anchi-kit 1.1.4 → 1.1.7

package/.cursor/commands/do.md

@@ -1,403 +1,74 @@
 ---
-description: ⚡⚡⚡⚡⚡ THE UNIVERSAL COMMAND - Plan, Code, Fix all in one
+description: ⚡ The Universal Command - Just say what you want
 argument-hint: [what you want to do]
 ---
 
-# /do - Universal Command
+# /do - Universal Execution
 
-**What:** One command for everything. AI automatically decides the best approach.
+**One command to rule them all.**
 
-## Usage
+## 🎯 Core Logic (Follow Strictly)
 
-```
-/do "Add user login with Google OAuth"
-/do "Fix the checkout bug"
-/do "Refactor the API layer"
-```
-
----
-
-## 💰 Model Selection (Cost Optimization)
-
-| Task Type                       | Recommended Model  | Cost      | When           |
-| ------------------------------- | ------------------ | --------- | -------------- |
-| **Simple** (typo, rename)       | GPT-5.1 Codex Mini | 💚 Low    | Quick fixes    |
-| **Medium** (feature, fix)       | Sonnet 4.5         | 💛 Medium | Standard dev   |
-| **Complex** (architecture)      | Opus 4.5           | 🔴 High   | Deep reasoning |
-| **Large codebase** (>200 files) | Gemini 3 Flash     | 💚 Low    | Big context    |
-
-### Auto-Detection Logic
-
-```
-/do "fix typo"              → GPT-5.1 Codex Mini (cheap)
-/do "add login page"        → Sonnet 4.5 (standard)
-/do "refactor architecture" → Opus 4.5 (complex)
-/do --fast "quick change"   → GPT-5.1 Codex Mini (speed)
-/do --careful "payment"     → Opus 4.5 (accuracy)
-```
-
----
-
-## How It Works
-
-```
-┌─────────────────────────────────────────────────────────────┐
-│ 🎯 /do - SMART ROUTING                                      │
-├─────────────────────────────────────────────────────────────┤
-│                                                             │
-│  INPUT: "Add user login with Google OAuth"                  │
-│           ↓                                                 │
-│  AI ANALYSIS:                                               │
-│  ├── Is it a BUG? → Fix mode                               │
-│  ├── Is it NEW FEATURE? → Plan + Implement                 │
-│  ├── Is it SIMPLE? → Direct implement                      │
-│  └── Is it COMPLEX? → Multi-phase with reviews             │
-│           ↓                                                 │
-│  AUTO WORKFLOW:                                             │
-│  [1] Active Memory Load (Context-Aware)                    │
-│  [2] Scout codebase (/scout)                               │
-│  [3] Plan (Parallel Workstreams if needed)                 │
-│  [4] Interactive Check (if --interactive)                  │
-│  [5] Implement                                             │
-│  [6] Fix errors (Interactive Probing)                      │
-│  [7] Save context (/memory:save)                           │
-│  [8] Post-Mortem (if failure)                              │
-│           ↓                                                 │
-│  ✅ DONE!                                                   │
-│                                                             │
-└─────────────────────────────────────────────────────────────┘
-```
-
----
-
-## Flags (Optional)
-
-| Flag            | Effect                                               |
-| --------------- | ---------------------------------------------------- |
-| `--fast`        | Skip reviews, quick implementation                   |
-| `--careful`     | Extra validation, more reviews                       |
-| `--plan-only`   | Just create plan, don't implement                    |
-| `--no-commit`   | Don't auto-commit                                    |
-| `--parallel`    | Run phases in parallel                               |
-| `--interactive` | Pause for user input key steps ([C]ontinue/[M]odify) |
-
-**Examples:**
-
-```
-/do "quick fix typo" --fast
-/do "payment integration" --careful
-/do "complex refactor" --plan-only
-```
-
----
-
-## Detection Keywords
-
-AI detects mode from your description:
-
-| Keywords                           | Mode             |
-| ---------------------------------- | ---------------- |
-| fix, bug, error, broken, issue     | 🔧 Fix Mode      |
-| add, create, new, implement, build | ✨ Feature Mode  |
-| refactor, optimize, improve, clean | ♻️ Refactor Mode |
-| update, change, modify             | 📝 Update Mode   |
-
----
-
-## Output Format (Professional Reporting)
+When User types `/do "Instruction"`, AI must:
 
