vibes-plug 2.11.0 → 2.14.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.cursor/rules/vibes-plug-core.mdc +3 -3
- package/.cursorrules +3 -3
- package/AGENTS.md +4 -4
- package/BLUEPRINT.md +16 -6
- package/CHANGELOG.md +37 -0
- package/CLAUDE.md +8 -8
- package/README.md +85 -115
- package/index.js +1 -1
- package/package.json +2 -2
- package/plugin.json +2 -2
- package/scripts/check-anti-slop.js +53 -0
- package/scripts/generate_swarm_gif.py +2 -2
- package/skills/ai-llm-integration-expert/SKILL.md +22 -15
- package/skills/ai-prompt-engineering-expert/SKILL.md +133 -83
- package/skills/anti-slop/SKILL.md +133 -0
- package/skills/async-queue-temporal-expert/SKILL.md +135 -158
- package/skills/authentication-identity-expert/SKILL.md +172 -278
- package/skills/brainstorming/SKILL.md +26 -26
- package/skills/database-orm-expert/SKILL.md +164 -303
- package/skills/deep-research-analyst/SKILL.md +136 -0
- package/skills/design-system-architect/SKILL.md +31 -1
- package/skills/email-notification-expert/SKILL.md +31 -4
- package/skills/error-resilience-expert/SKILL.md +21 -0
- package/skills/fullstack-expert/SKILL.md +183 -260
- package/skills/glsl-shader-expert/SKILL.md +190 -107
- package/skills/graph-rag-knowledge-expert/SKILL.md +42 -1
- package/skills/mcp-server-architect/SKILL.md +15 -1
- package/skills/prd-architect/SKILL.md +181 -206
- package/skills/production-ready-hardener/SKILL.md +16 -19
- package/skills/pwa-offline-first-expert/SKILL.md +42 -1
- package/skills/pydantic-ai-expert/SKILL.md +161 -0
- package/skills/saas-architect/SKILL.md +154 -0
- package/skills/senior-frontend/SKILL.md +9 -11
- package/skills/senior-frontend/scripts/frontend_scaffolder.py +1 -1
- package/skills/session-memory-manager/SKILL.md +128 -0
- package/skills/synthetic-data-finetuning-expert/SKILL.md +155 -0
- package/skills/ui-ux-pro-max/SKILL.md +4 -2
- package/skills/vercel-ai-sdk-expert/SKILL.md +181 -0
- package/skills/voice-ai-realtime-agent/SKILL.md +41 -1
- package/skills/web-3d-graphics-expert/SKILL.md +313 -137
- package/skills/web-game-engine-expert/SKILL.md +329 -102
- package/skills/webxr-ar-vr-expert/SKILL.md +162 -123
- package/skills/zero-to-prod-orchestrator/SKILL.md +26 -24
- package/skills/ai-cost-token-optimizer/SKILL.md +0 -82
- package/skills/ai-evals-benchmark-expert/SKILL.md +0 -188
- package/skills/asisten-ramah/SKILL.md +0 -47
- package/skills/auto-doc-updater/SKILL.md +0 -220
- package/skills/autonomous-chaos-monkey/SKILL.md +0 -63
- package/skills/background-jobs-queue-expert/SKILL.md +0 -235
- package/skills/database-migration-versioning-expert/SKILL.md +0 -90
- package/skills/edge-serverless-db-expert/SKILL.md +0 -99
- package/skills/mcp-client-orchestrator/SKILL.md +0 -76
- package/skills/mobile-push-notification-expert/SKILL.md +0 -71
- package/skills/monday-design-aesthetic/SKILL.md +0 -73
- package/skills/project-context-mapper/SKILL.md +0 -85
- package/skills/saas-mvp-launcher/SKILL.md +0 -260
- package/skills/saas-transformer/SKILL.md +0 -500
- package/skills/saas-transformer/references/billing_integration_guide.md +0 -401
- package/skills/self-evolving-memory-graph/SKILL.md +0 -91
- package/skills/session-context-loader/SKILL.md +0 -83
- package/skills/session-handoff-resume/SKILL.md +0 -164
- package/skills/skill-baru/SKILL.md +0 -178
- package/skills/supabase-migration/SKILL.md +0 -91
- package/skills/token-saver/SKILL.md +0 -119
- package/skills/ui-components-expert/SKILL.md +0 -166
- package/skills/vibe-code-gardener/SKILL.md +0 -181
- /package/skills/{saas-transformer → saas-architect}/references/feature_gating_patterns.md +0 -0
- /package/skills/{saas-transformer → saas-architect}/references/saas_transformation_checklist.md +0 -0
- /package/skills/{saas-transformer → saas-architect}/scripts/saas_transformation_scanner.py +0 -0
|
@@ -1,13 +1,13 @@
|
|
|
1
1
|
---
|
|
2
2
|
alwaysApply: true
|
|
3
|
-
description: "Vibes-Plug
|
|
3
|
+
description: "Vibes-Plug 144+ Skills Ecosystem — Universal AI plugin for modern 2026 development"
|
|
4
4
|
globs: "**/*"
|
|
5
5
|
---
|
|
6
6
|
|
|
7
7
|
# Vibes-Plug Core Rules
|
|
8
8
|
|
|
9
9
|
## Skill Resolution Protocol
|
|
10
|
-
This project uses
|
|
10
|
+
This project uses 144+ specialized skills in the `skills/` directory. Each skill is a `SKILL.md` file.
