vibes-plug 2.11.0 → 3.9.0

package/skills/self-evolving-memory-graph/SKILL.md

@@ -1,91 +0,0 @@
----
-name: self-evolving-memory-graph
-description: "Grants the AI long-term episodic memory. The agent autonomously documents the user's coding preferences, past mistakes to avoid, and architectural decisions into a persistent learning graph."
-author: "Roedy Rustam"
----
-
-# Self-Evolving Memory Graph (Episodic Memory)
-
-[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
-Claude forgets everything once a chat is cleared, and its "Project Knowledge" requires manual human updating. This skill gives Antigravity the "superpower" of continuous, autonomous self-improvement. The agent actively listens for user corrections, stylistic preferences, and hard-learned debugging lessons, writing them into a persistent `LEARNING_GRAPH.md` (or `.agents/LEARNING.md`) file. The agent gets smarter and more aligned with the user over time.
-
-### Trigger Conditions
-Activate this skill when:
-- The user corrects your code (e.g., "Don't use `any`, use `unknown`", or "Always use Arrow functions").
-- You just spent a long time fixing a very complex bug.
-- The user says "Remember this for the future."
-
-### Core Concepts
-
-#### 1. Memory Encoding
-Whenever a hard lesson is learned or a strong user preference is stated, do not just say "I will remember that." You must physically write it down.
-Use the `multi_replace_file_content` or `write_to_file` tool to append the lesson to the memory file.
-
-#### 2. Memory Format (`LEARNING_GRAPH.md`)
-```markdown
-# 🧠 Self-Evolving Memory Graph
-
-## User Stylistic Preferences
-- [2026-08-12] Always use `Tailwind v4 @theme` variables instead of arbitrary values like `text-[#ff0000]`.
-- [2026-08-12] Prefer functional components with `const` over `function` declarations.
-
-## Hard-Learned Lessons (Avoid these mistakes)
-- [2026-08-11] Supabase RLS policies: Never use `auth.uid()` in a `FOR ALL` policy without checking role claims. It caused an infinite recursion bug in `users` table.
-
-## Architectural Decisions
-- [2026-08-10] State Management: We exclusively use `Zustand` for global state. Do not suggest Redux.
-```
-
-#### 3. Memory Retrieval
-Ensure `session-context-loader` is configured to read this memory file at the start of every new chat session. 
-
-#### 4. Cross-Project Episodic Memory (Global Context)
-- **Continuous Capture**: For complex architectural decisions or bug fixes that span beyond a single project, extract the root cause and solution into a global knowledge graph (e.g., `~/.gemini/knowledge` or equivalent `<appDataDir>/knowledge` KI system).
-- **Contextual Retrieval**: On new sessions, search the global context directory for similar past issues before diving into complex bugs.
-- **Synthesis & Injection**: Inject 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."*
-
----
-
-### Integration with Other Skills (MANDATORY)
-- `session-context-loader` — Essential for loading the `LEARNING_GRAPH.md` when a new session starts.
-- `project-context-mapper` — The context map tracks *where* things are; the memory graph tracks *how* and *why* things are built.
-
-### Referenced By Orchestrators (MANDATORY)
-- `brainstorming` — Add to "Discovery & Audit".
-- `zero-to-prod-orchestrator` — Phase 1 (Discovery & Architecture).
-
----
-
-<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
-Claude melupakan segalanya saat sesi chat baru dimulai. Skill ini memberi Anda "kekuatan super" berupa *Ingatan Jangka Panjang* yang berevolusi sendiri. Agen secara aktif mencatat preferensi koding pengguna, pelajaran dari *bug* yang sulit dipecahkan, dan keputusan arsitektur ke dalam file persisten `LEARNING_GRAPH.md`. 
-
-### Kondisi Pemicu
-- Saat pengguna mengoreksi gaya koding Anda (misal: "Gunakan bahasa Indonesia baku", "Jangan pakai `var`").
-- Setelah Anda berhasil memecahkan *bug* yang menghabiskan waktu lama.
-- Saat pengguna berkata "Ingat ini untuk proyek ke depannya."