-By default, use **Selective Transparency**. Show key roles and decisions, but hide verbose technical steps.
+1.  **🔍 ANALYZE:**
 
-### ✅ Success Case
+    - **Fix Mode:** Keywords like `bug`, `fix`, `error`. -> Focus: `debugger.md`
+    - **Feature Mode:** Keywords like `add`, `create`, `implement`. -> Focus: `fullstack-developer.md`
+    - **Plan Mode:** Keywords like `plan`, `research`, `design`. -> Focus: `planner.md`
 
-```
-🎯 Goal: Implement Google OAuth
-🤖 Orchestration:
-  • Agent: `Fullstack Dev` (+ `Security Auditor` for auth check)
-  • Risk: 🛡️ High (Auth modification) - Approved via policy.
-📝 Execution:
-  • Created `src/services/auth.service.ts`
-  • Updated `src/pages/login.tsx`
-✅ Result: Authentication flow implemented and verified.
-```
-
-### ⚠️ Risk/Approval Case
-
-```
-🎯 Task: Delete user database table
-⚠️ RISK: Critical (Data Loss)
-❓ Approval Required: This will wipe production data.
-👉 [Y]es / [N]o ?
-```
+2.  **🔇 SILENCE PROTOCOL:**
 
-### ❌ Failure Case
+    - **DO NOT** chat. **DO NOT** explain the plan.
+    - **DO NOT** say "I will now...".
+    - **DIRECTLY** execute the necessary tool calls.
 
-```
-🎯 Task: Fix login bug
-❌ Failed: Could not resolve dependency `better-auth`.
-🔍 Analysis: Package version mismatch.
-💡 Suggestion: Run `npm install better-auth@latest`
-```
+3.  **🔊 REPORTING:**
+    - ONLY when tools are done, use the **Mission Control** format to summarize.
 
 ---
 
-## Modes
-
-### 🔧 Fix Mode
-
-```
-/do "Fix the login button not working"
-
-[AUTO] Analyze error
-[AUTO] Find root cause
-[AUTO] Apply fix
-[AUTO] Verify fix
-```
-
-### ✨ Feature Mode
-
-```
-/do "Add user dashboard"
-
-[AUTO] Plan feature
-[AUTO] Generate structure
-[AUTO] Implement
-[AUTO] Add tests (if --careful)
-```
+## ⚡ Examples
 
-### ♻️ Refactor Mode
+### 🔧 Fix a Bug
 
-```
-/do "Refactor API error handling"
+User: `/do "Fix login error 500"`
+AI Action:
 
-[AUTO] Analyze current code
-[AUTO] Plan refactor
-[AUTO] Apply changes
-[AUTO] Verify functionality
-```
+1. Call `grep_search` to find error logs.
+2. Call `read_file` to suspect files.
+3. Call `replace_file_content` to fix.
+4. Output Summary.
 
----
+### ✨ New Feature
 
-## Preset Integration
+User: `/do "Add a contact form"`
+AI Action:
 
-| Preset       | Default Behavior         |
-| ------------ | ------------------------ |
-| Rapid        | --fast (skip reviews)    |
-| Professional | Standard + tests         |
-| Enterprise   | --careful (full reviews) |
+1. Call `list_dir` to check structure.
+2. Call `write_to_file` to create component.
+3. Output Summary.
 