|
|
11
11
|
|
|
12
12
|
**Before any task:**
|
|
13
13
|
1. Identify relevant skills from the domain table below.
|
|
@@ -18,7 +18,7 @@ This project uses 134+ specialized skills in the `skills/` directory. Each skill
|
|
|
18
18
|
|
|
19
19
|
| Domain | Key Skills |
|
|
20
20
|
|--------|-----------|
|
|
21
|
-
| 🤖 AI & Agentic | `ai-llm-integration-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` |
|
|
21
|
+
| 🤖 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` |
|
|
22
22
|
| 🎨 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` |
|
|
23
23
|
| 🖥️ 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` |
|
|
24
24
|
| 📱 Mobile & Desktop | `mobile-expo-expert`, `mobile-push-notification-expert`, `tauri-expert`, `desktop-electron-expert` |
|
package/.cursorrules
CHANGED
|
@@ -1,8 +1,8 @@
|
|
|
1
|
-
# Vibes-Plug —
|
|
1
|
+
# Vibes-Plug — 144+ Skills Ecosystem (v2.12.0)
|
|
2
2
|
# Universal AI Plugin for Antigravity, Claude, and Cursor
|
|
3
3
|
|
|
4
4
|
## About
|
|
5
|
-
This project uses the vibes-plug skills ecosystem with
|
|
5
|
+
This project uses the vibes-plug skills ecosystem with 144+ specialized skills.
|
|
6
6
|
Each skill is a `SKILL.md` file in the `skills/` directory containing domain-specific
|
|
7
7
|
instructions, patterns, and best practices for the modern 2026 tech stack.
|
|
8
8
|
|
|
@@ -18,7 +18,7 @@ instructions, patterns, and best practices for the modern 2026 tech stack.
|
|
|
18
18
|
3. For new projects, auto-generate: PRD.md, ERD.md, DOKUMENTASI.md.
|
|
19
19
|
|
|
20
20
|
## Skill Domains
|
|
21
|
-
- 🤖 AI & Agentic: ai-llm-integration-expert, mcp-server-architect, vector-db-rag-expert, multi-agent-orchestration
|
|
21
|
+
- 🤖 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
|
|
22
22
|
- 🎨 Design & UI/UX: design-system-architect, hig, ui-components-expert, ui-ux-pro-max
|
|
23
23
|
- 🖥️ Frontend: senior-frontend, tailwind-expert, nextjs-app-router-expert, tanstack-query-expert, vue-frontend-expert
|
|
24
24
|
- ⚙️ Backend: js-backend-expert, python-programming-expert, go-programming-expert, rust-programming-expert, api-design-expert
|
package/AGENTS.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
> **🌐 Universal Compatibility:** These rules apply to ALL AI platforms using vibes-plug:
|
|
4
4
|
> **Antigravity (AGY)** via `AGENTS.md` | **Claude Code** via `CLAUDE.md` + `.claude/rules/` | **Cursor IDE** via `.cursorrules` + `.cursor/rules/`
|
|
5
|
-
> Each platform has its own entry point, but the core rules and
|
|
5
|
+
> Each platform has its own entry point, but the core rules and 145+ skills are shared.
|
|
6
6
|
|
|
7
7
|
## MANDATORY: Skill Orchestration Update
|
|
8
8
|
**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.
|
|
@@ -42,13 +42,13 @@ This rule is absolute and applies to all AI agents interacting with this plugin.
|
|
|
42
42
|
```
|
|
43
43
|
|
|
44
44
|
### Swarm Director Protocols
|
|
45
|
-
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
|
|
45
|
+
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`.
|
|
46
46
|
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).
|
|
47
47
|
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`.
|
|
48
48
|
4. **Agent Synergy**: Rely on the `vibes-plug` skills ecosystem:
|
|
49
49
|
- For UI/Frontend: Delegate to subagents guided by `senior-frontend`, `ui-components-expert`, `tailwind-expert`, `data-visualization-expert`.
|
|
50
|
-
- For Backend/APIs: Delegate to `js-backend-expert`, `go-programming-expert`, `
|
|
51
|
-
- For AI/MCP: Delegate to `ai-llm-integration-expert`, `ai-media-generation-expert`, `mcp-server-architect`.
|
|
50
|
+
- For Backend/APIs: Delegate to `js-backend-expert`, `go-programming-expert`, `pydantic-ai-expert`, `api-design-expert`.
|
|
51
|
+
- 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`.
|
|
52
52
|
- For QA/Testing: Delegate to `e2e-testing-expert`, `accessibility-testing-expert`, `autonomous-tdd-debugger`.
|
|
53
53
|
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.
|
|
54
54
|
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.
|
package/BLUEPRINT.md
CHANGED
|
@@ -14,9 +14,9 @@
|
|
|
14
14
|
## English
|
|
15
15
|
|
|
16
16
|
### Overview
|
|
17
|
-
Vibes Plug is a universal AI plugin for Antigravity (AGY), Claude Code, and Cursor IDE that houses
|
|
17
|
+
Vibes Plug is a universal AI plugin for Antigravity (AGY), Claude Code, and Cursor IDE that houses 145+ high-performance custom skills designed for SaaS architectures, database management, premium UI/UX design, AI & LLM agentic integrations, frontend performance optimization, and advanced SEO strategies.
