vibes-plug 2.11.0 → 2.14.1

package/skills/background-jobs-queue-expert/SKILL.md

@@ -1,235 +0,0 @@
----
-name: background-jobs-queue-expert
-description: "Dedicated deep-dive for BullMQ v5, Trigger.dev v3, Inngest, delayed jobs, job deduplication, idempotency, dead letter queues, and job priority / Panduan mendalam untuk BullMQ v5, Trigger.dev v3, Inngest, delayed jobs, deduplikasi job, idempotency, dead letter queue, dan prioritas job."
-author: "Roedy Rustam"
----
-
-# Background Jobs & Queue Expert (BullMQ v5 & Resilient Queues)
-
-[English](#english) | [Bahasa Indonesia](#bahasa-indonesia)
-
----
-
-<a name="english"></a>
-## English
-
-### Purpose & Overview
-Production-grade engineering guide for background job queues and asynchronous task processing using **BullMQ v5**, **Trigger.dev v3**, and **Inngest**. Focuses on the core mechanics of fault-tolerant distributed queues: job deduplication, multi-tenant priority queues, exponential backoff jitter, Dead Letter Queue (DLQ) automated forwarding, and strict transactional idempotency.
-
-### Key Capabilities
-1. **Strict Idempotency**: Ensuring background workers execute with deterministic effects using database-backed idempotency keys.
-2. **Job Deduplication**: Leveraging deterministic BullMQ `jobId` hashing to prevent duplicate enqueueing of ongoing or delayed tasks.
-3. **Dead Letter Queues (DLQ)**: Automatic relocation of permanently failing jobs after retry exhaustion for manual inspection and alerting.
-4. **Tenant Prioritization**: Differentiating throughput between VIP/enterprise tiers and free-tier users using BullMQ job priorities.
-5. **Backoff Jitter & Throttling**: Exponential backoff combined with randomized full jitter to prevent upstream thundering herds.
-
----
-
-### Production Implementation Recipes
-
-#### Recipe 1: Production BullMQ v5 Worker with Deduplication & DLQ Forwarding (TypeScript)
-```typescript
-import { Queue, Worker, Job } from 'bullmq';
-import Redis from 'ioredis';
-
-const redisConnection = new Redis(process.env.REDIS_URL || 'redis://localhost:6379', {
-  maxRetriesPerRequest: null, // Required by BullMQ
-});
-
-export interface NotificationPayload {
-  tenantId: string;
-  userId: string;
-  type: 'email' | 'webhook';
-  payload: Record<string, unknown>;
-  idempotencyKey: string;
-}
-
-// Main Queue
-export const notificationQueue = new Queue<NotificationPayload>('notifications', {
-  connection: redisConnection,
-  defaultJobOptions: {
-    attempts: 5,
-    backoff: {
-      type: 'exponential',
-      delay: 1500, // Starts at 1.5s, doubles up to ~24s with jitter
-    },
-    removeOnComplete: { age: 86400, count: 5000 },
-    removeOnFail: false, // Preserved for DLQ audit
-  },
-});
-
-// Dead Letter Queue (DLQ)
-export const notificationDLQ = new Queue('notifications-dlq', {
-  connection: redisConnection,
-});
-
-/**
- * Enqueues a notification job with strict deduplication and priority
- */
-export async function enqueueNotification(
-  data: NotificationPayload,
-  isVip = false
-) {
-  return await notificationQueue.add('send_notification', data, {
-    jobId: `notif_${data.idempotencyKey}`, // Deterministic deduplication key
-    priority: isVip ? 1 : 10, // Lower numbers denote higher priority in BullMQ
-  });
-}
-
-// Background Worker
-export const notificationWorker = new Worker<NotificationPayload>(
-  'notifications',
-  async (job: Job<NotificationPayload>) => {
-    console.log(`[Worker] Processing Job ${job.id} for Tenant: ${job.data.tenantId}`);
-    
-    // Simulate task processing with idempotency verification
-    if (job.data.type === 'email') {
-      await deliverEmail(job.data);
-    }
-  },
-  {
-    connection: redisConnection,
-    concurrency: 20, // Max concurrent jobs per worker process
-    limiter: {
-      max: 100, // Maximum 100 jobs processed
-      duration: 1000, // Per 1000ms (Rate Limiting)
-    },
-  }
-);
-
-// Forward to DLQ upon exhaustion of retry attempts
-notificationWorker.on('failed', async (job, error) => {
-  if (job && job.attemptsMade >= (job.opts.attempts || 5)) {
-    console.error(`[DLQ] Job ${job.id} exhausted retries. Forwarding to notifications-dlq:`, error.message);
-    await notificationDLQ.add('failed_notification', {
-      originalJobId: job.id,
-      failedReason: error.message,
-      data: job.data,
-      exhaustedAt: new Date().toISOString(),
-    });
-  }
-});
-```
-
----
-
-### Implementation Checklist
-- [ ] Configure `maxRetriesPerRequest: null` on the Redis client as required by BullMQ v5.