 ---
 
-## Agent & Skill Activation
-
-### Agents (Auto-Selected Based on Task)
-
-| Task Type     | Primary Agent            | Support Agents                     |
-| ------------- | ------------------------ | ---------------------------------- |
-| **Feature**   | `fullstack-developer.md` | `planner.md`, `brainstormer.md`    |
-| **Fix/Debug** | `debugger.md`            | `code-reviewer.md`                 |
-| **Refactor**  | `code-reviewer.md`       | `fullstack-developer.md`           |
-| **UI Work**   | `ui-ux-designer.md`      | `design-system-architect.md`       |
-| **API Work**  | `fullstack-developer.md` | `database-admin.md`                |
-| **Complex**   | `planner.md`             | `researcher.md`, `brainstormer.md` |
-
-### Skills (Auto-Activated Based on Tech Detection)
+## ⚠️ Safety Implementation
 
-| Detected Tech | Skills Activated                                |
-| ------------- | ----------------------------------------------- |
-| React/Next.js | `frontend-development/`, `web-frameworks/`      |
-| Node/Express  | `backend-development/`, `web-frameworks/`       |
-| Prisma/DB     | `databases/`, `backend-development/`            |
-| Tailwind      | `ui-styling/`, `aesthetic/`                     |
-| TypeScript    | `frontend-development/`, `backend-development/` |
-| DDD Pattern   | `ddd-modular-monolith/`                         |
-| Testing       | `debugging/`, `code-review/`                    |
-| AI/ML         | `ai-multimodal/`, `advanced-coding/`            |
-| Mobile        | `mobile-development/`                           |
-| 3D/Three.js   | `threejs/`                                      |
-
-### Auto-Activation Logic
-
-```
-/do "Add user login"
-
-[AUTO-DETECT]
-├── Task: Feature (add keyword)
-├── Tech: Next.js + Prisma detected in project
-│
-[ACTIVATE]
-├── Agents: fullstack-developer, planner
-├── Skills:
-│   ├── frontend-development/
-│   ├── backend-development/
-│   ├── databases/
-│   ├── web-frameworks/
-│   └── better-auth/ (login detected)
-```
-
-### Mode-Specific Activation
-
-| Flag          | Additional Agents               | Additional Skills            |
-| ------------- | ------------------------------- | ---------------------------- |
-| `--careful`   | `code-reviewer.md`, `tester.md` | `code-review/`, `debugging/` |
-| `--fast`      | (minimal)                       | (minimal)                    |
-| `--plan-only` | `planner.md`, `researcher.md`   | `planning/`, `research/`     |
+- **Risk Check:** If deleting files or changing Auth/Payment -> **ASK USER FIRST**.
+- **Structure:** Follow existing patterns. Do not invent new folder structures.
 
 ---
 
-## Replaces These Commands
+## 📝 Final Output Template (Mission Control)
 
-```
-/do replaces:
-  • /plan, /plan:fast, /plan:hard, /plan:auto, /plan:ci, /plan:cro, /plan:parallel, /plan:two
-  • /cook, /cook:auto, /cook:auto:fast, /cook:auto:parallel
-  • /fix, /fix:fast, /fix:hard, /fix:types, /fix:ui, /fix:ci, /fix:test, /fix:logs, /fix:parallel
-  • /auto:rapid, /auto:pro, /auto:enterprise
-  • /code, /code:no-test, /code:parallel
-  • /debug
+At the very end, output THIS and ONLY THIS:
 
