` untuk memastikan eksekusi yang kohesif.
 
 ### Ringkasan
 **Zero to Production Orchestrator** adalah skill master utama yang dirancang untuk mengorkestrasi seluruh ekosistem `vibes-plug` sebagai sebuah **engineering swarm** yang saling terhubung erat. Dengan bertindak sebagai konduktor pusat, skill ini memastikan tidak ada sub-skill yang dieksekusi secara terisolasi. Skill ini memandu pengembang *fullstack* melalui seluruh siklus hidup rekayasa perangkat lunak — mulai dari tahap ide awal hingga integrasi AI, arsitektur backend multi-platform, design system, pengujian otomatis, optimasi GEO/AEO, dan deployment produksi.
@@ -131,17 +132,17 @@ Terhubung dan mengorkestrasi skill domain yang relevan seperti `brainstorming`,
 
 ### Prinsip Inti & Gerbang Ketat
 1. **Jangan Pernah Melewati Fase**: Setiap fase harus diselesaikan dan divalidasi sebelum beralih ke fase berikutnya.
-2. **Otomatisasi Dokumentasi**: Panggil `auto-doc-updater` untuk memperbarui `CHANGELOG.md` dan `BLUEPRINT.md` setelah setiap milestone utama.
+2. **Otomatisasi Dokumentasi**: Panggil `prd-architect` untuk memperbarui `CHANGELOG.md` dan `BLUEPRINT.md` setelah setiap milestone utama.
 3. **Pelacakan Progres**: Pelihara daftar periksa `PROGRESS.md` di root repositori.
-4. **Preservasi State & Konteks**: Gunakan `session-handoff-resume` saat menjeda pekerjaan, dan `session-context-loader` di awal setiap sesi baru untuk menjaga konteks penuh.
-5. **Efisiensi**: Aktifkan `token-saver` selama refactoring besar-besaran untuk mempertahankan *loop* eksekusi yang ringkas dan *powerful*.
+4. **Preservasi State & Konteks**: Gunakan `session-memory-manager` saat menjeda pekerjaan atau memulai sesi baru untuk menjaga konteks penuh.
+5. **Efisiensi**: Aktifkan `anti-slop` selama refactoring besar-besaran untuk mempertahankan *loop* eksekusi yang ringkas, powerful, dan bebas dari placeholder.
 
 ---
 
 ### Master Pipeline Fullstack 8-Fase
 
 #### FASE 1: Discovery & Perencanaan Arsitektur PRD AI
-**Mengorkestrasi:** `prd-architect`, `brainstorming`, `mcp-server-architect`, `session-context-loader`, `dependency-upgrade-migrator`, `app-analyzer-optimizer`, `seo`, `project-context-mapper`, `self-evolving-memory-graph`, `saas-mvp-launcher`, `web-scraper`, `website-design-cloner`, `headless-cms-expert`, `wordpress-headless-expert`, `documentation-site-expert`, `asisten-ramah`, `skill-baru`
+**Mengorkestrasi:** `prd-architect`, `brainstorming`, `deep-research-analyst`, `mcp-server-architect`, `session-memory-manager`, `dependency-upgrade-migrator`, `app-analyzer-optimizer`, `seo`, `saas-architect`, `web-scraper`, `website-design-cloner`, `headless-cms-expert`, `wordpress-headless-expert`, `documentation-site-expert`, `anti-slop`
 - [ ] Dialog terstruktur untuk memperjelas tujuan produk, audiens target, dan persyaratan non-fungsional.
 - [ ] Secara otomatis menyusun Product Requirements Document (PRD.md), Entity Relationship Diagram (ERD.md), dan Dokumentasi (DOKUMENTASI.md) yang komprehensif beserta Roadmap (ROADMAP.md).
 - [ ] Merencanakan integrasi AI/LLM (Vercel AI SDK, alat MCP Server, atau Graf Multi-Agen).
@@ -156,14 +157,14 @@ Terhubung dan mengorkestrasi skill domain yang relevan seperti `brainstorming`,
 - [ ] Menyiapkan template pipeline CI/CD awal (GitHub Actions, Docker).
 