-- [ ] Use deterministic `jobId` derived from business logic (`order_${orderId}`) to enforce deduplication.
-- [ ] Add event listener on `failed` to automatically forward permanently dead jobs to a Dead Letter Queue.
-- [ ] Implement rate limiting using worker `limiter` to protect third-party services against rate-limit bans.
-
-## Orchestration & Integration
-- Integrates with: `js-backend-expert`, `async-queue-temporal-expert`, `error-resilience-expert`, `data-telemetry-expert`.
-
----
-
-<a name="bahasa-indonesia"></a>
-## Bahasa Indonesia
-
-### Tujuan & Gambaran Umum
-Panduan rekayasa tingkat produksi untuk antrean pekerjaan latar belakang (*background job queues*) dan pemrosesan tugas asinkron menggunakan **BullMQ v5**, **Trigger.dev v3**, dan **Inngest**. Berfokus pada mekanika inti antrean terdistribusi yang tangguh: deduplikasi job, prioritas multi-tenant, *exponential backoff jitter*, pemindahan otomatis ke Dead Letter Queue (DLQ), dan idempotensi transaksi yang ketat.
-
-### Kemampuan Utama
-1. **Idempotensi Ketat**: Memastikan pekerja (*worker*) mengeksekusi tugas dengan dampak deterministik menggunakan kunci idempotensi yang tercatat di database.
-2. **Deduplikasi Job**: Memanfaatkan penetapan `jobId` deterministik di BullMQ untuk mencegah antrean ganda pada tugas yang sedang berjalan atau tertunda.
-3. **Dead Letter Queue (DLQ)**: Pemindahan otomatis tugas yang gagal total setelah jatah percobaan ulang habis untuk audit dan penanganan manual.
-4. **Prioritas Tenant**: Membedakan prioritas tugas antara pengguna VIP/Enterprise dengan pengguna paket gratis menggunakan nilai prioritas BullMQ.
-5. **Backoff Jitter & Throttling**: Mekanisme penundaan eksponensial dengan *jitter* acak untuk mencegah fenomena *thundering herd* pada server hilir.