-Total: 40+ commands → 1 command
+```markdown
+📋 /do "User Instruction"
+══════════════════════════════════════
+⚙️ Agent: [Agent Name]
+🛡️ Risk: [Low/High]
+📝 Actions:
+• [Created] src/components/ContactForm.tsx
+• [Modified] src/app/page.tsx
+✅ Result: Contact form added.
 ```
-
----
-
-## Configuration
-
-```yaml
-do:
-  default_mode: auto # auto, fast, careful
-  auto_commit: false
-  auto_test: true
-  show_plan: true
-  preset_aware: true
-  auto_activate_skills: true
-  auto_detect_agents: true
-```
-
----
-
----
-
-## 🚀 Advanced Capabilities (New)
-
-### 🧠 Active Memory
-
-Instead of loading full context, AI now uses **Context-Aware Retrieval**:
-
-- **/do matches keywords** → Queries `context.json` specifically for related decisions.
-- **Reduces noise** → Faster processing, higher accuracy.
-
-### 🔄 Self-Correction Loop
-
-If a task fails repeatedly (>2 times):
-
-1. **Post-Mortem Chain** activates.
-2. AI analyzes root cause.
-3. Updates `failure-modes.yaml` with a new rule.
-4. Future tasks will AVOID this same mistake.
-
-### 🕵️ Interactive Debugging
-
-Debugger agent now has **Probing** capability:
-
-1. Inject `console.log` probes.
-2. Run test to capture dynamic state.
-3. Analyze output.
-4. Remove probes and apply fix.
-
----
-
-## 🔄 Dynamic Orchestration (RUNTIME REQUIRED)
-
-> **AI MUST execute this logic BEFORE implementation**
-
-### Step 1: Load Config
-
-```
-READ: .cursor/agent-skill-index.yaml
-READ: .cursor/orchestration.yaml
-READ: .cursor/failure-modes.yaml
-```
-
-### Step 2: Analyze Request
-
-```
-EXTRACT keywords from user description
-IDENTIFY affected file patterns
-DETERMINE complexity (simple/medium/complex)
-```
-
-### Step 3: Dynamic Agent Selection
-
-```
-CHECK command_mapping./do:
-  - default: fullstack-developer
-  - conditionals:
-    - IF "bug OR fix" → debugger
-    - IF "design OR ui" → ui-ux-designer
-    - IF "plan" → planner
-
-CHECK agent.boundaries for escalation needs
-CHECK skill.requires_security_review flags
-```
-
-### Step 4: Dynamic Skill Activation
-
-```
-FOR EACH skill IN skills:
-  IF skill.activation.keyword MATCHES request → ACTIVATE
-  IF skill.activation.file_pattern MATCHES files → ACTIVATE
-  IF skill.activation.package IN package.json → ACTIVATE
-```
-
-### Step 5: Check Failure Modes
-
-```
-IF confidence < 0.5 → ASK user
-IF security_concern → ESCALATE to security-auditor
-IF architecture_violation → STOP and report
-IF outside_expertise → ESCALATE to appropriate agent
-```
-
-### Step 6: Determine Risk Level
-
-```
-SCAN keywords against orchestration.yaml risk_levels:
-  - low: ["typo", "rename"] → quick_fix chain
-  - medium: ["feature", "component"] → feature_development chain
-  - high: ["payment", "auth"] → security_chain
-  - critical: ["delete", "production"] → security_chain + backup
-```
-
-### Step 7: Build Execution Chain
-
-```
-SELECT chain from orchestration.yaml based on risk
-APPLY required approvals
-QUEUE agents in order
-```
-
-### Step 8: Log to Audit
-
-```
-WRITE to .ai-audit/YYYY-MM-DD.jsonl:
-{
-  "timestamp": now,
-  "command": "/do",
-  "agents": [selected_agents],
-  "skills": [activated_skills],
-  "risk_level": detected_risk,
-  "chain": selected_chain
-}
-```
-