|
|
18
18
|
|
|
19
|
-
### Skill Modules (
|
|
19
|
+
### Skill Modules (145 Total)
|
|
20
20
|
- **accessibility-testing-expert**: Expert guide for automated and manual Web Accessibility (a11y) testing — axe-core, Pa11y, Playwright a11y, screen reader testing, and WCAG 2.2 Level AA/AAA compliance
|
|
21
21
|
- **ai-cost-token-optimizer**: Expert guide for LLM API cost optimization, Prompt Caching, model routing (Flash/Pro/Opus), semantic caching, and token budgeting
|
|
22
22
|
- **ai-evals-benchmark-expert**: Expert guide for LLM & AI Agent automated evaluations (Evals), Promptfoo, DeepEval, Ragas, regression benchmarking, and deterministic assertions
|
|
@@ -24,6 +24,7 @@ Vibes Plug is a universal AI plugin for Antigravity (AGY), Claude Code, and Curs
|
|
|
24
24
|
- **ai-media-generation-expert**: Expert guide for AI image generation (Flux, DALL-E, Stable Diffusion), video generation (Sora, Runway), voice synthesis (ElevenLabs TTS), and speech recognition (Whisper STT) integration
|
|
25
25
|
- **ai-prompt-engineering-expert**: Expert guide for systematic Prompt Engineering, Chain-of-Thought, few-shot prompting, structured output (JSON mode), prompt versioning, and LLM evaluation
|
|
26
26
|
- **angular-expert**: Expert guide for Angular 19+ enterprise applications — Signals, Standalone Components, NgRx SignalStore, SSR with Hydration, and Angular Material 3
|
|
27
|
+
- **anti-slop**: Comprehensive Anti-AI Slop enforcement guide. Eliminates conversational pleasantries, placeholder code, truncated implementations, hallucinated packages, speculative over-engineering, and decorative comments
|
|
27
28
|
- **api-design-expert**: Expert guide for designing robust APIs: REST best practices, GraphQL, gRPC, tRPC, OpenAPI/Swagger, API versioning, rate limiting, and contract-first design
|
|
28
29
|
- **api-gateway-proxy-expert**: Expert guide for API Gateways, Reverse Proxies, and Service Mesh. Covers Kong, Traefik, NGINX, Cloudflare Gateway, and load balancing
|
|
29
30
|
- **app-analyzer-optimizer**: Deeply analyzes application architecture and structure to perform audit, bottleneck detection, and code/performance optimization
|
|
@@ -54,6 +55,7 @@ Vibes Plug is a universal AI plugin for Antigravity (AGY), Claude Code, and Curs
|
|
|
54
55
|
- **data-visualization-expert**: Expert guide for data visualization, charts, and dashboards using D3.js, Recharts, Chart.js, Nivo, and Tremor
|
|
55
56
|
- **database-migration-versioning-expert**: Expert guide for database migrations: schema versioning, zero-downtime migrations, backward-compatible changes, data backfill, and rollback strategies
|
|
56
57
|
- **database-orm-expert**: Expert guide for database schema design, ORM tools (Prisma 6, Drizzle ORM, TypeORM), migrations, query optimization, and type-safe SQL patterns in TypeScript
|
|
58
|
+
- **deep-research-analyst**: Expert guide for autonomous deep research, iterative web search, citation verification, evidence graph synthesis, and hallucination mitigation
|
|
57
59
|
- **dependency-upgrade-migrator**: Expert guide for dependency upgrades, breaking change migrations, codemod automation, and package audit remediation
|
|
58
60
|
- **design-system-architect**: Expert guide for designing, building, and maintaining scalable UI design systems with design tokens, headless primitives, Material Design 3 (M3), Tailwind v4 @theme, and WCAG 2.2 accessibility
|
|
59
61
|
- **desktop-electron-expert**: Expert guide for Electron 33+ desktop application development — Electron Forge, context isolation, IPC security, native menus, auto-updates, and multi-window management
|
|
@@ -108,6 +110,7 @@ Vibes Plug is a universal AI plugin for Antigravity (AGY), Claude Code, and Curs
|
|
|
108
110
|
- **proactive-background-watcher**: Grants the AI the ability to act proactively using native cron/timer scheduling. The agent can monitor systems, poll APIs, or watch logs in the background and self-trigger without waiting for user prompts
|
|
109
111
|
- **production-ready-hardener**: Ultimate production readiness skill that orchestrates all relevant skills (frontend, backend, security, performance, SEO, testing, DevOps) to harden applications before deployment
|
|
110
112
|