-
----
-
-### Resep Implementasi Produksi
-
-#### Resep 1: Worker BullMQ v5 Produksi dengan Deduplikasi & Forward DLQ (TypeScript)
-```typescript
-import { Queue, Worker, Job } from 'bullmq';
-import Redis from 'ioredis';
-
-const koneksiRedis = new Redis(process.env.REDIS_URL || 'redis://localhost:6379', {
-  maxRetriesPerRequest: null,
-});
-
-export interface MuatanNotifikasi {
-  tenantId: string;
-  userId: string;
-  type: 'email' | 'webhook';
-  payload: Record<string, unknown>;
-  idempotencyKey: string;
-}
-
-// Antrean Utama
-export const antreanNotifikasi = new Queue<MuatanNotifikasi>('notifikasi', {
-  connection: koneksiRedis,
-  defaultJobOptions: {
-    attempts: 5,
-    backoff: {
-      type: 'exponential',
-      delay: 1500,
-    },
-    removeOnComplete: { age: 86400, count: 5000 },
-    removeOnFail: false,
-  },
-});
-
-// Antrean Dead Letter (DLQ)
-export const antreanDLQ = new Queue('notifikasi-dlq', {
-  connection: koneksiRedis,
-});
-
-/**
- * Memasukkan tugas ke antrean dengan deduplikasi dan prioritas
- */
-export async function masukkanNotifikasi(
-  data: MuatanNotifikasi,
-  isVip = false
-) {
-  return await antreanNotifikasi.add('kirim_notifikasi', data, {
-    jobId: `notif_${data.idempotencyKey}`, // Kunci deduplikasi unik
-    priority: isVip ? 1 : 10, // Nilai lebih kecil menandakan prioritas lebih tinggi
-  });
-}
-
-// Worker Pemroses
-export const workerNotifikasi = new Worker<MuatanNotifikasi>(
-  'notifikasi',
-  async (job: Job<MuatanNotifikasi>) => {
-    console.log(`[Worker] Memproses Job ${job.id} untuk Tenant: ${job.data.tenantId}`);
-    if (job.data.type === 'email') {
-      await kirimEmail(job.data);
-    }
-  },
-  {
-    connection: koneksiRedis,
-    concurrency: 20,
-    limiter: {
-      max: 100,
-      duration: 1000,
-    },
-  }
-);
-
-// Teruskan ke DLQ jika jatah retry telah habis
-workerNotifikasi.on('failed', async (job, error) => {
-  if (job && job.attemptsMade >= (job.opts.attempts || 5)) {
-    console.error(`[DLQ] Job ${job.id} gagal total. Memindahkan ke DLQ:`, error.message);
-    await antreanDLQ.add('notifikasi_gagal', {
-      originalJobId: job.id,
-      failedReason: error.message,
-      data: job.data,
-      exhaustedAt: new Date().toISOString(),
-    });
-  }
-});
-```
-
----
-
-### Checklist Implementasi
-- [ ] Atur konfigurasi `maxRetriesPerRequest: null` pada koneksi ioredis untuk BullMQ v5.
-- [ ] Gunakan `jobId` deterministik dari ID transaksi bisnis (`invoice_${invoiceId}`) untuk mencegah duplikasi.
-- [ ] Pasang *event listener* pada event `failed` untuk meneruskan job yang gagal total ke antrean DLQ.
-- [ ] Terapkan pembatasan *rate limiter* pada worker untuk menjaga kestabilan API eksternal.
-
-## Integrasi Orkestrasi
-- Terintegrasi dengan: `js-backend-expert`, `async-queue-temporal-expert`, `error-resilience-expert`, `data-telemetry-expert`.

package/skills/database-migration-versioning-expert/SKILL.md

@@ -1,90 +0,0 @@
----
-name: database-migration-versioning-expert
-description: "Expert guide for database migrations: schema versioning, zero-downtime migrations, backward-compatible changes, data backfill, and rollback strategies / Panduan ahli migrasi database."
-author: "Roedy Rustam"
----
-
-# Database Migration & Versioning Expert
-
-[English](#english) | [Bahasa Indonesia](#bahasa-indonesia)
-
----
-
-<a name="english"></a>
-## English
-
-### Description
-A specialized skill focused strictly on the lifecycle of database schemas in production environments. While `database-orm-expert` handles queries and types, this skill covers the DevOps aspect of databases: zero-downtime schema migrations, backward-compatible release cycles, stateful data backfills, rollback mechanisms, and schema versioning strategies.
-
-### Trigger Conditions
-- When modifying an existing production database schema.
-- When planning a deployment that involves database changes (blue-green, canary).
-- When resolving merge conflicts in migration files (e.g., Prisma, Drizzle, Alembic).
-- When designing backfill scripts for massive data migrations.
-
-### Core Architectural Guidelines
-
-#### 1. Zero-Downtime Migration Pattern (Expand and Contract)
-Never make breaking changes in a single deployment. Use the "Expand and Contract" pattern (Parallel Change):
-- **Phase 1 (Expand)**: Add the new schema element (column, table) without removing the old one. Deploy the database change.
-- **Phase 2 (Migrate)**: Update application code to write to *both* old and new elements, and read from the new element (with fallback). Deploy code.
-- **Phase 3 (Backfill)**: Run a background script to backfill data from the old element to the new element for older records.