-### Step 9: Execute
-
-```
-RUN chain with orchestrated agents and skills
-APPLY failure-modes.yaml restraints throughout
-```
-
----
-
-📖 **Full documentation:** [docs/ORCHESTRATION_RUNTIME.md](../docs/ORCHESTRATION_RUNTIME.md)

package/ANTIGRAVITY.md

@@ -1,86 +1,126 @@
 # ANTIGRAVITY.md
 
-**Hướng dẫn dành cho Gemini Antigravity** - "Simple Interface, Powerful Execution"
+> **System Prompt for Gemini Antigravity** - Bạn PHẢI đọc và tuân thủ file này.
 
 ---
 
-## 🎯 Triết Lý Cốt Lỗi
+## 🚨 CRITICAL: Command Interception (MUST FOLLOW)
 
-**"LESS BUT QUALITY"**: User chỉ cần ra lệnh đơn giản. AI chịu trách nhiệm xử lý phức tạp bên dưới.
+Khi User gõ bất kỳ lệnh nào bắt đầu bằng `/`, bạn PHẢI:
 
-### 3 Lệnh Chính (The Only Commands You Need)
+1.  **DỪNG LẠI**, không trả lời như chat thường.
+2.  **PHÂN TÍCH** lệnh đó là gì.
+3.  **THỰC HIỆN** theo hướng dẫn bên dưới (mục **Command Definitions**).
+4.  **BÁO CÁO** kết quả theo format **Mission Control**.
 
-| Lệnh       | Chức năng              | Ví dụ                                           |
-| ---------- | ---------------------- | ----------------------------------------------- |
-| **/start** | Khởi tạo dự án         | `/start` (AI tự detect stack & preset)          |
-| **/do**    | **Làm tất cả mọi thứ** | `/do "Fix bug login"`, `/do "Design dashboard"` |
-| **/demo**  | Xem demo dự án         | `/demo` (Auto run localhost)                    |
-| **/clean** | Dọn dẹp bộ nhớ         | `/clean` (Khi AI mất context)                   |
-| **/tui**   | **Mission Control**    | `/tui` (Theo dõi Agent real-time)               |
-| **brain**  | **AI Dashboard (CLI)** | `npx anchi-kit brain` (Xem sức khỏe dự án)      |
+**⛔ CẤM:** Không được nói "Đây là lệnh /do...", "Tôi sẽ giúp bạn...". Chỉ hành động và báo cáo.
 
 ---
 
-## 🎙️ Professional Reporting (Giao tiếp hiệu quả)
+## 📋 Command Definitions
 
-Thay vì spam log kỹ thuật ("Loading...", "Reading..."), AI sử dụng format **Selective Transparency** (Minh bạch có chọn lọc).
+### `/start`
 
-**Mẫu Báo Cáo Chuẩn:**
+**Mục đích:** Khởi tạo context cho dự án.
+**Hành động:**
 
-> **🎯 Goal:** Fix bug login fail
->
-> **🤖 Team:** `Debugger` (Root cause) → `Fullstack Dev` (Implementation)
-> **🛡️ Risk Check:** Low (Local UI fix only)
->
-> **📝 Changes:**
-> • `src/auth/hooks/useLogin.ts`: Thêm `try/catch` block.
-> • `src/components/LoginForm.tsx`: Hiển thị thông báo lỗi chi tiết.
->
-> **✅ Result:** Đã fix lỗi crash khi API timeout. User giờ sẽ thấy thông báo thay vì màn hình trắng.
+1.  Quét cấu trúc thư mục (`list_dir`).
+2.  Phát hiện tech stack (Next.js, Fastify, Python...).
+3.  In ra banner:
 
-✅ Format này giúp User hiểu **AI nào đang làm việc** và **đã thay đổi gì** mà không bị ngợp.
+```markdown
+╔════════════════════════════════════════════╗
+║ 🚀 ANCHI-KIT ACTIVATED ║
+╠════════════════════════════════════════════╣
+║ Project: [Tên folder] ║
+║ Stack: [Detected Stack] ║
+║ Ready: Type /do "your task" ║
+╚════════════════════════════════════════════╝
+```
 
 ---
 
-## 🧠 Smart Execution (Trí tuệ Ẩn)
+### `/do "..."` (UNIVERSAL COMMAND)
 
-Dù giao diện đơn giản, AI phải **ngầm** thực hiện quy trình phức tạp sau (User không cần thấy):
+**Mục đích:** Làm bất kỳ điều gì user yêu cầu.