-
-### Panduan Singkat
-- **Jangan Hanya Berjanji:** Jika pengguna mengoreksi Anda, jangan sekadar menjawab "Baik, saya akan ingat." LLM tidak punya ingatan bawaan antar-sesi. Anda **wajib** menulis koreksi tersebut ke dalam file `LEARNING_GRAPH.md` di folder `.agents/` atau direktori *root*.
-- **Kategorisasi Ingatan:** Pisahkan ingatan menjadi: Preferensi Gaya (*Style*), Pelajaran Berharga (*Lessons Learned*), dan Keputusan Arsitektur (*Decisions*).
-- **Semakin Lama Semakin Pintar:** Dengan membaca file ini di awal setiap percakapan, Anda tidak akan pernah mengulangi kesalahan yang sama dua kali.
-
-### Memori Episodik Lintas-Proyek (Konteks Global)
-- **Penangkapan Berkelanjutan**: Untuk bug yang rumit dan pola arsitektur tingkat lanjut, ekstrak solusi ke dalam grafik pengetahuan global (misal: `~/.gemini/knowledge`).
-- **Pencarian Kontekstual**: Sebelum memecahkan masalah kompleks baru, cari direktori konteks global untuk kasus serupa.
-- **Sintesis & Injeksi**: Secara proaktif sebutkan: *"Saya ingat kita menyelesaikan ini di Proyek X dengan cara Y, saya akan menerapkannya di sini."*

package/skills/session-context-loader/SKILL.md

@@ -1,83 +0,0 @@
----
-name: session-context-loader
-description: "Automatically loads and learns project context (Tech Stack, PRD, Roadmap, Blueprint) at the start of every new conversation session to ensure focused and directed development / Otomatis memuat dan mempelajari konteks proyek (Tech Stack, PRD, Roadmap, Blueprint) di awal setiap sesi percakapan baru untuk memastikan pengembangan yang terarah dan fokus."
-author: "Roedy Rustam"
----
-
-# Session Context Loader
-
-[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 ensures that the AI agent is always aligned with the project's core documentation. At the beginning of every new conversation session, it automatically searches for and reads essential project context files (Tech Stack, PRD, Roadmap, Blueprint). This guarantees that development remains focused, directed, and strictly adheres to established requirements and architectural decisions.
-
-### Trigger Conditions
-Activate this skill IMMEDIATELY when:
-- It is the very first message of a new conversation session.
-- The user says "start session", "initialize project", or "load context".
-- The AI realizes it lacks the high-level context of the current repository.
-
-### Execution Protocol
-
-When triggered, you MUST perform the following steps before answering the user's primary request or writing any code:
-
-1. **Locate Key Documentation Files:**
-   Use your file search tools (`list_dir`, `grep_search`, or `view_file`) to look for the following files in the project root or `.docs/` folder:
-   - `PRD.md` (Product Requirements Document)
-   - `ROADMAP.md` or `ROADMAP.txt`
-   - `BLUEPRINT.md` or `ARCHITECTURE.md`
-   - `TECH_STACK.md`, `package.json`, `go.mod`, `Cargo.toml`, or `requirements.txt` (to identify the tech stack)
-
-2. **Read and Internalize Context:**
-   - Read the contents of the found files.
-   - Understand the project's primary goal, current phase in the roadmap, architectural constraints (blueprint), and the specific tech stack being used.
-
-3. **Acknowledge and Align:**
-   - Briefly acknowledge to the user that the project context has been loaded successfully.
-   - State the current Tech Stack and the immediate goal based on the Roadmap/PRD.
-   - Proceed with addressing the user's actual request using the newly loaded context.
-
----
-
-<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 memastikan bahwa agen AI selalu selaras dengan dokumentasi inti proyek. Di awal setiap sesi percakapan baru, agen akan secara otomatis mencari dan membaca file konteks proyek esensial (Tech Stack, PRD, Roadmap, Blueprint). Ini menjamin bahwa pengembangan proyek aplikasi tetap lebih terarah, fokus, dan sangat mematuhi persyaratan serta keputusan arsitektur yang telah ditetapkan.
-
-### Kondisi Pemicu
-Aktifkan skill ini SEGERA ketika:
-- Ini adalah pesan pertama dari sesi percakapan baru.
-- Pengguna berkata "mulai sesi", "inisialisasi proyek", atau "muat konteks".