-- **Phase 4 (Contract)**: Remove the old application code that writes to the old element. Deploy code.
-- **Phase 5 (Cleanup)**: Drop the old schema element from the database.
-
-#### 2. Backward Compatibility Rules
-- **Never `DROP` or `RENAME`** a column/table in active use. Create a new one, migrate data, then drop the old one later.
-- **Avoid changing constraints** on existing data without carefully verifying that all data complies.
-- **Add `DEFAULT` values** to new `NOT NULL` columns, or make them nullable first, backfill, then enforce `NOT NULL`.
-
-#### 3. Migration Mechanics
-- Always use version-controlled, immutable migration scripts (e.g., `20260814_add_user_status.sql`).
-- Never modify an already-applied migration file. If a mistake was made, create a new forward-migration to fix it.
-- **Idempotency**: Write scripts that can be safely run multiple times (e.g., `CREATE TABLE IF NOT EXISTS`, `ADD COLUMN IF NOT EXISTS`).
-
-#### 4. Safe Data Backfilling
-For large tables (millions of rows), running `UPDATE table SET new_col = old_col` will lock the table and cause downtime.
-- **Chunking**: Perform updates in batches using `LIMIT` and sleep intervals to avoid locking the database.
-- **Background Jobs**: Use dedicated queues (like BullMQ or Inngest) to orchestrate massive backfills.
-
-## Orchestration & Integration
-- Enhances `database-orm-expert` with production-grade migration strategies.
-- Complements `ci-cd-devops-architect` for automated migration deployment steps.
-- Integrates with `supabase-migration` for Supabase-specific PostgreSQL migration workflows.
-
----
-
-<a name="bahasa-indonesia"></a>
-## Bahasa Indonesia
-
-### Deskripsi
-Skill khusus yang berfokus ketat pada siklus hidup skema database di lingkungan produksi. Sementara `database-orm-expert` menangani query dan tipe, skill ini mencakup aspek DevOps database: migrasi skema tanpa downtime (zero-downtime), rilis backward-compatible, skrip backfill data stateful, mekanisme rollback, dan strategi pembuatan versi skema.
-
-### Kondisi Pemicu
-- Saat memodifikasi skema database produksi yang sudah ada.
-- Saat merencanakan deployment yang melibatkan perubahan database (blue-green, canary).
-- Saat merancang skrip backfill untuk tabel berukuran besar (jutaan baris).
-
-### Panduan Arsitektur Inti
-
-#### 1. Pola Zero-Downtime (Expand and Contract)
-Jangan pernah melakukan perubahan yang merusak (breaking change) dalam satu deployment.
-- Tambahkan kolom baru tanpa menghapus yang lama.
-- Ubah aplikasi untuk menulis ke keduanya dan membaca dari yang baru.
-- Lakukan migrasi data lama (backfill).
-- Hapus penggunaan kolom lama dari kode aplikasi.
-- Hapus kolom lama dari database di migrasi berikutnya.
-
-#### 2. Aturan Kompatibilitas Mundur (Backward Compatibility)
-- **Jangan pernah melakukan `DROP` atau `RENAME`** pada kolom yang sedang aktif digunakan. Buat yang baru, pindahkan data, baru hapus yang lama di siklus rilis berikutnya.
-- Kolom `NOT NULL` baru harus selalu memiliki nilai `DEFAULT`, atau jadikan nullable terlebih dahulu sebelum memaksakan constraint.
-
-#### 3. Keamanan Skrip Migrasi
-- Gunakan file migrasi yang immutable (tidak boleh diubah setelah di-deploy). Jika ada bug, buat file migrasi baru untuk memperbaikinya (forward-fix).
-- Skrip harus sebisa mungkin bersifat idempoten.
-- Untuk tabel besar, lakukan backfill data secara bertahap (chunking/batching) agar tidak terjadi table lock yang menyebabkan downtime aplikasi.
-
-## Integrasi Orkestrasi
-- Memperkuat `database-orm-expert` dengan strategi deployment yang aman.
-- Melengkapi `ci-cd-devops-architect` dalam alur CI/CD untuk otomatisasi migrasi.
