vibes-plug 2.5.0 → 2.14.1

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

@@ -1,43 +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 applications powered by serverless and edge databases — Neon Serverless Postgres, Cloudflare D1 (SQLite at Edge), Turso (libsql distributed SQLite), Upstash Serverless Redis & Vector, HTTP connection pooling via Hyperdrive/Prisma Accelerate, and zero-cold-start strategies.
-
-### Key Capabilities
-- **Neon & Cloudflare D1**: Serverless autoscaling Postgres with instant branching and distributed edge SQLite.
-- **Connection Pooling**: WebSocket/HTTP proxy pooling (Neon Serverless Driver, Upstash Redis over HTTP) for edge workers without TCP pool exhaustion.
-- **Embedded Replicas**: Syncing 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 });
-```
-
----
-
-<a name="bahasa-indonesia"></a>
-## Bahasa Indonesia
-
-### Deskripsi
-Praktik terbaik membangun aplikasi latensi rendah dengan database serverless dan edge — Neon Serverless Postgres, Cloudflare D1 (SQLite di Edge), Turso (libsql terdistribusi), Upstash Serverless Redis & Vector, connection pooling HTTP/WebSocket, dan mitigasi cold-start.
-
-### Fitur Utama
-- **Neon & Cloudflare D1**: Serverless Postgres autoscaling dengan branching instan dan distributed edge SQLite.
-- **Connection Pooling**: Proxy pooling HTTP/WebSocket untuk edge worker tanpa risiko kehabisan koneksi TCP.
-- **Embedded Replicas**: Sinkronisasi read-replica SQLite di edge dengan database utama untuk query di bawah 10ms.

package/skills/hyper-context-synthesizer/SKILL.md

@@ -1,55 +0,0 @@
----
-name: hyper-context-synthesizer
-description: "Cross-project episodic memory. Synthesizes bug fixes and architectural choices from previous tasks to bypass zero-shot limitations / Memori episodik lintas proyek. Menyintesis perbaikan bug dan pilihan arsitektur dari tugas sebelumnya untuk melampaui batasan zero-shot."
-author: vibes-plug-swarm
----
-
-# Hyper-Context Synthesizer (Cross-Project Episodic Memory)
-
-[English](#english) | [Bahasa Indonesia](#bahasa-indonesia)
-
----
-
-<a name="english"></a>
-## English
-
-### Description
-Transforms the AI from a stateless engine into a senior teammate with persistent, cross-project memory. It maintains a centralized vector or semantic knowledge graph (in the user's root environment) of complex bug fixes, architectural decisions, and personal coding styles across ALL projects the user has worked on. When a new project encounters a familiar problem, the synthesizer retrieves the exact context and applies the historical fix, bypassing zero-shot limitations and repetitive prompt engineering.
-
-### Trigger Conditions
-- During Phase 1 (Discovery & PRD) to load historical preferences and avoid past mistakes.
-- When facing complex, obscure bugs that were solved in a different repository or earlier conversation.
-- When standard coding attempts fail and require deep historical experiential retrieval.
-
-### Operating Protocol
-1. **Continuous Capture**: When a difficult problem is solved, it extracts the root cause, solution code, and rationale, storing it in the global knowledge graph.
-2. **Contextual Retrieval**: On new sessions, it queries the memory graph against the current task intent.
-3. **Synthesis & Injection**: Injects the historical context directly into the current execution loop, stating explicitly: *"I remember we solved this architectural issue in Project X using technique Y. Applying the same proven pattern here."*
-
-## Orchestration & Integration
-- Enhances `self-evolving-memory-graph` by elevating it from single-repo memory to cross-workspace episodic memory.
-- Feeds crucial background context into `brainstorming` and `zero-to-prod-orchestrator` during the ideation phase.
-- Prevents recurring regressions during `autonomous-tdd-debugger` loops.
-
----
-
-<a name="bahasa-indonesia"></a>
-## Bahasa Indonesia
-
-### Deskripsi
-Mengubah AI dari mesin yang melupakan konteks (*stateless*) menjadi rekan setim senior yang memiliki memori episodik lintas-proyek yang persisten. Agen ini memelihara grafik pengetahuan semantik atau vektor terpusat (di lingkungan root pengguna) tentang perbaikan bug yang kompleks, keputusan arsitektural, dan gaya penulisan kode pribadi di SELURUH proyek yang pernah dikerjakan pengguna. Ketika sebuah proyek baru menghadapi masalah yang tidak asing, agen ini akan mengambil konteks yang tepat dan menerapkan perbaikan historis tersebut, melampaui batasan *zero-shot* dan meminimalisir manipulasi *prompt* yang berulang.
-
-### Kondisi Pemicu
-- Saat Fase 1 (Penemuan & PRD) untuk memuat preferensi historis dan menghindari kesalahan di masa lalu.
-- Ketika menghadapi bug yang kompleks dan tidak lazim yang pernah diselesaikan di repositori lain atau di percakapan sebelumnya.
-- Ketika upaya koding standar gagal dan membutuhkan pencarian pengalaman historis yang mendalam.
-
-### Protokol Operasi
-1. **Penangkapan Berkelanjutan**: Ketika masalah sulit berhasil dipecahkan, agen ini mengekstrak akar masalah, kode solusi, dan alasan logisnya, lalu menyimpannya di grafik pengetahuan global.
-2. **Pencarian Kontekstual**: Pada sesi baru, ia melakukan *query* ke grafik memori berdasarkan tujuan tugas saat ini.
-3. **Sintesis & Injeksi**: Menyuntikkan konteks historis langsung ke dalam loop eksekusi saat ini, dan secara eksplisit menyatakan: *"Saya ingat kita pernah menyelesaikan masalah arsitektural ini di Proyek X menggunakan teknik Y. Saya akan menerapkan pola terbukti yang sama di sini."*
-
-## Integrasi Orkestrasi
-- Memperkuat `self-evolving-memory-graph` dengan meningkatkannya dari sekadar memori repositori tunggal menjadi memori episodik lintas-workspace.
-- Memasok konteks latar belakang krusial ke dalam `brainstorming` dan `zero-to-prod-orchestrator` selama fase ideasi.
-- Mencegah regresi berulang selama *loop* `autonomous-tdd-debugger`.