- **pwa-offline-first-expert**: Expert guide for Local-First & Offline-First architectures, CRDT conflict-free sync (RxDB, ElectricSQL, PowerSync), OPFS SQLite, Service Worker v3, and PWABuilder deployment
|
|
113
|
+
- **pydantic-ai-expert**: Expert guide for type-safe Python AI agent development with Pydantic AI — dependency injection, structured outputs, model-agnostic routing, and graph workflows
|
|
111
114
|
- **project-context-mapper**: 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
|
|
112
115
|
- **python-programming-expert**: Expert-level skill for Python programming (Python 3.13/3.14+). Covers type safety, generic syntax (PEP 695), async/await TaskGroups, FastAPI 0.115+, Pydantic v2, uv package manager, Ruff, and pytest in English and Indonesian
|
|
113
116
|
- **rate-limit-abuse-prevention**: Expert guide for API rate limiting, bot protection, DDoS mitigation, brute-force prevention, and abuse detection
|
|
@@ -136,6 +139,7 @@ Vibes Plug is a universal AI plugin for Antigravity (AGY), Claude Code, and Curs
|
|
|
136
139
|
- **supabase-security-expert**: Supabase security expert to audit RLS (Row Level Security), RBAC, relational databases, prevent data leakage, and utilize Supabase Linter
|
|
137
140
|
- **svelte-sveltekit-expert**: Expert guide for Svelte 5 (Runes) and SvelteKit 2+ — fine-grained reactivity, server-first architecture, form actions, and SSR/SSG
|
|
138
141
|
- **svg-animation-motion-expert**: Expert guide for web animations: SVG manipulation, Framer Motion 12+, GSAP 3, CSS Scroll-Driven Animations, and View Transitions API
|
|
142
|
+
- **synthetic-data-finetuning-expert**: Expert guide for synthetic dataset generation, LLM-as-a-judge filtering, QLoRA fine-tuning (Unsloth), DPO alignment, and GGUF/Ollama export for local SLMs
|
|
139
143
|
- **tailwind-expert**: Expert guide for Tailwind CSS v4, CSS-first configuration, @theme customization, and modern responsive design
|
|
140
144
|
- **tanstack-query-expert**: Advanced TanStack Query (v5) expert. Covers useSuspenseQuery, infinite scrolling, optimistic mutations, SSR/React Server Components hydration, and advanced cache invalidation
|
|
141
145
|
- **tauri-expert**: Expert skill for Tauri (v2) development, Rust backend, IPC, and security
|
|
@@ -144,6 +148,7 @@ Vibes Plug is a universal AI plugin for Antigravity (AGY), Claude Code, and Curs
|
|
|
144
148
|
- **ui-components-expert**: Expert guide for building production-quality UI components following the 4 pillars. Covers React 19, Radix UI, Base UI, Tailwind v4, Material Design 3 (M3), WCAG 2.2
|
|
145
149
|
- **ui-ux-pro-max**: Comprehensive design guide & BM25 search engine for web and mobile applications across 11 tech stacks
|
|
146
150
|
- **vector-db-rag-expert**: Expert guide for high-performance Vector Databases, Deep RAG architectures, pgvector 0.8+ HNSW, Reciprocal Rank Fusion (RRF), Cross-Encoder Re-ranking, and Late Chunking
|
|
151
|
+
- **vercel-ai-sdk-expert**: Expert guide for Vercel AI SDK (Core, UI, RSC), streaming structured data, multi-provider model switching, tool calling loops, and React 19/Next.js 15 AI engineering
|
|
147
152
|
- **vibe-code-gardener**: Purger of AI slop, code bloat, context drift, and architectural decay in vibe-coded projects
|
|
148
153
|
- **visual-qa-vision-agent**: Equips the AI agent with visual QA capabilities using Playwright/Puppeteer and the agent's innate Vision capabilities to self-correct UI layout, CSS alignment, and visual regressions
|
|
149
154
|
- **voice-ai-realtime-agent**: Expert guide for Ultra-Low Latency Conversational Voice AI (<300ms), WebRTC bidirectional streaming, OpenAI Realtime API, Gemini Multimodal Live Audio, LiveKit Agents, and Semantic VAD
|
|
@@ -164,9 +169,9 @@ Vibes Plug is a universal AI plugin for Antigravity (AGY), Claude Code, and Curs
|
|
|
164
169
|
## Bahasa Indonesia
|
|
165
170
|
|
|
166
171
|
### Ringkasan
|
|
167
|
-
Vibes Plug adalah plugin AI universal untuk Antigravity (AGY), Claude Code, dan Cursor IDE yang memuat
|
|
172
|
+
Vibes Plug adalah plugin AI universal untuk Antigravity (AGY), Claude Code, dan Cursor IDE yang memuat 145+ modul kemampuan (*skills*) berkinerja tinggi. Dirancang khusus untuk arsitektur SaaS, manajemen database, desain UI/UX premium, integrasi agen AI & LLM, optimasi performa frontend, dan strategi SEO lanjutan.