-- Terintegrasi dengan `supabase-migration` untuk ekosistem spesifik Supabase.

package/skills/edge-serverless-db-expert/SKILL.md

@@ -1,99 +0,0 @@
----
-name: edge-serverless-db-expert
-description: "Expert guide for Serverless & Edge Databases (Neon Serverless Postgres, Cloudflare D1, Turso/libsql, Upstash Redis), cold-start mitigation, and connection pooling / Panduan ahli database Serverless & Edge (Neon, Cloudflare D1, Turso, Upstash)."
-author: "Roedy Rustam"
----
-
-# Edge & Serverless DB Expert
-
-[English](#english) | [Bahasa Indonesia](#bahasa-indonesia)
-
----
-
-<a name="english"></a>
-## English
-
-### Purpose & Overview
-Best practices for building ultra-low-latency 2026/2027 applications powered by serverless and edge databases. Exploit Neon Serverless Postgres, Cloudflare D1, Turso, Upstash Serverless Redis & Vector. Implement zero-cold-start strategies and HTTP connection pooling.
-
-### Key Capabilities
-- **Neon & Cloudflare D1**: Serverless autoscaling Postgres with instant branching. Distributed edge SQLite.
-- **Connection Pooling**: WebSocket/HTTP proxy pooling (Neon Serverless Driver, Upstash Redis over HTTP) for edge workers. Prevent TCP pool exhaustion.
-- **Embedded Replicas**: Sync edge SQLite read-replicas with central cloud databases for sub-10ms queries.
-
-```typescript
-import { neon } from '@neondatabase/serverless';
-import { drizzle } from 'drizzle-orm/neon-http';
-
-const sql = neon(process.env.DATABASE_URL!);
-export const db = drizzle({ client: sql });
-```
-
-### Implementation Checklist
-- [ ] Use HTTP/WebSocket drivers (e.g., `neon-http`) for querying databases from Edge Workers/Functions.
-- [ ] Configure connection pooling (PgBouncer, Prisma Accelerate) for standard TCP connections to avoid exhausting database connection limits.
-- [ ] Use read-replicas near the edge location for global deployments to minimize latency.
-- [ ] Cache read-heavy queries at the edge using Upstash Redis or Cloudflare KV.
-
-### Example: Upstash Redis Edge Caching
-```typescript
-import { Redis } from '@upstash/redis';
-
-const redis = new Redis({
-  url: process.env.UPSTASH_REDIS_REST_URL!,
-  token: process.env.UPSTASH_REDIS_REST_TOKEN!,
-});
-
-export async function getCachedData(key: string) {
-  let data = await redis.get(key);
-  if (!data) {
-    data = await fetchFromDB();
-    await redis.set(key, data, { ex: 3600 }); // Cache for 1 hour
-  }
-  return data;
-}
-```
-
-## Orchestration & Integration
-- Integrates with: `database-orm-expert`, `js-backend-expert`, `cloud-hosting-expert`.
-
----
-
-<a name="bahasa-indonesia"></a>
-## Bahasa Indonesia
-
-### Deskripsi
-Praktik terbaik membangun aplikasi latensi rendah 2026/2027 dengan database serverless dan edge. Manfaatkan Neon Serverless Postgres, Cloudflare D1, Turso, Upstash Serverless Redis & Vector. Implementasi strategi tanpa cold-start dan connection pooling HTTP.
-
-### Fitur Utama
-- **Neon & Cloudflare D1**: Serverless Postgres autoscaling dengan branching instan. Distributed edge SQLite.
-- **Connection Pooling**: Proxy pooling HTTP/WebSocket untuk edge worker. Cegah kehabisan koneksi TCP.
-- **Embedded Replicas**: Sinkronisasi read-replica SQLite di edge dengan database utama untuk query di bawah 10ms.
-
-### Checklist Implementasi
-- [ ] Gunakan driver HTTP/WebSocket (misal: `neon-http`) untuk mengakses database dari Edge Workers/Functions.
-- [ ] Konfigurasi connection pooling (PgBouncer, Prisma Accelerate) pada koneksi TCP standar untuk mencegah batas koneksi habis.
