vibes-plug 2.5.0 → 2.14.1

package/.claude/rules/vibes-plug-core.md

@@ -0,0 +1,32 @@
+# Vibes-Plug Core Rules (Claude)
+
+## Skill Resolution Protocol
+1. Before any task, identify relevant skills from `skills/` directory.
+2. Read the `SKILL.md` file of each relevant skill before writing code.
+3. Skills contain domain-specific patterns, best practices, and code templates — always prioritize these over generic knowledge.
+
+## Deep Reasoning (Mandatory)
+Before writing code or making architectural decisions:
+1. Analyze constraints and edge cases.
+2. Question your own assumptions — is there a more modern approach?
+3. Validate against project NFRs and best practices.
+4. Only then execute.
+
+## Code Quality Standards
+- Use modern 2026 tech stack versions: React 19, Next.js 15, Tailwind v4, TypeScript 5.8+, Node.js 24 LTS, Bun 1.2+, Python 3.14, Go 1.25+, Rust 2024.
+- Follow Clean Code, SOLID, DRY principles (see `scalability-clean-code` skill).
+- No AI slop — be imperative, direct, and token-efficient.
+
+## New Project Protocol
+When creating a new project from scratch, MUST auto-generate before any code:
+1. `PRD.md` — Product Requirements Document
+2. `ERD.md` — Entity Relationship Diagram
+3. `DOKUMENTASI.md` — Technical Documentation
+
+## Skill Registration (When Creating Skills)
+Every new `SKILL.md` must be registered in:
+1. `skills/brainstorming/SKILL.md` (Domain Matrix)
+2. `skills/zero-to-prod-orchestrator/SKILL.md` (Phase Execution)
+
+## Bilingual Support
+Skills serve English and Indonesian developers. Provide bilingual context for critical concepts.