package/skills/llm-cost-arbitrage-router/SKILL.md

@@ -1,59 +0,0 @@
----
-name: llm-cost-arbitrage-router
-description: "Dynamically routes LLM calls based on cost/latency and builds semantic caching layers to reduce token burn / Mengarahkan pemanggilan LLM secara dinamis berdasarkan biaya/latensi dan membangun lapisan semantic cache untuk menekan pengeluaran token."
-author: vibes-plug-swarm
----
-
-# Predictive LLM Cost Arbitrage Router (FinOps AI Agent)
-
-[English](#english) | [Bahasa Indonesia](#bahasa-indonesia)
-
----
-
-<a name="english"></a>
-## English
-
-### Description
-An advanced FinOps architectural skill designed to prevent API cost overruns in AI applications. Instead of hardcoding a single model (e.g., GPT-4 or Claude 3.5 Sonnet) for every task, this agent builds an intelligent routing layer. It evaluates incoming prompts for complexity and dynamically routes simple queries to cheaper, faster models (e.g., Llama 3 8B, Gemini Flash) and complex reasoning tasks to frontier models. Additionally, it implements Semantic Caching (e.g., with Redis or Upstash) to serve identical or semantically similar queries without hitting the LLM provider, slashing token costs by up to 90%.
-
-### Trigger Conditions
-- When building AI-native applications, chatbots, or RAG systems.
-- During Phase 4 (Backend Architecture) when implementing external API layers.
-- When explicitly requested by the user to "optimize AI costs" or "reduce token usage."
-
-### 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.
-
-## Orchestration & Integration
-- Enhances `ai-llm-integration-expert` with enterprise-grade cost controls.
-- 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.
-
----
-
-<a name="bahasa-indonesia"></a>
-## Bahasa Indonesia
-
-### Deskripsi
-Keterampilan arsitektur *FinOps* canggih yang dirancang untuk mencegah pembengkakan biaya API pada aplikasi berbasis AI. Alih-alih menetapkan satu model secara kaku (misalnya GPT-4 atau Claude 3.5 Sonnet) untuk semua tugas, agen ini membangun lapisan *routing* yang cerdas. Agen akan mengevaluasi tingkat kerumitan setiap prompt yang masuk dan mengarahkan *query* sederhana ke model yang lebih murah dan cepat (mis. Llama 3 8B, Gemini Flash), sementara tugas penalaran kompleks diarahkan ke model raksasa (*frontier*). Selain itu, agen ini mengimplementasikan *Semantic Caching* (misal dengan Redis atau Upstash) untuk menyajikan jawaban pada *query* yang identik atau mirip secara semantik tanpa harus menghubungi penyedia LLM, memangkas biaya token hingga 90%.
-
-### Kondisi Pemicu
-- Saat membangun aplikasi AI-native, chatbot, atau sistem RAG.
-- Selama Fase 4 (Arsitektur Backend) saat mengimplementasikan lapisan API eksternal.
-- Ketika diminta secara eksplisit oleh pengguna untuk "mengoptimalkan biaya AI" atau "mengurangi penggunaan token".
-
-### 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.
-
-## Integrasi Orkestrasi
-- Memperkuat `ai-llm-integration-expert` dengan kontrol biaya skala *enterprise*.
-- 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*).