-- [ ] Gunakan read-replicas di dekat lokasi edge untuk deployment global guna meminimalkan latensi.
-- [ ] Cache query berat di edge menggunakan Upstash Redis atau Cloudflare KV.
-
-### Contoh: Upstash Redis Edge Caching
-```typescript
-import { Redis } from '@upstash/redis';
-
-const redis = new Redis({
-  url: process.env.UPSTASH_REDIS_REST_URL!,
-  token: process.env.UPSTASH_REDIS_REST_TOKEN!,
-});
-
-export async function getCachedData(key: string) {
-  let data = await redis.get(key);
-  if (!data) {
-    data = await fetchFromDB();
-    await redis.set(key, data, { ex: 3600 }); // Cache 1 jam
-  }
-  return data;
-}
-```
-
-## Integrasi Orkestrasi
-- Terintegrasi dengan: `database-orm-expert`, `js-backend-expert`, `cloud-hosting-expert`.

package/skills/mcp-client-orchestrator/SKILL.md

@@ -1,76 +0,0 @@
----
-name: mcp-client-orchestrator
-description: "Expert guide for the AI Agent to dynamically orchestrate and consume external MCP (Model Context Protocol) servers, giving it real-time superpowers over databases, GitHub, Slack, and local files."
-author: "Roedy Rustam"
----
-
-# MCP Client Orchestrator
-
-[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
-While `mcp-server-architect` teaches the agent how to *build* servers, this skill teaches the agent how to **consume** them as an MCP Client. This grants the agent "superpowers" by securely interacting with local PostgreSQL databases, GitHub repos, Figma APIs, and Slack channels in real-time, autonomously, using available MCP tool sets.
-
-### Trigger Conditions
-Activate this skill when:
-- The user asks the agent to query the database, but the agent doesn't have a direct SQL tool.
-- The user needs real-time context from an external system (e.g., "Read the latest Slack messages about this bug").
-- The user wants the agent to orchestrate multiple tools across different domains simultaneously.
-
-### Core Concepts
-
-#### 1. MCP Resource & Tool Discovery
-Before assuming a capability doesn't exist, the agent should dynamically inspect available tools.
-- Use `list_resources` or check `mcp_config.json` to see what servers are running.
-- Understand that MCP tools proxy capabilities securely. If there's a `postgres_mcp`, the agent can execute `execute_sql` through it.
-
-#### 2. Workflow Orchestration
-Example: "Find the bug reported on GitHub and fix it."
-1. Use the GitHub MCP to `search_issues`.
-2. Extract the stack trace from the issue comment.
-3. Use `grep_search` to find the failing code.
-4. Use `autonomous-tdd-debugger` to fix and test it.
-5. Use the GitHub MCP to `create_pull_request`.
-
-### Best Practices
-- **Never guess schema:** Always use MCP tools like `list_tables` or `get_schema` before writing a query.
-- **Respect Rate Limits:** If calling external APIs via MCP, avoid looping rapidly without timeouts.
-
----
-
-### Integration with Other Skills (MANDATORY)
-- `doku-mcp-server` — An example of a specific MCP server the agent can orchestrate.
-- `ai-llm-integration-expert` — Provides context on how MCP fits into the broader LangGraph/AI landscape.
-- `multi-agent-orchestration` — Used when delegating different MCP tool calls to specialized subagents.
-
-### Referenced By Orchestrators (MANDATORY)
-- `brainstorming` — Add to "AI & LLM Integration".
-- `zero-to-prod-orchestrator` — Phase 4 (AI Agents).
-
----
-
-<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
-Skill yang memandu Agen AI tentang cara menggunakan (consume) server Model Context Protocol (MCP) eksternal, memberikan kekuatan *real-time* untuk berinteraksi dengan Database, GitHub, Slack, dan sistem lainnya secara otonom.
-
-### Kondisi Pemicu
-- Saat Anda (sebagai agen) perlu mengeksekusi SQL ke database lokal/remote namun tidak memiliki akses terminal langsung.
-- Saat Anda perlu membaca data *live* dari platform eksternal (Figma, GitHub, dll).