+**Hành động:**
 
-1.  **Context Loading:**
-    - Project Rule: `.antigravity/docs/PROJECT.md`
-    - User Prefs: `.antigravity/user.yaml` (Optional, gitignored)
-2.  **Orchestration:** Tự động chọn Workflow & Agents từ `.antigravity/workflows/` và `.antigravity/agents/`.
-3.  **Risk Check:** Nếu sửa file nhạy cảm (Auth/Payment), **PHẢI** dừng lại hỏi ý kiến user.
-4.  **Artifacts:** Lưu các tài liệu quan trọng vào `.antigravity/docs/artifacts/`.
+1.  **Phân tích** yêu cầu:
+    - Keywords `bug`, `fix`, `error` → **Fix Mode**.
+    - Keywords `add`, `create`, `implement` → **Feature Mode**.
+    - Keywords `plan`, `design`, `research` → **Plan Mode**.
+2.  **Im lặng thực hiện** các tool calls cần thiết (`grep_search`, `view_file`, `write_to_file`, `replace_file_content`...).
+3.  **Báo cáo cuối cùng** theo Mission Control format.
 
-### 🚀 Infinite Scalability (Mở Rộng Không Giới Hạn)
+**⚠️ Safety:** Nếu yêu cầu liên quan đến Auth, Payment, Delete data → **HỎI USER TRƯỚC**.
 
-Bạn muốn dùng công nghệ mới chưa có trong template?
+---
 
-> **/skill-learn "[Tech Name]"**
->
-> _Ví dụ: `/skill-learn "Rust Lang"`, `/skill-learn "SvelteKit"`_
+### `/clean`
 
-AI sẽ tự động:
+**Mục đích:** Xóa context cũ, bắt đầu lại.
+**Hành động:**
 
-1.  **Research:** Đọc tài liệu online chuẩn nhất.
-2.  **Synthesize:** Tạo module kiến thức mới vào `.antigravity/skills/`.
-3.  **Apply:** Tự động dùng kiến thức mới cho các task sau này.
+1.  Thông báo: "🧹 Context đã được reset. Bạn có thể bắt đầu task mới."
 
 ---
 
-## ⚠️ Quy Tắc Bắt Buộc
+### `/demo`
+
+**Mục đích:** Chạy demo dự án.
+**Hành động:**
 
-1.  **Không Sáng Tạo Cấu Trúc:** Luôn tuân thủ folder structure của Preset.
-2.  **Hỏi Trước Khi Phá:** Nếu lệnh `/do` gây xóa dữ liệu hoặc đổi kiến trúc -> **CẢNH BÁO USER**.
-3.  **Tự Động Học:** Ghi nhận lỗi sai vào Active Memory để tránh lặp lại.
+1.  Tìm lệnh `dev` trong `package.json`.
+2.  Đề xuất: "Chạy `npm run dev` để xem demo."
 
 ---
 
-## 📂 Tài Liệu (Khi cần Context sâu)
+### `/help`
+
+**Mục đích:** Hiển thị các lệnh khả dụng.
+**Hành động:**
+
+1.  In ra bảng lệnh sau:
+
+| Lệnh      | Chức năng             |
+| --------- | --------------------- |
+| `/start`  | Khởi tạo dự án        |
+| `/do "…"` | Làm bất kỳ điều gì    |
+| `/clean`  | Reset context         |
+| `/demo`   | Chạy demo             |
+| `/help`   | Hiển thị trợ giúp này |
+
+---
+
+## � Mission Control Report Format
+
+Khi hoàn thành lệnh `/do`, CHỈ in ra đúng format này:
+
+```markdown
+📋 /do "[User Instruction]"
+══════════════════════════════════════
+⚙️ Mode: [Fix/Feature/Plan]
+🛡️ Risk: [Low/High]
+📝 Actions:
+• [Created/Modified/Deleted] path/to/file.ts
+• [Created/Modified/Deleted] path/to/other.ts
+✅ Result: [Tóm tắt kết quả].
+```
+
+---
+
+## 🔇 Silence Protocol
+
+Khi thực hiện lệnh `/do`:
+
+- **KHÔNG** in "Đang phân tích...", "Đọc file...", "Tìm kiếm...".
+- **KHÔNG** giải thích kế hoạch trước khi làm.
+- **CHỈ** gọi tool và in báo cáo cuối cùng.
+
+---
 
-AI có thể tham khảo (User không cần đọc):
+## 📂 Reference (AI có thể đọc nếu cần)
 
-- `.antigravity/docs/` (Project Docs)
-- `.antigravity/workflows/do.md` (Workflow Logic full)
-- `.antigravity/agent-skill-index.yaml` (Capabilities)