-- AI menyadari bahwa ia kekurangan konteks tingkat tinggi dari repositori saat ini.
-
-### Protokol Eksekusi
-
-Saat dipicu, Anda HARUS melakukan langkah-langkah berikut sebelum menjawab permintaan utama pengguna atau menulis kode apa pun:
-
-1. **Temukan File Dokumentasi Kunci:**
-   Gunakan alat pencarian file Anda (`list_dir`, `grep_search`, atau `view_file`) untuk mencari file berikut di root proyek atau folder `.docs/`:
-   - `PRD.md` (Product Requirements Document)
-   - `ROADMAP.md` atau `ROADMAP.txt`
-   - `BLUEPRINT.md` atau `ARCHITECTURE.md`
-   - `TECH_STACK.md`, `package.json`, `go.mod`, `Cargo.toml`, atau `requirements.txt` (untuk mengidentifikasi tech stack)
-
-2. **Baca dan Pahami Konteks:**
-   - Baca isi dari file-file yang ditemukan.
-   - Pahami tujuan utama proyek, fase saat ini di roadmap, batasan arsitektur (blueprint), dan tech stack spesifik yang digunakan.
-
-3. **Konfirmasi dan Selaraskan:**
-   - Berikan konfirmasi singkat kepada pengguna bahwa konteks proyek telah berhasil dimuat.
-   - Sebutkan Tech Stack saat ini dan tujuan langsung berdasarkan Roadmap/PRD.
-   - Lanjutkan dengan menjawab permintaan pengguna yang sebenarnya menggunakan konteks yang baru dimuat.

package/skills/session-handoff-resume/SKILL.md

@@ -1,164 +0,0 @@
----
-name: session-handoff-resume
-description: "Skill to save ultra-compact project checkpoints and seamlessly resume work across accounts or new chat sessions with minimum token consumption / Skill untuk menyimpan checkpoint proyek yang super ringkas dan melanjutkan pekerjaan secara efisien saat ganti akun/sesi tanpa boros token."
-author: "Roedy Rustam"
----
-
-# Session Handoff & Resume (2026 — Cross-Model Edition)
-
-[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
-Saves ultra-compact project checkpoints and enables seamless work resumption across new chat sessions, different accounts, or different AI models (Gemini, Claude, GPT). Designed for minimum token consumption while preserving full context needed for continuation.
-
-### Trigger Conditions
-- Session is running very long and context window is nearly exhausted.
-- User wants to switch to a new chat session or different AI model.
-- User wants to save progress before closing and resume later.
-- User says "save checkpoint", "handoff", "save progress", "resume later".
-
-### Checkpoint Format (Ultra-Compact)
-
-When creating a checkpoint, output a compact YAML block under 200 tokens:
-
-```yaml
-# CHECKPOINT — [Project Name] — [Date]
-project: "[Project Name]"
-goal: "[One-line goal of the current session]"
-status: "[brief status: e.g., '60% — backend API done, frontend in progress']"
-stack: "[e.g., Next.js 15 + Hono + Supabase + Drizzle]"
-last_completed:
-  - "[Most recent task completed]"
-  - "[Second most recent]"
-next_tasks:
-  - "[Immediate next task]"
-  - "[Following task]"
-  - "[Following task]"
-blockers: "[Any known blockers or pending decisions, or 'none']"
-key_files:
-  - "[path/to/critical/file.ts]"
-  - "[path/to/another/file.ts]"
-env_needed: "[List of env vars needed, e.g., SUPABASE_URL, STRIPE_KEY]"
-notes: "[Any critical context that doesn't fit above]"
-```
-
-### Cross-Model Handoff Protocol (2026)
-
-Different AI models interpret context differently. Use this universal handoff prompt:
-
-```markdown
-## RESUME CONTEXT — [Project Name]
-
-You are resuming work on [Project Name]. Read this context carefully before taking any action.