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

@@ -1,70 +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
-
-### 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
-
-### 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

@@ -1,51 +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;
-}
-```
-
----
-
-<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.

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

@@ -1,67 +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
-
-### 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
-
-### 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.

package/skills/project-context-mapper/SKILL.md

@@ -1,79 +0,0 @@
----
-name: project-context-mapper
-description: "Gives the agent a photographic memory of massive repositories. Forces the creation and maintenance of a highly compressed CONTEXT_MAP.md to prevent context exhaustion and hallucination."
-author: "Roedy Rustam"
----
-
-# Project Context Mapper (Memory Optimizer)
-
-[English](#english) | [Bahasa Indonesia](#bahasa-indonesia)
-
----
-
-<a name="english"></a>
-## English
-
-### Description
-LLMs struggle with repositories containing hundreds of files; they lose track of where things are, leading to hallucinations and excessive tool calls. This skill forces the agent to create, read, and maintain a `CONTEXT_MAP.md`—a highly compressed index of the repository's architecture, dependency graphs, and critical file locations. This acts as the agent's "photographic memory".
-
-### Trigger Conditions
-Activate this skill when:
-- The agent enters a massive, existing codebase for the first time.
-- The user complains that the AI is "editing the wrong file" or "forgetting how the app is structured."
-- Context token usage is dangerously high and needs optimization.
-
-### Core Concepts
-
-#### 1. The Context Map Format
-The agent should execute a script or traverse the directory to generate a compressed map in `CONTEXT_MAP.md` (or within `.agents/`).
-```markdown
-# CONTEXT MAP (Do not delete)
-
-## Architecture
-- Frontend: Next.js App Router (src/app)
-- Backend: Hono RPC (src/server)
-- DB: Drizzle (src/db/schema.ts)
-
-## Dependency Graph (Critical Paths)
-- `src/app/page.tsx` -> `src/components/ui/Button.tsx`
-- `src/server/routes/users.ts` -> `src/db/queries/users.ts`
-
-## State Locations
-- Global Auth: `src/store/auth.ts` (Zustand)
-```
-
-#### 2. Workflow
-1. **On Start:** The agent reads `CONTEXT_MAP.md` instead of blindly listing directories.
-2. **On Modification:** When the agent creates a new major component, route, or service, it MUST append that location to the context map.
-
-### Best Practices
-- **Keep it Ultra-Compressed:** Do not store full code in the map. Store ONLY file paths, responsibilities (1 sentence), and connections.
-- **BM25 Search First:** Before writing to the context map, consider using `grep_search` or semantic search for targeted lookups. The map is for *architectural* understanding, not exact variable finding.
-
----
-
-### Integration with Other Skills (MANDATORY)
-- `session-context-loader` — Integrates deeply to ensure the context map is loaded automatically on every new chat session.
-- `token-saver` — The map prevents the agent from reading 10 separate files just to find one function, saving massive amounts of tokens.
-- `monorepo-architect` — Essential for mapping out package boundaries in Turborepo/pnpm workspaces.
-
-### Referenced By Orchestrators (MANDATORY)
-- `brainstorming` — Add to "Discovery & Audit".
-- `zero-to-prod-orchestrator` — Phase 1 (Discovery & Architecture).
-
----
-
-<a name="bahasa-indonesia"></a>
-## Bahasa Indonesia
-
-### Deskripsi
-Kelemahan utama agen AI adalah keterbatasan jendela konteks (*context window*). Skill ini memberi agen "ingatan fotografis" dengan mewajibkannya memelihara file `CONTEXT_MAP.md`—sebuah indeks super padat yang memetakan arsitektur proyek, lokasi file penting, dan graf dependensi.
-
-### Kondisi Pemicu
-- Saat agen baru saja dimasukkan ke dalam repositori raksasa yang sudah ada (bukan dari nol).
-- Saat agen mulai salah mengedit file atau terlihat kebingungan dengan struktur folder.
-
-### Panduan Singkat
-- **Indeks Tersentralisasi:** Buat dan selalu perbarui `CONTEXT_MAP.md`. File ini berisi daftar *path* direktori krusial dan tanggung jawab masing-masing (misal: "Logic pembayaran ada di `src/lib/stripe.ts`").
-- **Ultra-Ringkas:** Jangan menaruh baris kode di dalam peta konteks ini. Hanya gunakan format *bullet points* agar konsumsi token saat dibaca sangat rendah.
-- **Baca di Awal Sesi:** Di setiap awal percakapan, agen tidak perlu lagi meraba-raba melakukan `ls` berulang kali. Cukup gunakan `view_file` pada `CONTEXT_MAP.md`, dan agen langsung mengerti seluruh topologi proyek.