 #### FASE 3: Database & Arsitektur Multi-Tenant
-**Mengorkestrasi:** `fullstack-expert`, `database-migration-versioning-expert`, `database-orm-expert`, `domain-driven-design-expert`, `saas-multi-tenant`, `supabase-migration`, `supabase-security-expert`, `edge-serverless-db-expert`, `data-pipeline-etl-expert`, `search-engine-expert`, `geospatial-maps-expert`, `graph-rag-knowledge-expert`
+**Mengorkestrasi:** `fullstack-expert`, `database-orm-expert`, `domain-driven-design-expert`, `saas-multi-tenant`, `supabase-security-expert`, `data-pipeline-etl-expert`, `search-engine-expert`, `geospatial-maps-expert`, `graph-rag-knowledge-expert`
 - [ ] Merancang skema relasional ter-normalisasi, pemodelan dokumen, dan struktur geospasial PostGIS.
 - [ ] Konfigurasi lapisan ORM (Drizzle ORM / Prisma 6 / SQLx / sqlc) dan indexing mesin pencari (Typesense/Meilisearch).
 - [ ] Mengimplementasikan kebijakan Row-Level Security (RLS) dan isolasi tenant.
 - [ ] Menerapkan migrasi database awal dan connection poolers (PgBouncer/Supavisor/Neon).
 
 #### FASE 4: Backend API, Microservices & Agen AI
-**Mengorkestrasi:** `js-backend-expert`, `go-programming-expert`, `graphql-apollo-expert`, `openapi-swagger-codegen-expert`, `ai-llm-integration-expert`, `ai-prompt-engineering-expert`, `ai-media-generation-expert`, `multi-agent-orchestration`, `mcp-server-architect`, `authentication-identity-expert`, `email-notification-expert`, `cron-scheduler-expert`, `rate-limit-abuse-prevention`, `file-upload-media-expert`, `saas-billing`, `payment-gateway-expert`, `vector-db-rag-expert`, `mcp-client-orchestrator`, `async-queue-temporal-expert`, `background-jobs-queue-expert`, `doku-mcp-server`, `event-driven-architect`, `gemini-agent-booster`, `mobile-push-notification-expert`, `realtime-collaboration-expert`, `api-gateway-proxy-expert`, `wasm-edge-computing-expert`, `sse-websocket-streaming-expert`, `n8n-automation-expert`, `chatbot-messaging-expert`, `pdf-document-generation-expert`, `ecommerce-expert`, `blockchain-web3-expert`, `local-slm-edge-ai-expert`, `voice-ai-realtime-agent`, `graph-rag-knowledge-expert`
+**Mengorkestrasi:** `js-backend-expert`, `go-programming-expert`, `pydantic-ai-expert`, `vercel-ai-sdk-expert`, `synthetic-data-finetuning-expert`, `graphql-apollo-expert`, `openapi-swagger-codegen-expert`, `ai-llm-integration-expert`, `ai-prompt-engineering-expert`, `ai-media-generation-expert`, `multi-agent-orchestration`, `mcp-server-architect`, `authentication-identity-expert`, `email-notification-expert`, `cron-scheduler-expert`, `rate-limit-abuse-prevention`, `file-upload-media-expert`, `saas-billing`, `payment-gateway-expert`, `vector-db-rag-expert`, `async-queue-temporal-expert`, `doku-mcp-server`, `event-driven-architect`, `gemini-agent-booster`, `realtime-collaboration-expert`, `api-gateway-proxy-expert`, `wasm-edge-computing-expert`, `sse-websocket-streaming-expert`, `n8n-automation-expert`, `chatbot-messaging-expert`, `pdf-document-generation-expert`, `ecommerce-expert`, `blockchain-web3-expert`, `local-slm-edge-ai-expert`, `voice-ai-realtime-agent`, `graph-rag-knowledge-expert`
 - [ ] Bangun API REST / GraphQL / gRPC *high-throughput* menggunakan Fastify 5, NestJS, Hono, Gin, atau Axum.
 - [ ] Mengimplementasikan autentikasi (Clerk, Auth.js, Supabase Auth) dan middleware RBAC.
 - [ ] Membangun alat MCP Server atau alur kerja multi-agen LangGraph berbasis state dengan gerbang *human-in-the-loop*.
@@ -173,7 +174,7 @@ Terhubung dan mengorkestrasi skill domain yang relevan seperti `brainstorming`,
 - [ ] Mengimplementasikan upload file dengan presigned URL (S3/R2) dan pemrosesan media.
 