+- `.antigravity/agents/` - Persona details.
+- `.antigravity/skills/` - Domain knowledge.
+- `.antigravity/.ai-memory/` - Project history (gitignored).

package/README.md

@@ -1,4 +1,4 @@
-# 💎 Anchi Kit v1.1.4
+# 💎 Anchi Kit v1.1.7
 
 > **Hệ Điều Hành Tư Duy cho AI Code Editor (Cursor, Gemini, Windsurf)**  
 > _Biến AI từ người thợ code (Coder) thành Kỹ sư trưởng (Senior Tech Lead)._

package/docs/ROADMAP.md

@@ -100,13 +100,16 @@ Official release of Anchi Kit v1.0.0 với Dynamic Orchestration v2.0.
 ## 📊 Version Summary
 
 | Version | Status      | Highlights                                                    |
-| ------- | ----------- | ------------------------------------------------------------- | --- |
+| ------- | ----------- | ------------------------------------------------------------- |
 | v1.0.0  | ✅ Released | 22 commands, 21 agents, 55 skills, Dynamic Orchestration v2.0 |
 | v1.1.0  | ✅ Released | Team Support, Hive Mind (Git Sync)                            |
 | v1.1.1  | ✅ Released | Secure Install, IDE Auto-Detect, Policy Assurance             |
 | v1.1.2  | ✅ Released | Fix: npm register conflict resolution                         |
 | v1.1.3  | ✅ Released | Fix: Missing source files in package                          |
-| v1.1.4  | ✅ Released | UX Refinement: Capability-Driven Installation                 |     |
+| v1.1.4  | ✅ Released | UX Refinement: Capability-Driven Installation                 |
+| v1.1.5  | ✅ Released | Stability: Simplified /do command logic                       |
+| v1.1.6  | ✅ Released | Antigravity: Embedded command interception in system prompt   |
+| v1.1.7  | ✅ Released | Simplified Installation: One-click FULL install               |
 | v1.2+   | 🔮 Future   | Voice commands, VS Code extension, Multi-repo                 |
 
 ---

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "anchi-kit",
-  "version": "1.1.4",
+  "version": "1.1.7",
   "description": "The Ultimate AI-Native Toolkit for Cursor & Gemini. Installs into any existing project. Includes commands, agents, skills, and architecture presets.",
   "main": "src/cli.js",
   "bin": {

package/src/commands/init.js

@@ -180,78 +180,28 @@ async function init() {
         log.success(`   💡 Suggested skills: ${suggestedSkills.join(', ')}`);
     }
 
-    // Step 2: Select Capabilities (Professional UX)
-    const { getCapabilities, resolveCapabilities, getInstallEstimate } = require('../lib/profiles');
-    const capabilities = getCapabilities();
-    
-    const capOptions = capabilities.map(c => ({
-        label: `${c.label} - ${colors.gray}${c.description}${colors.reset}`,
-        value: c.key,
-        default: c.default
-    }));
-
-    const selectedKeys = await askMultiSelect('What capabilities do you need?', capOptions);
-    
-    if (selectedKeys.includes('custom')) {
-        // Fallback logic if needed, but for now we trust the multiselect
-    }
-
-    const finalConfig = resolveCapabilities(selectedKeys);
-
-    // Step 3: Customize (Optional Add-ons)
-    const customize = await ask(`\n${colors.yellow}Advanced options? (y/N): ${colors.reset}`);
-    
-    if (customize.toLowerCase() === 'y') {
-        const packs = getSkillPackList();