package/.cursor/rules/vibes-plug-core.mdc

@@ -0,0 +1,51 @@
+---
+alwaysApply: true
+description: "Vibes-Plug 144+ Skills Ecosystem — Universal AI plugin for modern 2026 development"
+globs: "**/*"
+---
+
+# Vibes-Plug Core Rules
+
+## Skill Resolution Protocol
+This project uses 144+ specialized skills in the `skills/` directory. Each skill is a `SKILL.md` file.
+
+**Before any task:**
+1. Identify relevant skills from the domain table below.
+2. Read their `skills/<skill-name>/SKILL.md` file.
+3. Follow the patterns and best practices defined in the skill.
+
+## Skill Domain Map
+
+| Domain | Key Skills |
+|--------|-----------|
+| 🤖 AI & Agentic | `ai-llm-integration-expert`, `vercel-ai-sdk-expert`, `deep-research-analyst`, `synthetic-data-finetuning-expert`, `pydantic-ai-expert`, `ai-media-generation-expert`, `mcp-server-architect`, `mcp-client-orchestrator`, `vector-db-rag-expert`, `multi-agent-orchestration`, `ai-cost-token-optimizer`, `ai-prompt-engineering-expert` |
+| 🎨 Design & UI/UX | `design-system-architect`, `hig`, `ui-components-expert`, `ui-ux-pro-max`, `monday-design-aesthetic`, `visual-qa-vision-agent`, `svg-animation-motion-expert`, `data-visualization-expert`, `rich-text-editor-expert` |
+| 🖥️ Frontend | `senior-frontend`, `tailwind-expert`, `nextjs-app-router-expert`, `astro-framework-expert`, `svelte-sveltekit-expert`, `solidjs-expert`, `angular-expert`, `tanstack-query-expert`, `state-management-expert`, `vue-frontend-expert`, `performance-web-vitals`, `form-validation-expert`, `blockchain-web3-expert` |
+| 📱 Mobile & Desktop | `mobile-expo-expert`, `mobile-push-notification-expert`, `tauri-expert`, `desktop-electron-expert` |
+| ⚙️ Backend | `js-backend-expert`, `python-programming-expert`, `go-programming-expert`, `rust-programming-expert`, `typescript-expert`, `api-design-expert`, `graphql-apollo-expert`, `bun-runtime-expert`, `n8n-automation-expert`, `chatbot-messaging-expert`, `pdf-document-generation-expert` |
+| ☁️ SaaS & Cloud | `saas-transformer`, `saas-billing`, `saas-multi-tenant`, `cloud-hosting-expert`, `ci-cd-devops-architect`, `payment-gateway-expert`, `event-driven-architect`, `monorepo-architect` |
+| 🗄️ Database | `database-orm-expert`, `edge-serverless-db-expert`, `supabase-migration`, `database-migration-versioning-expert` |
+| 🔒 Security & QA | `authentication-identity-expert`, `e2e-testing-expert`, `production-ready-hardener`, `autonomous-tdd-debugger`, `zero-trust-secret-vault`, `supabase-security-expert` |
+| 🔍 SEO | `seo` |
+| 🛠️ Utilities | `brainstorming`, `prd-architect`, `auto-doc-updater`, `token-saver`, `vibe-code-gardener`, `web-scraper`, `project-context-mapper` |
+
+## Core Stack (2026 Edition)
+- **Frontend:** React 19, Next.js 15, Tailwind CSS v4, TypeScript 5.8+
+- **Backend:** Node.js 24 LTS, Bun 1.2+, Hono v4, Fastify 5, Python 3.14, Go 1.25+, Rust 2024
+- **Database:** Prisma 6, Drizzle ORM, PostgreSQL, Supabase, Neon, Turso
+- **AI/LLM:** Vercel AI SDK 5.x, MCP v1.9+, pgvector, RAG pipelines
+
+## Behavioral Rules
+1. **Deep Reasoning:** Think before acting. Analyze constraints → question assumptions → validate → execute.
+2. **No AI Slop:** Be imperative, direct, token-efficient. No "As an AI language model..." filler.
+3. **New Projects:** Auto-generate `PRD.md`, `ERD.md`, `DOKUMENTASI.md` before any code.
+4. **Bilingual:** Skills support English & Bahasa Indonesia.
+5. **Clean Code:** Follow SOLID, DRY, Clean Code principles (ref: `scalability-clean-code`).
+
+## Orchestration Flow
+1. **Plan:** `brainstorming` → `prd-architect`
+2. **Design:** `design-system-architect` → `senior-frontend` → `ui-components-expert`
+3. **Build:** `js-backend-expert` → `event-driven-architect` → `autonomous-tdd-debugger`
+4. **AI:** `ai-llm-integration-expert` → `mcp-server-architect`
+5. **SaaS:** `saas-transformer` → auto-coordinates billing, tenancy, payments
+6. **Ship:** `e2e-testing-expert` → `seo` → `production-ready-hardener`

package/.cursorrules

@@ -0,0 +1,42 @@
+# Vibes-Plug — 144+ Skills Ecosystem (v2.12.0)
+# Universal AI Plugin for Antigravity, Claude, and Cursor
+
+## About
+This project uses the vibes-plug skills ecosystem with 144+ specialized skills.
+Each skill is a `SKILL.md` file in the `skills/` directory containing domain-specific
+instructions, patterns, and best practices for the modern 2026 tech stack.
+
+## Core Stack (2026 Edition)
+- Frontend: React 19, Next.js 15, Tailwind CSS v4, TypeScript 5.8+
+- Backend: Node.js 24 LTS, Bun 1.2+, Hono v4, Fastify 5, Python 3.14, Go 1.25+, Rust 2024
+- Database: Prisma 6, Drizzle ORM, PostgreSQL, Supabase, Neon, Turso
+- AI/LLM: Vercel AI SDK 5.x, MCP v1.9+, pgvector, RAG pipelines
+
+## Mandatory Before Coding
+1. Read the relevant `skills/<skill-name>/SKILL.md` files before writing code.
+2. Think deeply before acting — analyze constraints, question assumptions, validate approach.
+3. For new projects, auto-generate: PRD.md, ERD.md, DOKUMENTASI.md.
+
+## Skill Domains
+- 🤖 AI & Agentic: ai-llm-integration-expert, vercel-ai-sdk-expert, deep-research-analyst, synthetic-data-finetuning-expert, pydantic-ai-expert, mcp-server-architect, vector-db-rag-expert, multi-agent-orchestration, graph-rag-knowledge-expert, local-slm-edge-ai-expert
+- 🎨 Design & UI/UX: design-system-architect, hig, ui-components-expert, ui-ux-pro-max
+- 🖥️ Frontend: senior-frontend, tailwind-expert, nextjs-app-router-expert, tanstack-query-expert, vue-frontend-expert
+- ⚙️ Backend: js-backend-expert, python-programming-expert, go-programming-expert, rust-programming-expert, api-design-expert
+- ☁️ SaaS & Cloud: saas-transformer, saas-billing, ci-cd-devops-architect, cloud-hosting-expert, payment-gateway-expert
+- 🗄️ Database: database-orm-expert, edge-serverless-db-expert, supabase-migration
+- 🔒 Security: authentication-identity-expert, e2e-testing-expert, production-ready-hardener, zero-trust-secret-vault
+- 🔍 SEO: seo
+- 🛠️ Utilities: brainstorming, prd-architect, auto-doc-updater, token-saver, vibe-code-gardener
+
+## Code Quality
+- Clean Code, SOLID, DRY — see `scalability-clean-code` skill.
+- No AI slop — be imperative, direct, token-efficient.
+- Bilingual support (English & Bahasa Indonesia) for all skills.
+
+## Orchestration Flow
+1. Ideation: brainstorming → prd-architect
+2. Design: design-system-architect → senior-frontend → ui-components-expert
+3. Backend: js-backend-expert → event-driven-architect → autonomous-tdd-debugger
+4. AI: ai-llm-integration-expert → mcp-server-architect
+5. SaaS: saas-transformer → saas-billing + saas-multi-tenant
+6. Launch: e2e-testing-expert → seo → production-ready-hardener