 #### FASE 5: Frontend, Design System & Mobile App
-**Mengorkestrasi:** `modern-web-guidance`, `design-system-architect`, `senior-frontend`, `nextjs-app-router-expert`, `vue-frontend-expert`, `astro-framework-expert`, `svelte-sveltekit-expert`, `solidjs-expert`, `angular-expert`, `tailwind-expert`, `tanstack-query-expert`, `spa-orchestrator`, `mobile-expo-expert`, `apple-ecosystem-expert`, `tauri-expert`, `desktop-electron-expert`, `form-validation-expert`, `ui-components-expert`, `svg-animation-motion-expert`, `web-3d-graphics-expert`, `web-game-engine-expert`, `glsl-shader-expert`, `webxr-ar-vr-expert`, `visual-qa-vision-agent`, `hig`, `global-a11y-i18n-expert`, `bootstrap-to-modern`, `monday-design-aesthetic`, `state-management-expert`, `ui-ux-pro-max`, `data-visualization-expert`, `rich-text-editor-expert`, `documentation-site-expert`, `blockchain-web3-expert`, `modern-css-native-expert`, `pwa-offline-first-expert`
+**Mengorkestrasi:** `modern-web-guidance`, `design-system-architect`, `senior-frontend`, `vercel-ai-sdk-expert`, `nextjs-app-router-expert`, `vue-frontend-expert`, `astro-framework-expert`, `svelte-sveltekit-expert`, `solidjs-expert`, `angular-expert`, `tailwind-expert`, `tanstack-query-expert`, `spa-orchestrator`, `mobile-expo-expert`, `apple-ecosystem-expert`, `tauri-expert`, `desktop-electron-expert`, `form-validation-expert`, `svg-animation-motion-expert`, `web-3d-graphics-expert`, `web-game-engine-expert`, `glsl-shader-expert`, `webxr-ar-vr-expert`, `visual-qa-vision-agent`, `hig`, `global-a11y-i18n-expert`, `bootstrap-to-modern`, `state-management-expert`, `ui-ux-pro-max`, `data-visualization-expert`, `rich-text-editor-expert`, `documentation-site-expert`, `blockchain-web3-expert`, `modern-css-native-expert`, `pwa-offline-first-expert`
 - [ ] **MANDATORY**: Jalankan `modern-web-guidance` PERTAMA KALI sebelum mengimplementasikan fitur frontend HTML/CSS/JS untuk memastikan kepatuhan dengan standar modern Google.
 - [ ] Implementasikan token desain (OKLCH) dan konfigurasi tema Tailwind CSS v4.
 - [ ] Bangun komponen primitif aksesibel menggunakan Radix UI / Base UI dan CVA.
@@ -181,28 +182,29 @@ Terhubung dan mengorkestrasi skill domain yang relevan seperti `brainstorming`,
 - [ ] Buat halaman React 19 / Next.js 15, Vue 3, Astro 5, Svelte 5, SolidJS 2, atau Angular 19+ dengan wallet Web3.
 - [ ] **MANDATORY**: Otomatis buat halaman standar: About, Profile, Contact, Terms of Reference/Service, dan Privacy Policy.
 - [ ] Mengimplementasikan formulir kompleks dengan React Hook Form + validasi Zod.
+- [ ] Jika Web 3D atau Web Game: arsitekturkan dengan WebGPU (`WebGPURenderer`, PlayCanvas, atau Babylon.js), kompresi tekstur KTX2 Basis Universal, geometri Meshopt, loop fisika fixed-timestep, zero-GC object pooling, dan audio spasial 3D.
 - [ ] Jika arsitektur SPA — koordinasikan dengan `spa-orchestrator` untuk routing (TanStack Router), state (TanStack Query v5), dan API layer terpisah.
 - [ ] Mengintegrasikan manajemen state frontend dengan TanStack Query v5.
 
 #### FASE 6: Pengujian Otomatis, Ketahanan Error & Audit Keamanan
-**Mengorkestrasi:** `e2e-testing-expert`, `accessibility-testing-expert`, `secure-fuzz-testing`, `firebase-security-expert`, `error-resilience-expert`, `logging-error-tracking-expert`, `vibe-code-gardener`, `coderabbit`, `autonomous-tdd-debugger`, `browser-automation-expert`, `zero-trust-secret-vault`, `autonomous-red-teamer`, `post-quantum-crypto-migrator`, `compliance-gdpr-privacy-expert`, `ai-evals-benchmark-expert`
+**Mengorkestrasi:** `e2e-testing-expert`, `accessibility-testing-expert`, `secure-fuzz-testing`, `firebase-security-expert`, `error-resilience-expert`, `logging-error-tracking-expert`, `anti-slop`, `coderabbit`, `autonomous-tdd-debugger`, `browser-automation-expert`, `zero-trust-secret-vault`, `autonomous-red-teamer`, `post-quantum-crypto-migrator`, `compliance-gdpr-privacy-expert`
 - [ ] Menulis unit test dan integration test dengan Vitest dan pytest.
 - [ ] Menulis pengujian browser E2E Playwright dan pengujian aksesibilitas WCAG 2.2 otomatis (`@axe-core/playwright` dan Pa11y).
 - [ ] Menjalankan pengujian fuzzing keamanan (Atheris / cargo-fuzz / native Go fuzzing).
 - [ ] Mengimplementasikan Error Boundary, pola retry, circuit breaker, dan degradasi anggun.
 - [ ] Menyiapkan logging terstruktur (Pino) dan pelacakan error (Sentry) dengan upload source map.
 - [ ] Mengaudit CORS, CSP headers, rate-limiting, dan sanitasi input.
-- [ ] Menjalankan audit kualitas kode untuk membersihkan AI slop dan pembusukan arsitektur.
+- [ ] Menjalankan audit kualitas kode untuk membersihkan AI slop dan pembusukan arsitektur dengan anti-slop.
 