-
-**Goal**: [One-sentence project goal]
-**Current Status**: [What's been done, what's pending]
-**Tech Stack**: [Stack details]
-**Repository**: [path or URL if available]
-
-**Completed**:
-- ✅ [Done item 1]
-- ✅ [Done item 2]
-
-**Next Tasks** (in priority order):
-1. [ ] [Immediate next task — be specific]
-2. [ ] [Second task]
-3. [ ] [Third task]
-
-**Critical Files to Read First**:
-- [file path] — [why it's critical]
-- [file path] — [why it's critical]
-
-**Known Constraints**:
-- [Constraint 1, e.g., "Use pnpm, not npm"]
-- [Constraint 2, e.g., "Admin panel must be on admin.domain.com"]
-
-**Do NOT**:
-- [Something the previous session explicitly avoided]
-- [Another anti-pattern to avoid]
-
-Start by reading the critical files listed above, then confirm you understand the current state before proceeding.
-```
-
-### Checkpoint Storage Locations
-
-| Destination | Use When |
-|---|---|
-| `CHECKPOINT.md` in project root | Primary — version-controlled |
-| `.agents/CHECKPOINT.md` | Alternative — agents-specific dir |
-| Copied to clipboard | Quick cross-session handoff |
-| Supabase notes table | Cloud-synced across devices |
-
-### Resume Protocol (For New Session)
-When the user provides a checkpoint to resume from:
-1. **Read all key files** listed in the checkpoint.
-2. **Verify current state** matches the checkpoint (check git status, recent commits).
-3. **Confirm understanding** — briefly state what you're resuming and what the first task is.
-4. **Proceed immediately** — don't ask unnecessary questions.
-
-### Automatic Checkpoint Triggers
-Proactively offer to create a checkpoint when:
-- User has been working for > 30 messages in a session.
-- The context window is > 70% consumed.
-- A major milestone is completed (e.g., "backend API is fully done").
-- The user says "I'll continue later".
-
----
-
-<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
-Menyimpan checkpoint proyek yang ultra-ringkas dan memungkinkan kelanjutan pekerjaan yang mulus di sesi chat baru, akun yang berbeda, atau model AI yang berbeda (Gemini, Claude, GPT). Dirancang untuk konsumsi token minimum sambil mempertahankan konteks penuh yang diperlukan untuk kelanjutan.
-
-### Kondisi Pemicu
-- Sesi berjalan sangat lama dan context window hampir habis.
-- Pengguna ingin beralih ke sesi chat baru atau model AI yang berbeda.
-- Pengguna ingin menyimpan progres sebelum menutup dan melanjutkan nanti.
-- Pengguna berkata "simpan checkpoint", "handoff", "simpan progres", "lanjut nanti".
-
-### Format Checkpoint (Ultra-Ringkas)
-
-Saat membuat checkpoint, keluarkan blok YAML ringkas di bawah 200 token dengan field: `project`, `goal`, `status`, `stack`, `last_completed`, `next_tasks`, `blockers`, `key_files`, `env_needed`, `notes`.
-
-### Protokol Handoff Lintas-Model (2026)
-
-Model AI yang berbeda menginterpretasikan konteks secara berbeda. Gunakan prompt handoff universal saat berpindah antar model (Gemini → Claude → GPT):
-- Sertakan goal satu kalimat, status saat ini, stack, daftar tugas yang selesai (✅), dan tugas berikutnya yang diprioritaskan.
-- Sertakan file kritis yang harus dibaca terlebih dahulu oleh model baru.
-- Sertakan kendala yang diketahui dan daftar "Jangan Lakukan".
-- Minta model baru untuk mengkonfirmasi pemahaman sebelum melanjutkan.
-
-### Lokasi Penyimpanan Checkpoint
-
-| Tujuan | Gunakan Saat |
-|---|---|
-| `CHECKPOINT.md` di root proyek | Utama — dikontrol versi |
-| `.agents/CHECKPOINT.md` | Alternatif — direktori agen |
-| Disalin ke clipboard | Handoff lintas sesi cepat |
-| Tabel catatan Supabase | Tersinkronisasi cloud antar perangkat |
-
-### Protokol Resume (Untuk Sesi Baru)
-Saat pengguna memberikan checkpoint untuk dilanjutkan:
-1. **Baca semua file kritis** yang tercantum dalam checkpoint.
-2. **Verifikasi status saat ini** cocok dengan checkpoint (periksa git status, commit terbaru).
-3. **Konfirmasi pemahaman** — nyatakan singkat apa yang dilanjutkan dan apa tugas pertama.