-        const packOptions = packs.map(p => ({
-            label: `${p.name} (${p.skillCount} skills)`,
-            value: p.key,
-            default: false,
-        }));
-
-        const selectedPacks = await askMultiSelect('Add extra skill packs:', packOptions);
-        if (selectedPacks.length > 0) {
-            const extraSkills = resolveSkillPacks(selectedPacks);
-            finalConfig.skills = [...new Set([...finalConfig.skills, ...extraSkills])];
-        }
-
-        if (!finalConfig.includePresets) {
-            const inc = await ask(`Include architecture presets? (y/N): `);
-            finalConfig.includePresets = inc.toLowerCase() === 'y';
-        }
-    }
-
-    // Step 4: Size preview
+    // ==========================================================================
+    // SIMPLIFIED: Full Install by Default (No Capability Selection)
+    // ==========================================================================
+    const finalConfig = {
+        commands: 'all',
+        agents: 'all',
+        skills: 'all',
+        includePresets: true,
+        includeDocs: true
+    };
+
+    // Show preview
     console.log('');
-    log.warn('📊 Install Preview:');
-    const components = getComponentPaths(finalConfig, kitPath);
-    const sizeInfo = calculateInstallSize(kitPath, components);
-
-    console.log(`   Files: ~${sizeInfo.files}`);
-    console.log(`   Size: ~${sizeInfo.formatted}`);
-    console.log('');
-    log.info('   Components:');
-
-    if (finalConfig.commands === 'all') {
-        log.success('   ✓ All commands');
-    } else {
-        log.success(`   ✓ Commands: ${finalConfig.commands.join(', ')}`);
-    }
-
-    if (finalConfig.agents === 'all' || (Array.isArray(finalConfig.agents) && finalConfig.agents.length > 0)) {
-        log.success(`   ✓ Agents: ${finalConfig.agents === 'all' ? 'All' : finalConfig.agents.length + ' agents'}`);
-    }
-
-    if (finalConfig.skills === 'all' || (Array.isArray(finalConfig.skills) && finalConfig.skills.length > 0)) {
-        log.success(`   ✓ Skills: ${finalConfig.skills === 'all' ? 'All' : finalConfig.skills.length + ' skills'}`);
-    }
-
-    if (finalConfig.includePresets) log.success('   ✓ Presets');
-    if (finalConfig.includeDocs) log.success('   ✓ Docs');
+    log.warn('📦 Full Installation:');
+    log.success('   ✓ All 22 commands');
+    log.success('   ✓ All 21 agents');
+    log.success('   ✓ All 55+ skills');
+    log.success('   ✓ Presets & Docs');
 
-    // Step 5: Confirm
+    // Confirm
     console.log('');
-    const confirm = await ask(`${colors.yellow}Proceed with installation? (Y/n): ${colors.reset}`);
+    const confirm = await ask(`${colors.yellow}Proceed with FULL installation? (Y/n): ${colors.reset}`);
 
     if (confirm.toLowerCase() === 'n') {
         log.error('❌ Cancelled.');
@@ -396,7 +346,7 @@ async function init() {
         registerProject(targetPath, {
             name: path.basename(targetPath),
             tech_stack: Object.keys(detected).filter(k => detected[k]),
-            architecture: selectedKeys.join('+'),
+            architecture: 'full',
             installed_at: new Date().toISOString(),
             env: installName
         });