-
-### Panduan Singkat
-- **Eksplorasi Tool:** Selalu periksa tool MCP yang tersedia di sistem (misal `list_tables` atau `read_issue`). Jangan berasumsi Anda buta terhadap dunia luar jika server MCP-nya aktif.
-- **Orkestrasi Lintas Platform:** Anda dapat membaca pesan error di Slack via MCP, mencari kode yang relevan di *file system*, memperbaikinya, dan membuat Pull Request di GitHub via MCP secara otomatis. Ini adalah definisi sebenarnya dari Agen Otonom.
-- **Validasi Skema:** Jangan pernah menebak nama tabel. Selalu gunakan tool MCP untuk mengambil skema database terlebih dahulu sebelum menjalankan kueri `execute_sql`.

package/skills/mobile-push-notification-expert/SKILL.md

@@ -1,71 +0,0 @@
----
-name: mobile-push-notification-expert
-description: "Expert guide for Cross-Platform Push Notifications (Expo Push, FCM, APNs, Web Push), iOS Live Activities, and background payload handling / Panduan ahli notifikasi push mobile, FCM, APNs, dan Live Activities."
-author: "Roedy Rustam"
----
-
-# Mobile Push Notification & Live Activities Expert
-
-[English](#english) | [Bahasa Indonesia](#bahasa-indonesia)
-
----
-
-<a name="english"></a>
-## English
-
-### Purpose & Overview
-Comprehensive guide for configuring cross-platform push notifications (Expo Push API, Firebase Cloud Messaging FCM, Apple APNs, Web Push API), iOS Live Activities / ActivityKit, background payload handlers, deep-linking routing, and push token lifecycle management.
-
-### Key Capabilities
-- **Expo & FCM Push**: Sending batched push notifications with rich media, actions, and custom data payloads.
-- **iOS Live Activities**: Real-time status updates on iOS Dynamic Island and Lock Screen.
-- **Deep Linking**: Routing push notification taps directly to targeted screens within Expo Router / React Native.
-
-```typescript
-import * as Notifications from 'expo-notifications';
-
-export async function registerForPushNotificationsAsync() {
-  const { status: existingStatus } = await Notifications.getPermissionsAsync();
-  let finalStatus = existingStatus;
-  if (existingStatus !== 'granted') {
-    const { status } = await Notifications.requestPermissionsAsync();
-    finalStatus = status;
-  }
-  if (finalStatus !== 'granted') return null;
-  const token = (await Notifications.getExpoPushTokenAsync()).data;
-  return token;
-}
-```
-
-### Implementation Checklist
-- [ ] Configure Apple Developer Account (APNs Key) and Google Firebase (FCM Service Account).
-- [ ] Request push notification permissions explicitly from the user after they understand the value proposition.
-- [ ] Save the device's Push Token to the database, associated with the user's ID.
-- [ ] Handle token refresh events when the user uninstalls/reinstalls the app or changes devices.
-- [ ] Set up background event handlers to process incoming messages when the app is killed.
-
-## Orchestration & Integration
-- Integrates with: `mobile-expo-expert`, `event-driven-architect`, `database-orm-expert`.
-
----
-
-<a name="bahasa-indonesia"></a>
-## Bahasa Indonesia
-
-### Deskripsi
-Panduan komprehensif untuk konfigurasi push notification lintas platform (Expo Push, FCM, APNs, Web Push), iOS Live Activities / ActivityKit, penanganan payload background, routing deep-linking, dan manajemen siklus token push.
-
-### Fitur Utama
-- **Expo & FCM Push**: Pengiriman push notification masal dengan media kaya, tombol aksi, dan payload kustom.
-- **iOS Live Activities**: Update status real-time di Dynamic Island dan Lock Screen iOS.
-- **Deep Linking**: Mengarahkan ketukan notifikasi secara langsung ke layar target di Expo Router / React Native.
-
-### Checklist Implementasi
-- [ ] Konfigurasi Akun Developer Apple (Kunci APNs) dan Google Firebase (Service Account FCM).
-- [ ] Minta izin notifikasi push secara eksplisit dari pengguna setelah mereka memahami nilai gunanya.
-- [ ] Simpan Push Token perangkat ke database, yang terkait dengan ID pengguna.