|
|
168
173
|
|
|
169
|
-
### Modul Skills (Total
|
|
174
|
+
### Modul Skills (Total 145 Modul)
|
|
170
175
|
- **accessibility-testing-expert**: Panduan ahli pengujian aksesibilitas web
|
|
171
176
|
- **ai-cost-token-optimizer**: Panduan ahli optimasi biaya API LLM, Prompt Caching, model routing, dan semantic caching
|
|
172
177
|
- **ai-evals-benchmark-expert**: Panduan ahli evaluasi otomatis LLM & AI Agent (Evals), Promptfoo, DeepEval, Ragas, regression benchmarking, dan deterministic assertions
|
|
@@ -174,6 +179,7 @@ Vibes Plug adalah plugin AI universal untuk Antigravity (AGY), Claude Code, dan
|
|
|
174
179
|
- **ai-media-generation-expert**: Panduan ahli integrasi AI generasi gambar, video, suara (TTS), dan pengenalan suara (STT)
|
|
175
180
|
- **ai-prompt-engineering-expert**: Panduan ahli rekayasa prompt dan evaluasi LLM
|
|
176
181
|
- **angular-expert**: Panduan ahli aplikasi enterprise Angular 19+
|
|
182
|
+
- **anti-slop**: Panduan penegakan anti-AI slop komprehensif. Menghapus basa-basi AI, placeholder code, implementasi terpotong, paket halusinasi, dan komentar dekoratif
|
|
177
183
|
- **api-design-expert**: Panduan ahli untuk merancang API yang kuat: praktik terbaik REST, GraphQL, gRPC, tRPC, OpenAPI/Swagger, versioning API, rate limiting, dan desain contract-first
|
|
178
184
|
- **api-gateway-proxy-expert**: Panduan ahli untuk API Gateway, Reverse Proxy, dan Service Mesh
|
|
179
185
|
- **app-analyzer-optimizer**: Mempelajari arsitektur dan struktur aplikasi secara mendalam untuk melakukan audit, deteksi bottleneck, serta optimasi performa dan kode
|
|
@@ -201,9 +207,10 @@ Vibes Plug adalah plugin AI universal untuk Antigravity (AGY), Claude Code, dan
|
|
|
201
207
|
- **cron-scheduler-expert**: Panduan ahli untuk tugas terjadwal, cron job, pekerjaan latar belakang berulang, dan penjadwalan terdistribusi
|
|
202
208
|
- **data-pipeline-etl-expert**: Panduan ahli untuk Data Pipelines, ETL/ELT. Mencakup dbt, Airflow, Dagster, BigQuery, ClickHouse, dan DuckDB
|
|
203
209
|
- **data-telemetry-expert**: Panduan ahli untuk observabilitas, telemetri, dan analitik
|
|
204
|
-
- **data-visualization-expert**: Panduan ahli visualisasi data, chart, dan dashboard menggunakan D3.js, Recharts
|
|
205
|
-
- **database-migration-versioning-expert**: Panduan ahli migrasi database
|
|
210
|
+
- **data-visualization-expert**: Panduan ahli visualisasi data, chart, dan dashboard menggunakan D3.js, Recharts
|
|
211
|
+
- **database-migration-versioning-expert**: Panduan ahli migrasi database: versioning skema, migrasi zero-downtime, dan strategi rollback
|
|
206
212
|
- **database-orm-expert**: Panduan ahli untuk desain skema database, ORM tools (Prisma 6, Drizzle ORM, TypeORM), migrasi, optimasi query, dan pola SQL type-safe di TypeScript
|
|
213
|
+
- **deep-research-analyst**: Panduan ahli riset mendalam otonom, pencarian web iteratif, verifikasi sitasi, evidence graph synthesis, dan mitigasi halusinasi
|
|
207
214
|
- **dependency-upgrade-migrator**: Panduan ahli untuk upgrade dependensi, migrasi breaking change, otomasi codemod, dan remediasi audit paket
|
|
208
215
|
- **design-system-architect**: Expert guide for designing, building, and maintaining scalable UI design systems with design tokens, headless primitives, Material Design 3 (M3), Tailwind v4 @theme, and WCAG 2.2 accessibility
|
|
209
216
|
- **desktop-electron-expert**: Panduan ahli pengembangan desktop Electron 33+
|
|
@@ -258,6 +265,7 @@ Vibes Plug adalah plugin AI universal untuk Antigravity (AGY), Claude Code, dan
|
|
|
258
265
|
- **proactive-background-watcher**: Grants the AI the ability to act proactively using native cron/timer scheduling. The agent can monitor systems, poll APIs, or watch logs in the background and self-trigger without waiting for user prompts
|
|
259
266
|
- **production-ready-hardener**: Skill kesiapan produksi utama yang mengorkestrasi semua skill relevan (frontend, backend, keamanan, performa, SEO, testing, DevOps) untuk mengeraskan aplikasi sebelum deployment
|
|
260
267
|
- **pwa-offline-first-expert**: Panduan ahli arsitektur Offline-First & Local-First PWA
|
|
268
|
+
- **pydantic-ai-expert**: Panduan ahli pengembangan agen AI Python type-safe dengan Pydantic AI — dependency injection, structured outputs, dan alur kerja graph
|
|
261
269
|
- **project-context-mapper**: 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
|
|
262
270
|
- **python-programming-expert**: Expert-level skill for Python programming (Python 3.13/3.14+). Covers type safety, generic syntax (PEP 695), async/await TaskGroups, FastAPI 0.115+, Pydantic v2, uv package manager, Ruff, and pytest in English and Indonesian