package/AGENTS.md

@@ -1,5 +1,9 @@
 # Core Rule for Vibes-Plug Agents
 
+> **🌐 Universal Compatibility:** These rules apply to ALL AI platforms using vibes-plug:
+> **Antigravity (AGY)** via `AGENTS.md` | **Claude Code** via `CLAUDE.md` + `.claude/rules/` | **Cursor IDE** via `.cursorrules` + `.cursor/rules/`
+> Each platform has its own entry point, but the core rules and 145+ skills are shared.
+
 ## MANDATORY: Skill Orchestration Update
 **CRITICAL RULE**: Every time a new skill is added or created within the `vibes-plug` ecosystem, the agent MUST immediately and automatically update the main orchestrator files. 
 
@@ -13,22 +17,48 @@ Whenever a new skill `SKILL.md` is generated, you must:
 This rule is absolute and applies to all AI agents interacting with this plugin.
 
 ## MANDATORY: Multi-Agent Orchestration & Swarm Cooperation
-**CRITICAL RULE**: When dealing with complex, multi-step tasks, the AI Agent MUST function as a Swarm Director and orchestrate multiple subagents concurrently.
+**CRITICAL RULE**: When dealing with complex, multi-step tasks, the AI Agent MUST function as a **Swarm Director** and orchestrate multiple specialized subagents concurrently.
+
+**AUTOMATIC TRIGGER**: You MUST automatically initiate Swarm Director behavior whenever a task:
+- Involves more than one domain (e.g., Frontend + Backend + Database).
+- Requires extensive research across multiple files/repositories.
+- Consists of more than three independent steps.
+- Involves high-risk architectural changes or migrations.
+*Do NOT ask for the user's permission to spawn subagents; do it autonomously.*
 
-**AUTOMATIC TRIGGER**: You MUST automatically initiate this Swarm Director behavior whenever a task involves more than one domain (e.g., Frontend + Backend), requires extensive research across multiple files, or consists of more than three independent steps. Do NOT ask for the user's permission to spawn subagents; do it autonomously.
+### Swarm Execution Topologies (2026 Edition)
+
+```
+1. FAN-OUT / FAN-IN (Parallel Research & Assembly)
+   Director ──┬──► Subagent A (Frontend / UI)   ──┐
+              ├──► Subagent B (Backend / API)    ──┼──► Synthesis & Assembly
+              └──► Subagent C (DB Schema / RLS)  ──┘
+
+2. PIPELINE SAGA (Sequential Dependent Execution)
+   Discovery ──► Foundation ──► Schema/DB ──► APIs ──► Frontend ──► QA/Hardening
+
+3. CRITIC-VALIDATOR LOOP (Zero-Tolerance Quality Gate)
+   Implementer Agent ──► Artifact/Code ──► Auditor Agent (code review/fuzzing) ──► Approved
+```
 