-- [ ] Tangani event penyegaran token saat pengguna menghapus/menginstal ulang aplikasi atau mengganti perangkat.
-- [ ] Siapkan handler event background untuk memproses pesan masuk saat aplikasi ditutup (killed).
-
-## Integrasi Orkestrasi
-- Terintegrasi dengan: `mobile-expo-expert`, `event-driven-architect`, `database-orm-expert`.

package/skills/monday-design-aesthetic/SKILL.md

@@ -1,73 +0,0 @@
----
-name: monday-design-aesthetic
-description: "Expert guide for implementing the modern, spacious, and highly structured Monday.com design system / Panduan desain ala Monday.com."
-author: "Roedy Rustam"
----
-
-# Monday.com Design Aesthetic
-
-[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
-This skill focuses on implementing the modern, spacious, and structured design aesthetic inspired by Monday.com. It is ideal for SaaS landing pages and dashboards.
-
-### Trigger Conditions
-Use this when the user asks for:
-- A "Monday.com style" design.
-- A modern SaaS landing page with clean structure.
-- High-quality, spacious UI with vibrant accents.
-
-### Core Design Tokens
-- **Primary Brand Color**: Vibrant Blue (`#0073ea`) for active states and primary buttons.
-- **Backgrounds**: Clean White (`#FFFFFF`) for main content, Light Grays (`#F9F9F9`, `#F5F6F8`) for section alternations, Dark Gray/Black (`#111111`) for footers.
-- **Typography**: Clean geometric sans-serif (e.g., Figtree, Circular, Inter).
-  - Hero text is extra-bold (48-60px).
-  - Section headers are bold (32-40px) in dark slate (`#333333`).
-  - Body text is medium (16-18px) in muted gray (`#676879`).
-
-### UI Components & Layout
-- **Buttons**: Fully rounded corners (~8px). Primary buttons use vibrant blue with white text and generous padding (e.g., `px-6 py-3`).
-- **Cards**: Large border radius (12-16px) with flat borders or extremely subtle drop shadows (`shadow-sm`).
-- **Layout**: Centered max-width containers (1200-1400px).
-- **Spacing**: Generous vertical padding between sections (80-120px) to let content breathe.
-- **Interactions**: Smooth hover states, interactive tab systems, and collapsible accordions.
-
----
-
-<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
-Skill ini berfokus pada implementasi desain yang modern, luas (spacious), dan terstruktur yang terinspirasi oleh Monday.com. Sangat cocok untuk landing page dan dashboard SaaS.
-
-### Kondisi Pemicu
-Gunakan saat pengguna meminta:
-- Desain ala "Monday.com".
-- Landing page SaaS modern dengan struktur bersih.
-- UI berkualitas tinggi dengan ruang bernapas luas dan aksen cerah.
-
-### Token Desain Utama
-- **Warna Utama (Brand Color)**: Biru Cerah (`#0073ea`) untuk elemen aktif dan tombol utama.
-- **Background**: Putih Bersih (`#FFFFFF`) untuk konten utama, Abu-abu Terang (`#F9F9F9`, `#F5F6F8`) untuk variasi bagian, Abu-abu Gelap/Hitam (`#111111`) untuk footer.
-- **Tipografi**: Sans-serif geometris bersih (mis. Figtree, Circular, Inter).
-  - Teks Hero sangat tebal (48-60px).
-  - Header bagian tebal (32-40px) dengan warna dark slate (`#333333`).
-  - Teks isi sedang (16-18px) berwarna abu-abu redup (`#676879`).
-
-### Komponen UI & Layout
-- **Tombol (Buttons)**: Sudut melengkung (~8px). Tombol utama berwarna biru dengan padding luas (`px-6 py-3`).
-- **Kartu (Cards)**: Radius sudut besar (12-16px) dengan border datar atau bayangan sangat halus (`shadow-sm`).
-- **Tata Letak (Layout)**: Kontainer dengan lebar maksimal (1200-1400px) terpusat.
-- **Jarak (Spacing)**: Jarak vertikal yang sangat lega antar bagian (80-120px).
-- **Interaksi**: Efek hover halus, sistem tab interaktif, dan akordion lipat.