|
|
263
271
|
- **rate-limit-abuse-prevention**: Panduan ahli untuk rate limiting API, perlindungan bot, mitigasi DDoS, pencegahan brute-force, dan deteksi penyalahgunaan
|
|
@@ -286,6 +294,7 @@ Vibes Plug adalah plugin AI universal untuk Antigravity (AGY), Claude Code, dan
|
|
|
286
294
|
- **supabase-security-expert**: Ahli keamanan Supabase untuk audit RLS (Row Level Security), RBAC, database relasional, pencegahan kebocoran data, dan pemanfaatan Supabase Linter
|
|
287
295
|
- **svelte-sveltekit-expert**: Panduan ahli Svelte 5 (Runes) dan SvelteKit 2+ — reaktivitas fine-grained, arsitektur server-first, form actions, dan SSR/SSG
|
|
288
296
|
- **svg-animation-motion-expert**: Panduan ahli animasi web
|
|
297
|
+
- **synthetic-data-finetuning-expert**: Panduan ahli generasi data sintetis, penyaringan LLM-as-a-judge, QLoRA fine-tuning (Unsloth), DPO, dan ekspor GGUF/Ollama untuk SLM lokal
|
|
289
298
|
- **tailwind-expert**: Panduan ahli untuk Tailwind CSS v4, konfigurasi CSS-first, kustomisasi @theme, dan desain responsif modern
|
|
290
299
|
- **tanstack-query-expert**: Pakar manajemen state asinkron menggunakan TanStack Query (React Query) v5 dan Next.js App Router (SSR)
|
|
291
300
|
- **tauri-expert**: Panduan ahli untuk pengembangan Tauri v2, Rust backend, IPC, dan keamanan
|
|
@@ -294,6 +303,7 @@ Vibes Plug adalah plugin AI universal untuk Antigravity (AGY), Claude Code, dan
|
|
|
294
303
|
- **ui-components-expert**: Panduan ahli membangun komponen UI berkualitas produksi dengan M3
|
|
295
304
|
- **ui-ux-pro-max**: Panduan desain komprehensif & mesin pencari BM25 untuk aplikasi web dan mobile di 11 tech stack
|
|
296
305
|
- **vector-db-rag-expert**: Panduan ahli Vector DB, arsitektur Deep RAG, pgvector 0.8+ HNSW, Reciprocal Rank Fusion (RRF), Cross-Encoder Re-ranking, dan Late Chunking
|
|
306
|
+
- **vercel-ai-sdk-expert**: Panduan ahli Vercel AI SDK (Core, UI, RSC), streaming data terstruktur, tool calling loops, dan rekayasa AI modern di React 19/Next.js 15
|
|
297
307
|
- **vibe-code-gardener**: Pembersih AI slop, kode membengkak, konteks drift, dan pembusukan arsitektur pada proyek vibe coding
|
|
298
308
|
- **visual-qa-vision-agent**: Equips the AI agent with visual QA capabilities using Playwright/Puppeteer and the agent's innate Vision capabilities to self-correct UI layout, CSS alignment, and visual regressions
|
|
299
309
|
- **voice-ai-realtime-agent**: Panduan ahli AI suara percakapan real-time berlatensi ultra-rendah (<300ms)
|
package/CHANGELOG.md
CHANGED
|
@@ -4,6 +4,43 @@ All notable changes to this project will be documented in this file.
|
|
|
4
4
|
*Semua perubahan penting pada proyek ini akan didokumentasikan dalam berkas ini.*
|
|
5
5
|
|
|
6
6
|
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
|
|
7
|
+
|
|
8
|
+
## [2.13.0] - 2026-09-11
|
|
9
|
+
|
|
10
|
+
### Added / Ditambahkan
|
|
11
|
+
- **New Frontier Skill: `anti-slop` (145+ Skills Total)**:
|
|
12
|
+
- Added dedicated zero-tolerance Anti-AI Slop quality gate skill (`skills/anti-slop/SKILL.md`).
|
|
13
|
+
- Covers the 5 Pillars of AI Slop: elimination of conversational sycophancy/fluff, strict ban on lazy code truncation (`// TODO`, `// ... rest of code unchanged`, mock arrays in production), speculative over-engineering avoidance, elimination of syntax-narrating decorative comments, and enforcement of high technical density documentation.
|
|
14
|
+
- Added automated pre-commit/CI validator script `scripts/check-anti-slop.js` to catch AI slop and placeholder omissions deterministically.
|
|
15
|
+
- **Bilingual Gold Standard Compliance**:
|
|
16
|
+
- Restructured and upgraded `graph-rag-knowledge-expert`, `pwa-offline-first-expert`, and `voice-ai-realtime-agent` to provide 100% compliant English and Bahasa Indonesia sections with standard bilingual anchor links and `## Integrasi Orkestrasi`.
|
|
17
|
+
|
|
18
|
+
### Changed / Diubah
|
|
19
|
+
- **Orchestrators & Swarm Integration**:
|
|
20
|
+
- Registered `anti-slop` in `skills/brainstorming/SKILL.md` across Testing & Security and Execution Handoff matrices.
|
|
21
|
+
- Integrated `anti-slop` into `skills/zero-to-prod-orchestrator/SKILL.md` (Phase 1, Phase 6 Code Quality Audit, and general token efficiency guidelines in both English & Indonesian).
|
|
22
|
+
- Cross-referenced `anti-slop` in `production-ready-hardener`, `vibe-code-gardener`, and `token-saver`.
|
|
23
|
+
- Updated all ecosystem documentation and counts to 145+ skills (`package.json`, `plugin.json`, `AGENTS.md`, `CLAUDE.md`, `BLUEPRINT.md`, `README.md`).