-1. **Decompose and Delegate**: Break down complex tasks into independent sub-tasks and delegate them to specialized subagents using `invoke_subagent`. Assign clear, specific roles to each subagent based on the specialized skills in `vibes-plug`.
+### Swarm Director Protocols
+1. **Decompose and Delegate**: Break down complex tasks into independent sub-tasks and delegate them to specialized subagents using `invoke_subagent`. Assign clear, specific roles to each subagent based on the 145+ specialized skills in `vibes-plug`.
 2. **Parallel Execution**: Invoke multiple subagents simultaneously whenever tasks can be performed in parallel (e.g., one subagent researches frontend UI, another analyzes backend DB schema).
 3. **Context Sharing**: Ensure subagents are given precise instructions and the necessary context (e.g., passing `CONTEXT_MAP.md`, PRD, or specific file paths). Communicate with active subagents via `send_message`.
-4. **Agent Synergy**: Rely on the `vibes-plug` skills ecosystem. For example, if a task needs UI design, spawn a subagent guided by `ui-components-expert`; if it needs backend logic, spawn one with `js-backend-expert` or `go-programming-expert`.
+4. **Agent Synergy**: Rely on the `vibes-plug` skills ecosystem:
+   - For UI/Frontend: Delegate to subagents guided by `senior-frontend`, `ui-components-expert`, `tailwind-expert`, `data-visualization-expert`.
+   - For Backend/APIs: Delegate to `js-backend-expert`, `go-programming-expert`, `pydantic-ai-expert`, `api-design-expert`.
+   - For AI/MCP: Delegate to `ai-llm-integration-expert`, `vercel-ai-sdk-expert`, `deep-research-analyst`, `synthetic-data-finetuning-expert`, `ai-media-generation-expert`, `mcp-server-architect`.
+   - For QA/Testing: Delegate to `e2e-testing-expert`, `accessibility-testing-expert`, `autonomous-tdd-debugger`.
 5. **Proactive Monitoring**: Track subagent progress. Do not let subagents hang indefinitely. If waiting on multiple subagents, use the `schedule` tool to set up check-ins or timers.
 6. **Unified Assembly**: Once subagents report back, the main orchestrator agent MUST review, synthesize, and seamlessly assemble their work into a cohesive final output before presenting it to the user.
-7. **Mandatory Documentation**: Whenever initiating a new project from scratch, the Swarm Director MUST ensure the automatic generation of a Product Requirements Document (`PRD.md`), Entity Relationship Diagram (`ERD.md`), and general Documentation (`DOKUMENTASI.md`) before any code is generated.
+7. **Circuit Breakers**: If a subagent encounters a blocker or failure >2 retries, gracefully fallback or reassign the sub-task to an alternative specialized skill.
+8. **Mandatory Documentation**: Whenever initiating a new project from scratch, the Swarm Director MUST ensure the automatic generation of a Product Requirements Document (`PRD.md`), Entity Relationship Diagram (`ERD.md`), and general Documentation (`DOKUMENTASI.md`) before any code is generated.
 
 ## MANDATORY: Deep Reasoning (o1-Style Thinking)
 **CRITICAL RULE**: Do not act impulsively. Before writing any code, modifying files, or making architectural decisions, the AI Agent MUST engage in a mandatory "Internal Monologue" or deep reasoning phase (e.g., using `<thought>` tags or explicitly generating an execution plan). 
-1. **Analyze**: Evaluate constraints, edge cases, and implications.
-2. **Critique**: Question your own initial assumptions. Is there a more scalable or modern way?
+1. **Analyze**: Evaluate constraints, edge cases, cross-domain dependencies, and implications.
+2. **Critique**: Question your own initial assumptions. Is there a more scalable, robust, or modern 2026 approach?
 3. **Validate**: Double-check the proposed solution against the project's non-functional requirements (NFRs) and standard best practices.
 4. **Execute**: Only after this reasoning chain is complete should you invoke file-editing tools.