-4. **Lanjutkan segera** — jangan ajukan pertanyaan yang tidak perlu.
-
-### Pemicu Checkpoint Otomatis
-Tawarkan secara proaktif untuk membuat checkpoint saat:
-- Pengguna telah bekerja lebih dari 30 pesan dalam satu sesi.
-- Context window > 70% terpakai.
-- Milestone besar selesai.
-- Pengguna berkata "saya akan lanjutkan nanti".

package/skills/skill-baru/SKILL.md

@@ -1,178 +0,0 @@
----
-name: skill-baru
-description: "Comprehensive template for creating new vibes-plug skills with proper structure, trigger conditions, and bilingual support / Template komprehensif untuk membuat skill vibes-plug baru dengan struktur yang tepat, kondisi pemicu, dan dukungan bilingual."
-author: "Roedy Rustam"
----
-
-# [Skill Name] — vibes-plug Skill Template
-
-[English](#english) | [Bahasa Indonesia](#bahasa-indonesia)
-
----
-
-> **HOW TO USE THIS TEMPLATE**
-> 1. Copy this entire folder (`skill-baru/`) and rename it using kebab-case (e.g., `my-new-skill/`).
-> 2. Replace all placeholder text marked with `[...]` brackets.
-> 3. Update the frontmatter `name` and `description` fields above.
-> 4. Delete this instruction block before publishing.
-> 5. Add your skill to the `brainstorming` orchestration matrix if it belongs to a domain.
-
----
-
-<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
-[One paragraph describing the purpose and scope of this skill. Be specific about what problems it solves and what technology versions it targets.]
-
-Example: *"Expert guide for [Technology/Domain] (v[X.Y]+). Covers [feature A], [feature B], [pattern C], and [best practice D] for production-grade TypeScript/JavaScript applications."*
-
-### Trigger Conditions
-Activate this skill when the user is:
-- [Trigger scenario 1 — be specific, e.g., "Writing X with framework Y"]
-- [Trigger scenario 2]
-- [Trigger scenario 3]
-- [Trigger scenario 4]
-
----
-
-### Core Concepts
-
-#### [Concept 1 — e.g., "Architecture Overview"]
-[Explain the foundational concept. Use tables for comparisons, bullet points for lists, and code blocks for examples.]
-
-```typescript
-// [Language] — [What this code demonstrates]
-// Replace this block with a real, runnable code example.
-const example = {
-  field: 'value',
-};
-```
-
-#### [Concept 2 — e.g., "Selection Guide"]
-
-| Criteria | Option A | Option B | Option C |
-|---|---|---|---|
-| [Criterion 1] | [Value] | [Value] | [Value] |
-| [Criterion 2] | [Value] | [Value] | [Value] |
-| **Best For** | [Use case] | [Use case] | [Use case] |
-
-**Recommendation:** [State a clear default recommendation with rationale.]
-
----
-
-### [Main Topic Section 1 — e.g., "Setup & Configuration"]
-
-#### [Sub-topic 1.1]
-```typescript
-// Example: Configuration or setup code
-```
-
-#### [Sub-topic 1.2]
-```typescript
-// Example: Core usage pattern
-```
-
----
-
-### [Main Topic Section 2 — e.g., "Best Practices"]
-
-1. **[Practice 1]:** [Explanation]
-2. **[Practice 2]:** [Explanation]
-3. **[Practice 3]:** [Explanation]
-4. **[Practice 4]:** [Explanation]
-
----
-
-### Common Pitfalls to Avoid
-
-| Anti-Pattern | Problem | Correct Approach |
-|---|---|---|
-| [Bad practice 1] | [Why it's bad] | [What to do instead] |
-| [Bad practice 2] | [Why it's bad] | [What to do instead] |
-| [Bad practice 3] | [Why it's bad] | [What to do instead] |
-
----
-
-### Integration with Other Skills (MANDATORY)
-
-> ⚠️ **Every skill MUST list at least 3 cross-references.** No skill should exist in isolation.