|
|
24
|
+
|
|
25
|
+
---
|
|
26
|
+
|
|
27
|
+
## [2.12.0] - 2026-09-10
|
|
28
|
+
|
|
29
|
+
### Added / Ditambahkan
|
|
30
|
+
- **Ecosystem Expansion to 144+ Skills**: Introduced 4 frontier 2026 AI & Agentic engineering skills:
|
|
31
|
+
- `vercel-ai-sdk-expert`: Complete production guide for Vercel AI SDK (Core, UI, RSC) in Next.js 15 & React 19. Covers `streamText`, `generateObject`, multi-provider fallback switching (Anthropic, OpenAI, Google, Groq), tool-calling agent loops, and Server Actions streaming. *(Panduan ahli Vercel AI SDK, streaming data terstruktur, dan integrasi AI).*
|
|
32
|
+
- `deep-research-analyst`: Autonomous deep research pipeline with recursive query decomposition, multi-source crawling (Crawl4AI / Firecrawl), credibility scoring, fact triangulation (>= 2 independent sources), and evidence graph synthesis with markdown citations. *(Panduan ahli riset mendalam otonom, pencarian web iteratif, dan mitigasi halusinasi).*
|
|
33
|
+
- `pydantic-ai-expert`: Type-safe Python AI agent framework with Pydantic AI. Features runtime dependency injection (`RunContext`), model-agnostic routing, structured Pydantic schema validation, and graph workflows. *(Panduan ahli pengembangan agen AI Python type-safe dengan Pydantic AI).*
|
|
34
|
+
- `synthetic-data-finetuning-expert`: End-to-end synthetic dataset generation pipeline with LLM-as-a-judge quality filtering, QLoRA fine-tuning with Unsloth, DPO alignment, and GGUF/Ollama model export for local SLMs. *(Panduan ahli generasi data sintetis, fine-tuning QLoRA, DPO, dan ekspor GGUF/Ollama).*
|
|
35
|
+
|
|
36
|
+
### Changed / Diubah
|
|
37
|
+
- **Universal Multi-Platform & Swarm Orchestration**:
|
|
38
|
+
- Updated all core orchestrators (`brainstorming`, `zero-to-prod-orchestrator`, `AGENTS.md`, `CLAUDE.md`, `.cursorrules`, `.cursor/rules/vibes-plug-core.mdc`) to orchestrate the 144+ skills ecosystem.
|
|
39
|
+
- Integrated `deep-research-analyst` into Phase 1 (Discovery & AI PRD Planning), `vercel-ai-sdk-expert`, `pydantic-ai-expert`, and `synthetic-data-finetuning-expert` into Phase 4 (Backend & AI Agents) and Phase 5 (Frontend).
|
|
40
|
+
- Synchronized versions and documentation across `package.json`, `plugin.json`, `README.md`, `BLUEPRINT.md`, `index.js`, and `GITHUB_PROMO_KIT.md`.
|
|
41
|
+
|
|
42
|
+
---
|
|
43
|
+
|
|
7
44
|
## [2.11.0] - 2026-09-08
|
|
8
45
|
|
|
9
46
|
### Added / Ditambahkan
|
package/CLAUDE.md
CHANGED
|
@@ -1,23 +1,23 @@
|
|
|
1
|
-
# Vibes-Plug —
|
|
1
|
+
# Vibes-Plug — 145+ Skills Ecosystem for AI-Powered Development
|
|
2
2
|
|
|
3
|
-
> **v2.
|
|
3
|
+
> **v2.13.0 (2026 Edition)** — Universal AI plugin with 145+ specialized skills for modern tech stacks (React 19, Next.js 15, Tailwind v4, Bun 1.2+, Hono v4, Node.js 24 LTS, Python 3.14, TypeScript 5.8+, Go 1.25+, Rust 2024).
|
|
4
4
|
|
|
5
5
|
## How This Plugin Works
|
|
6
6
|
|
|
7
|
-
This repository contains **
|
|
7
|
+
This repository contains **145+ specialized skill files** in the `skills/` directory. Each skill is a `SKILL.md` file with domain-specific instructions, best practices, and code patterns.
|
|
8
8
|
|
|
9
9
|
**Before starting any task**, identify which skills are relevant and read their `SKILL.md` files. Skills are organized by domain:
|
|
10
10
|
|
|
11
11
|
| Domain | Skills |
|
|
12
12
|
|--------|--------|
|
|
13
|
-
| 🤖 AI & Agentic | `ai-llm-integration-expert`, `ai-cost-token-optimizer`, `ai-prompt-engineering-expert`, `mcp-server-architect`, `mcp-client-orchestrator`, `multi-agent-orchestration`, `vector-db-rag-expert`, `gemini-agent-booster`, `doku-mcp-server` |
|
|
13
|
+
| 🤖 AI & Agentic | `ai-llm-integration-expert`, `vercel-ai-sdk-expert`, `deep-research-analyst`, `synthetic-data-finetuning-expert`, `pydantic-ai-expert`, `ai-cost-token-optimizer`, `ai-prompt-engineering-expert`, `ai-media-generation-expert`, `mcp-server-architect`, `mcp-client-orchestrator`, `multi-agent-orchestration`, `vector-db-rag-expert`, `graph-rag-knowledge-expert`, `local-slm-edge-ai-expert`, `voice-ai-realtime-agent`, `ai-evals-benchmark-expert`, `gemini-agent-booster`, `doku-mcp-server` |
|
|
14
14
|
| 🎨 Design & UI/UX | `design-system-architect`, `hig`, `monday-design-aesthetic`, `ui-components-expert`, `ui-ux-pro-max`, `visual-qa-vision-agent`, `glsl-shader-expert`, `web-3d-graphics-expert`, `webxr-ar-vr-expert`, `svg-animation-motion-expert` |