 #### FASE 7: Hardening Pra-Peluncuran, Monitoring & DevOps Sentinel
-**Mengorkestrasi:** `production-ready-hardener`, `app-analyzer-optimizer`, `seo`, `logging-error-tracking-expert`, `proactive-background-watcher`, `ai-cost-token-optimizer`, `data-telemetry-expert`, `feature-flag-analytics-expert`, `autonomous-chaos-monkey`, `self-healing-cloud-orchestrator`
+**Mengorkestrasi:** `ci-cd-devops-architect`, `cloud-hosting-expert`, `performance-web-vitals`, `logging-error-tracking-expert`, `production-ready-hardener`, `proactive-background-watcher`, `data-telemetry-expert`, `feature-flag-analytics-expert`, `error-resilience-expert`, `self-healing-cloud-orchestrator`
 - [ ] Audit pra-peluncuran pada Core Web Vitals (LCP, INP, CLS) dan ukuran bundle.
 - [ ] Mengonfigurasi monitoring produksi, aturan alerting, dan notifikasi on-call.
 - [ ] Mengoptimalkan GEO untuk AI Overviews, Perplexity, ChatGPT Search, dan merilis `/llms.txt`.
 - [ ] Membuat markup terstruktur Schema.org JSON-LD dan landing page konversi AEO.
 
 #### FASE 8: Peluncuran, Deployment & Serah Terima
-**Mengorkestrasi:** `cloud-hosting-expert`, `saas-billing`, `saas-transformer`, `auto-doc-updater`, `ci-cd-devops-architect`, `doku-payment-gateway`
+**Mengorkestrasi:** `cloud-hosting-expert`, `saas-billing`, `saas-architect`, `prd-architect`, `ci-cd-devops-architect`, `doku-payment-gateway`, `payment-gateway-expert`
 - [ ] Deploy backend dan edge services ke Vercel, Cloudflare, AWS, atau Railway.
 - [ ] Untuk aplikasi SaaS: deploy dashboard Super Admin pada **subdomain terpisah** (misal: `admin.domain.com`) dengan kontrol akses berbasis role (`isSuperAdmin`).
 - [ ] Konfigurasi billing Stripe / Polar.sh / LemonSqueezy dan webhooks.