-
-This skill works best when combined with:
-- `[skill-name]` — [Why and when to combine]
-- `[skill-name]` — [Why and when to combine]
-- `[skill-name]` — [Why and when to combine]
-
-### Referenced By Orchestrators (MANDATORY)
-
-> ⚠️ **Update the orchestrator skills below when creating a new domain skill.**
-
-This skill should be referenced by the following orchestrators:
-- `brainstorming` — Add to the "[Domain]" row in the Skill Integration & Orchestration Matrix
-- `zero-to-prod-orchestrator` — Add to Phase [N]: [Phase Name]
-- `production-ready-hardener` — Add to Phase [N] if relevant to pre-launch audit
-
----
-
-<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
-[Satu paragraf menjelaskan tujuan dan ruang lingkup skill ini. Spesifik tentang masalah apa yang dipecahkan dan versi teknologi apa yang ditargetkan.]
-
-Contoh: *"Panduan ahli untuk [Teknologi/Domain] (v[X.Y]+). Mencakup [fitur A], [fitur B], [pola C], dan [praktik terbaik D] untuk aplikasi TypeScript/JavaScript berkualitas produksi."*
-
-### Kondisi Pemicu
-Aktifkan skill ini ketika pengguna sedang:
-- [Skenario pemicu 1 — spesifik, misal: "Menulis X dengan framework Y"]
-- [Skenario pemicu 2]
-- [Skenario pemicu 3]
-- [Skenario pemicu 4]
-
-### Panduan Singkat
-
-[Ringkasan praktis berisi poin-poin utama yang harus diketahui. Merujuk ke bagian English untuk detail teknis dan contoh kode lengkap.]
-
-- **[Prinsip 1]:** [Penjelasan singkat]
-- **[Prinsip 2]:** [Penjelasan singkat]
-- **[Prinsip 3]:** [Penjelasan singkat]
-- **[Prinsip 4]:** [Penjelasan singkat]
-
-### Integrasi dengan Skill Lain (WAJIB)
-
-> ⚠️ **Setiap skill WAJIB mencantumkan minimal 3 referensi silang.** Tidak ada skill yang boleh berdiri sendiri.
-
-Skill ini bekerja paling baik dikombinasikan dengan:
-- `[nama-skill]` — [Mengapa dan kapan dikombinasikan]
-- `[nama-skill]` — [Mengapa dan kapan dikombinasikan]
-- `[nama-skill]` — [Mengapa dan kapan dikombinasikan]
-
-### Direferensikan oleh Orchestrator (WAJIB)
-
-Skill ini harus direferensikan oleh orchestrator berikut:
-- `brainstorming` — Tambahkan ke baris "[Domain]" di Matriks Orkestrasi
-- `zero-to-prod-orchestrator` — Tambahkan ke Fase [N]
-- `production-ready-hardener` — Tambahkan ke Fase [N] jika relevan
-
----
-
-## Checklist Sebelum Mempublikasikan Skill Ini
-
-- [ ] Frontmatter `name` dan `description` sudah diisi (bilingual EN/ID).
-- [ ] Semua teks `[...]` placeholder sudah diganti.
-- [ ] Ada minimal 2 contoh kode yang nyata dan dapat dijalankan.
-- [ ] Ada tabel perbandingan atau selection guide jika relevan.
-- [ ] Ada bagian "Common Pitfalls" atau anti-pattern.
-- [ ] **Bagian "Integration with Other Skills" mencantumkan minimal 3 skill.**
-- [ ] **Bagian "Referenced By Orchestrators" sudah diisi.**
-- [ ] Bagian Bahasa Indonesia sudah diterjemahkan dengan benar.
-- [ ] Blok instruksi ini sudah dihapus.
-- [ ] **Skill sudah ditambahkan ke matriks orkestrasi `brainstorming`.**
-- [ ] **Skill sudah ditambahkan ke fase yang relevan di `zero-to-prod-orchestrator`.**
-- [ ] `BLUEPRINT.md` sudah diperbarui dengan deskripsi skill baru.

package/skills/supabase-migration/SKILL.md

@@ -1,91 +0,0 @@
----
-name: supabase-migration
-description: "A skill to create or apply a Supabase database migration / Kemampuan untuk membuat atau menerapkan migrasi database Supabase."