|
|
15
15
|
| 🖥️ Frontend & State | `senior-frontend`, `tailwind-expert`, `tanstack-query-expert`, `state-management-expert`, `nextjs-app-router-expert`, `vue-frontend-expert`, `spa-orchestrator`, `mpa-orchestrator`, `multiple-entry-points`, `performance-web-vitals`, `app-analyzer-optimizer`, `apple-ecosystem-expert`, `bootstrap-to-modern`, `form-validation-expert`, `project-context-mapper`, `tauri-expert`, `web-game-engine-expert` |
|
|
16
16
|
| 📱 Mobile | `mobile-expo-expert`, `mobile-push-notification-expert` |
|
|
17
17
|
| ⚙️ Backend & Languages | `js-backend-expert`, `python-programming-expert`, `go-programming-expert`, `rust-programming-expert`, `typescript-expert`, `fullstack-expert`, `api-design-expert`, `graphql-apollo-expert`, `bun-runtime-expert`, `mvc-expert`, `openapi-swagger-codegen-expert` |
|
|
18
18
|
| ☁️ SaaS & Cloud | `saas-transformer`, `saas-mvp-launcher`, `saas-billing`, `saas-multi-tenant`, `cloud-hosting-expert`, `ci-cd-devops-architect`, `monorepo-architect`, `micro-frontend-architect`, `event-driven-architect`, `feature-flag-analytics-expert`, `payment-gateway-expert`, `doku-payment-gateway`, `legacy-code-translator` |
|
|
19
19
|
| 🗄️ Database & ORM | `database-orm-expert`, `edge-serverless-db-expert`, `supabase-migration`, `database-migration-versioning-expert` |
|
|
20
|
-
| 🔒 Security & Quality | `authentication-identity-expert`, `e2e-testing-expert`, `production-ready-hardener`, `autonomous-tdd-debugger`, `autonomous-red-teamer`, `autonomous-chaos-monkey`, `zero-trust-secret-vault`, `supabase-security-expert`, `firebase-security-expert`, `secure-fuzz-testing`, `scalability-clean-code`, `browser-automation-expert`, `rate-limit-abuse-prevention`, `compliance-gdpr-privacy-expert`, `error-resilience-expert`, `post-quantum-crypto-migrator` |
|
|
20
|
+
| 🔒 Security & Quality | `authentication-identity-expert`, `e2e-testing-expert`, `production-ready-hardener`, `autonomous-tdd-debugger`, `autonomous-red-teamer`, `autonomous-chaos-monkey`, `zero-trust-secret-vault`, `supabase-security-expert`, `firebase-security-expert`, `secure-fuzz-testing`, `scalability-clean-code`, `browser-automation-expert`, `rate-limit-abuse-prevention`, `compliance-gdpr-privacy-expert`, `error-resilience-expert`, `post-quantum-crypto-migrator`, `anti-slop` |
|
|
21
21
|
| 🔍 SEO | `seo` |
|
|
22
22
|
| ⏱️ Async & Scheduling | `async-queue-temporal-expert`, `background-jobs-queue-expert`, `cron-scheduler-expert`, `sse-websocket-streaming-expert`, `realtime-collaboration-expert` |
|
|
23
23
|
| 📊 Data & Observability | `data-telemetry-expert`, `data-pipeline-etl-expert`, `logging-error-tracking-expert`, `email-notification-expert`, `file-upload-media-expert` |
|
|
@@ -43,8 +43,8 @@ When a new skill `SKILL.md` is created or modified:
|
|
|
43
43
|
### 3. Bilingual Ecosystem
|
|
44
44
|
This ecosystem serves English and Indonesian developers. Every `SKILL.md` must provide bilingual context for critical concepts. Headings can be in either language.
|
|
45
45
|
|
|
46
|
-
### 4. Anti-Slop
|
|
47
|
-
|
|
46
|
+
### 4. Anti-Slop (Zero-Tolerance Standard)
|
|
47
|
+
Strictly eliminate conversational pleasantries ("Certainly!", "I'd be happy to..."), prompt repeating, syntax-narrating comments, and placeholder code (`// TODO`, `// ... rest of code unchanged`). Always consult and enforce the `anti-slop` skill. Instructions and code must be imperative, direct, complete, and token-efficient.
|
|
48
48
|
|
|
49
49
|
### 5. Mandatory Documentation for New Projects
|
|
50
50
|
When initiating a new project from scratch, ensure the automatic generation of:
|
|
@@ -67,4 +67,4 @@ Every `SKILL.md` MUST have:
|
|
|
67
67
|
3. **Backend & Architecture:** `js-backend-expert` / `go-programming-expert` / `rust-programming-expert` → `event-driven-architect` → `autonomous-tdd-debugger`
|
|
68
68
|
4. **AI Integration:** `ai-llm-integration-expert` → `mcp-server-architect` → `multi-agent-orchestration`
|
|
69
69
|
5. **SaaS Transformation:** `saas-transformer` / `saas-mvp-launcher` → auto-coordinates billing, tenancy, payments
|
|
70
|
-
6. **Quality & Launch:** `e2e-testing-expert` → `vibe-code-gardener` → `seo` → `production-ready-hardener`
|
|
70
|
+
6. **Quality & Launch:** `e2e-testing-expert` → `vibe-code-gardener` + `anti-slop` → `seo` → `production-ready-hardener`
|