package/skills/ai-cost-token-optimizer/SKILL.md

@@ -1,82 +0,0 @@
----
-name: ai-cost-token-optimizer
-description: "Expert guide for LLM API cost optimization, Prompt Caching, model routing (Flash/Pro/Opus), semantic caching, and token budgeting / Panduan ahli optimasi biaya API LLM, Prompt Caching, model routing, dan semantic caching."
-author: "Roedy Rustam"
----
-
-# AI Cost & Token Optimizer
-
-[English](#english) | [Bahasa Indonesia](#bahasa-indonesia)
-
----
-
-<a name="english"></a>
-## English
-
-### Purpose & Overview
-Production-grade guidelines for FinOps in AI engineering — prompt caching (Anthropic Prompt Caching, Gemini Context Caching), dynamic model routing (routing lightweight queries to Flash/Haiku and complex reasoning to Pro/Opus), semantic caching with Redis/GPTCache, and real-time token expenditure tracking.
-
-### Key Capabilities
-- **Prompt & Context Caching**: Storing static system prompts, long-context documents, and schemas in cache to reduce token costs by up to 90%.
-- **Model Router**: Heuristic and classifier-based routing between ultra-fast Flash models and high-reasoning Pro models.
-- **Semantic Caching**: Hashing query vector embeddings to serve cached responses for semantically identical user queries.
-
-```typescript
-// Model Routing Strategy Example
-export function selectOptimalModel(promptLength: number, taskType: 'classification' | 'reasoning' | 'summary') {
-  if (taskType === 'classification' || promptLength < 500) {
-    return 'gemini-3.5-flash'; // High speed, ultra low cost
-  }
-  return 'gemini-3.1-pro'; // Complex reasoning
-}
-```
-
-### Implementation Checklist
-- [ ] Enable Context Caching for static system prompts or documents larger than 32k tokens.
-- [ ] Implement a router heuristic: use `gemini-3.5-flash` for simple parsing and `gemini-3.1-pro` for deep reasoning.
-- [ ] Set up semantic caching (e.g., Redis + Vector Search) for frequently asked identical queries.
-- [ ] Monitor token usage and set hard budgeting limits per user/tenant to prevent abuse.
-
-### Operating Protocol
-1. **Model Fallback & Routing**: Sets up an abstraction layer (like LiteLLM or Vercel AI SDK Core) to support multiple providers.
-2. **Complexity Scoring**: Implements heuristics (prompt length, required JSON schema, keyword analysis) to route to the cheapest capable model.
-3. **Semantic Caching Integration**: Implements a Vector DB or Redis caching layer. Before routing to an LLM, it embeddings the user prompt and checks if a semantically similar query was answered recently.
-4. **Token Budgeting**: Sets hard limits and alerts for daily API consumption per tenant/user.
-
----
-
-<a name="bahasa-indonesia"></a>
-## Bahasa Indonesia
-
-### Deskripsi
-Panduan tingkat produksi untuk FinOps dalam rekayasa AI — prompt caching (Anthropic Prompt Caching & Gemini Context Caching), routing model dinamis (mengarahkan tugas ringan ke Flash/Haiku dan tugas penalaran ke Pro/Opus), semantic caching dengan Redis, dan pelacakan anggaran token real-time.
-
-### Fitur Utama
-- **Prompt & Context Caching**: Menyimpan prompt sistem dan dokumen konteks panjang di cache untuk menghemat hingga 90% biaya token.
-- **Model Router**: Routing otomatis berdasarkan heuristik antara model ultra-cepat Flash dan model penalaran Pro.
-- **Semantic Caching**: Memanfaatkan embedding vector query untuk menyajikan respon cache pada pertanyaan pengguna yang serupa secara semantik.
-
-### Checklist Implementasi
-- [ ] Aktifkan Context Caching untuk prompt sistem statis atau dokumen yang lebih besar dari 32k token.
-- [ ] Terapkan heuristik router: gunakan `gemini-3.5-flash` untuk parsing sederhana dan `gemini-3.1-pro` untuk penalaran mendalam.
-- [ ] Siapkan semantic caching (misal: Redis + Vector Search) untuk pertanyaan identik yang sering diajukan.
-- [ ] Pantau penggunaan token dan tetapkan batas anggaran yang ketat per pengguna/tenant untuk mencegah penyalahgunaan.
-
-### Protokol Operasi
-1. **Routing & Fallback Model**: Menyiapkan lapisan abstraksi (seperti LiteLLM atau Vercel AI SDK Core) untuk mendukung berbagai penyedia model.
-2. **Penilaian Kompleksitas**: Mengimplementasikan heuristik (panjang prompt, kebutuhan skema JSON, analisis kata kunci) untuk mengarahkan prompt ke model termurah yang mampu menyelesaikannya.
-3. **Integrasi Semantic Caching**: Mengimplementasikan lapisan *cache* Vector DB atau Redis. Sebelum mengirim ke LLM, prompt pengguna diubah menjadi vektor (*embedding*) untuk mengecek apakah pertanyaan serupa pernah dijawab baru-baru ini.
-4. **Penganggaran Token**: Menetapkan batas maksimal dan notifikasi untuk konsumsi API harian per pengguna/tenant.
-
-
-## Orchestration & Integration
-- Integrates with `ai-llm-integration-expert`, `token-saver`, and `zero-to-prod-orchestrator`.
-- Connects to `edge-serverless-db-expert` (Upstash/Redis) for fast semantic caching.
-- Collaborates with `vector-db-rag-expert` for similarity scoring during cache retrieval.
-- Feeds billing metrics into `saas-billing` for usage-based AI pricing models.
-
-## Integrasi Orkestrasi
-- Terintegrasi dengan `ai-llm-integration-expert`, `token-saver`, dan `zero-to-prod-orchestrator`.
-- Terhubung dengan `edge-serverless-db-expert` (Upstash/Redis) untuk *semantic caching* secepat kilat.
-- Berkolaborasi dengan `vector-db-rag-expert` untuk perhitungan kemiripan saat pencarian *cache*.
-- Memasok metrik penagihan ke `saas-billing` untuk model bisnis AI berbasis penggunaan (*usage-based pricing*).