-author: "Roedy Rustam"
----
-
-# Supabase Migration Skill
-
-[English](#english) | [Bahasa Indonesia](#bahasa-indonesia)
-
----
-
-<a name="english"></a>
-## English
-
-### Description
-When the user asks to create or apply a database migration for Supabase, follow these instructions:
-
-### Instructions
-1. **Check Environment**: Ensure `supabase/migrations` directory exists. Run `list_dir` on it if needed.
-2. **Review Available MCP Commands**: Utilize the Supabase MCP integration.
-   - For listing existing migrations, use `mcp_supabase-mcp-server_list_migrations` with `project_id`.
-   - Before executing migration queries on the server directly, confirm the SQL is correct.
-3. **Execute Command**: 
-   - Write the SQL script to a local migration file located in `supabase/migrations/` using `write_to_file`. Use standard timestamps or `supabase migration new` command to get the filename.
-   - Run `npx supabase migration up` to test locally or use the remote MCP `apply_migration` if the user wants it applied remotely.
-4. **Final Step**: Confirm with the user that the migration successfully completed.
-
-### Implementation Checklist
-- [ ] Generate a new migration file: `npx supabase migration new [name]`
-- [ ] Write raw SQL in the generated migration file (DDL and DML).
-- [ ] Test the migration locally: `npx supabase db reset` or `npx supabase migration up`.
-- [ ] If using RLS, explicitly add policies to the new tables.
-- [ ] Commit the migration file to version control.
-
-### Example: Supabase Migration Command Flow
-```bash
-# 1. Create a new migration file
-npx supabase migration new create_users_table
-
-# 2. Write SQL to supabase/migrations/<timestamp>_create_users_table.sql
-# 3. Apply to local database
-npx supabase migration up
-
-# 4. Apply to remote production database
-npx supabase db push
-```
-
-## Orchestration & Integration
-- Integrates with: `supabase-security-expert`, `database-orm-expert`, `ci-cd-devops-architect`.
-
----
-
-<a name="bahasa-indonesia"></a>
-## Bahasa Indonesia
-
-### Deskripsi
-Ketika pengguna meminta untuk membuat atau menerapkan migrasi database untuk Supabase, ikuti instruksi berikut:
-
-### Instruksi
-1. **Periksa Lingkungan**: Pastikan direktori `supabase/migrations` ada. Jalankan `list_dir` jika diperlukan.
-2. **Tinjau Perintah MCP yang Tersedia**: Manfaatkan integrasi Supabase MCP.
-   - Untuk mencantumkan migrasi yang ada, gunakan `mcp_supabase-mcp-server_list_migrations` dengan `project_id`.
-   - Sebelum menjalankan kueri migrasi di server secara langsung, pastikan kode SQL-nya sudah benar.
-3. **Jalankan Perintah**:
-   - Tulis skrip SQL ke file migrasi lokal yang terletak di `supabase/migrations/` menggunakan `write_to_file`. Gunakan timestamp standar atau perintah `supabase migration new` untuk mendapatkan nama file.
-   - Jalankan `npx supabase migration up` untuk menguji secara lokal atau gunakan MCP remote `apply_migration` jika pengguna ingin menerapkannya secara remote.
-4. **Langkah Terakhir**: Konfirmasikan dengan pengguna bahwa migrasi telah berhasil diselesaikan.
-
-### Checklist Implementasi
-- [ ] Buat file migrasi baru: `npx supabase migration new [nama]`
-- [ ] Tulis SQL mentah di file migrasi yang dihasilkan (DDL dan DML).
-- [ ] Uji migrasi secara lokal: `npx supabase db reset` atau `npx supabase migration up`.
-- [ ] Jika menggunakan RLS, tambahkan kebijakan secara eksplisit ke tabel baru.
-- [ ] Commit file migrasi ke sistem kontrol versi.
-
-### Contoh: Alur Perintah Migrasi Supabase
-```bash
-# 1. Buat file migrasi baru
-npx supabase migration new create_users_table
-
-# 2. Tulis SQL ke supabase/migrations/<timestamp>_create_users_table.sql
-# 3. Terapkan ke database lokal
-npx supabase migration up
-
-# 4. Terapkan ke database remote produksi
-npx supabase db push
-```
-
-## Integrasi Orkestrasi
-- Terintegrasi dengan: `supabase-security-expert`, `database-orm-expert`, `ci-cd-devops-architect`.