anchi-toolkit 1.0.0 → 1.2.1

package/.antigravity/workflows/help.md

@@ -29,7 +29,7 @@ argument-hint: [optional: command name]
 ## Output
 
 ```
-📚 anchi-kit v3.0.0 - Command Reference
+📚 anchi-toolkit v1.0.0 - Command Reference
 
 ═══════════ ESSENTIAL (5) ═══════════
 
@@ -55,6 +55,13 @@ argument-hint: [optional: command name]
 /integrate "..."    Third-party integrations
 /memory             Context management
 
+═══════════ META (4) ═══════════
+
+/config             View/edit config
+/audit              AI decision logs
+/migrate            Preset migration
+/why                Explain AI decisions
+
 ═══════════ QUICK START ═══════════
 
 Beginner:
@@ -96,7 +103,7 @@ Examples:
 ## Agent & Skill Activation
 
 **Primary Agents:**
-- `.antigravity/agents/docs-manager.md` - Command info
+- `.cursor/agents/docs-manager.md` - Command info
 
 **Skills:**
 - `document-skills/` - Help content
@@ -111,10 +118,10 @@ Examples:
 > **AI MUST read orchestration config before execution**
 
 ```
-1. READ .antigravity/agent-skill-index.yaml
+1. READ .cursor/agent-skill-index.yaml
 2. CHECK command_mapping for this command
 3. APPLY skill activation rules
-4. CHECK .antigravity/failure-modes.yaml
+4. CHECK .cursor/failure-modes.yaml
 5. LOG decision to .ai-audit/
 ```
 

package/.antigravity/workflows/skill-learn.md

@@ -0,0 +1,48 @@
+---
+description: 🧠 Teach AI new skills from the web
+argument-hint: [skill name / tech stack]
+---
+
+# /skill-learn - Infinite Knowledge
+
+**What:** Crawls documentation and creates a new Skill Module dynamically.
+
+## Logic
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│ 🧠 /skill-learn - KNOWLEDGE ACQUISITION                     │
+├─────────────────────────────────────────────────────────────┤
+│                                                             │
+│  [1] ANALYZE REQUEST: "Learn Rust"                          │
+│      ├── Identify Tech: Rust Language                       │
+│      └── Identify Goal: syntax, best practices, packaging   │
+│                                                             │
+│  [2] RESEARCH (Agent: Researcher):                          │
+│      ├── Search Official Docs (rust-lang.org)               │
+│      ├── Search Popular Patterns (Awesome Rust)             │
+│      └── Extract: "Do's & Don'ts", "Snippet Patterns"       │
+│                                                             │
+│  [3] SYNTHESIZE (Agent: Docs-Manager):                      │
+│      ├── Template: .cursor/skills/_template.md             │
+│      ├── Fill: Rules, File Patterns, Dependencies           │
+│      └── Create: .cursor/skills/rust-development/README.md  │
+│                                                             │
+│  [4] REGISTER:                                              │
+│      ├── Append to: .cursor/agent-skill-index.yaml          │
+│      └── Map to: fullstack-developer (or create new role)   │
+│                                                             │
+│  [5] OUTPUT:                                                │
+│      "✅ Learned Skill: Rust Development                    │
+│       Activated for *.rs files."                            │
+│                                                             │
+└─────────────────────────────────────────────────────────────┘
+```
+
+## Usage
+
+```
+/skill-learn "Tailwind CSS"
+/skill-learn "Go Fiber Framework"
+/skill-learn "Solidity Smart Contracts"
+```

package/.antigravity/workflows/start.md

@@ -1,135 +1,56 @@
 ---
-description: ⚡⚡⚡⚡ Bắt đầu sử dụng anchi-kit - Entry point cho mọi dự án
+description: 🚀 Start/Resume project with Context Recall
+argument-hint: [optional: new project name]
 ---
 
-# INSTRUCTION: Follow this workflow exactly
+# /start - Project Intelligence
 
-> ⛔ **CRITICAL: PAUSE POINTS**
-> 
-> This command has MULTIPLE decision points where you MUST STOP.
-> 
-> At each decision point:
-> 1. **ONLY show the question** - No other actions
-> 2. **DO NOT call any tools** in parallel with the question
-> 3. **WAIT for user's number input** before proceeding
-> 4. **DO NOT assume or decide** for the user
->
-> Decision points:
-> - STEP 1: Ask "1 or 2" (existing vs new project) → STOP
-> - STEP 2B: Ask "1, 2, or 3" (preset selection) → STOP
+**What:** Initialize project or RESUME work with context awareness.
 
----
-
-## ▶️ STEP 1: Show Welcome (⛔ STOP HERE)
-
-**Show ONLY this, then STOP:**
-
-```
-👋 Chào mừng đến với anchi-kit!
-
-Tôi sẽ giúp bạn setup dự án. Chỉ cần trả lời 1 câu hỏi:
-
-📂 Dự án của bạn là:
-  1️⃣ Dự án có sẵn - Đã có code
-  2️⃣ Dự án mới - Bắt đầu từ đầu
-
-👉 Gõ 1 hoặc 2:
-```
-
-⛔ **STOP. Wait for user to type 1 or 2. Do not proceed until user responds.**
-
----
-
-## ▶️ STEP 2A: Existing Project (User typed "1")
-
-If user typed 1, proceed with scanning:
-
-### Phase 1: Deploy Scout Agents
-Spawn scout agents to scan codebase in parallel.
-
-### Phase 2: Activate Skills
-Based on detected tech stack.
-
-### Phase 3: Auto-Detect Preset
-Analyze and suggest preset.
-
-### Phase 4: Fill Docs
-Generate project documentation.
-
----
-
-## ▶️ STEP 2B: New Project (User typed "2") (⛔ STOP HERE)
-
-If user typed 2, **show ONLY this, then STOP:**
+## Logic (The "Brain")
 
 ```
-📂 Bạn chọn: 2️⃣ Dự án mới
-
-📋 Chọn Architecture Preset:
-
 ┌─────────────────────────────────────────────────────────────┐
-│ 1️⃣ 🚀 RAPID MVP                                             │
-│    SQLite | Flat structure | Skip tests OK                 │
-│    Best for: Prototype, demo, hackathon                    │
-│    ⏱️ ~5 min setup                                          │
+│ 🧠 /start - PROJECT RECALL                                  │
 ├─────────────────────────────────────────────────────────────┤
-│ 2️⃣ 💼 PROFESSIONAL                                          │
-│    PostgreSQL | Modular | Tests required                   │
-│    Best for: Startup, production app                       │
-│    ⏱️ ~10 min setup                                         │
-├─────────────────────────────────────────────────────────────┤
-│ 3️⃣ 🏢 ENTERPRISE                                            │
-│    PostgreSQL + Redis | DDD | Full compliance              │
-│    Best for: Large project, regulated industry             │
-│    ⏱️ ~20 min setup                                         │
+│                                                             │
+│  [1] CHECK: Is this a new project?                          │
+│      ├── YES → Show Preset Selection (Rapid/Pro/Enterprise) │
+│      └── NO  → Activate RECALL MODE                         │
+│                                                             │
+│  [2] RECALL MODE (The "Wow" Factor):                        │
+│      ├── READ: .ai-memory/feature_status.json              │
+│      ├── READ: .ai-audit/latest.jsonl                       │
+│      └── ANALYZE: What was the last active task?            │
+│                                                             │
+│  [3] OUTPUT:                                                │
+│      "Welcome back! 👋                                      │
+│       Last time we were working on [Task Name].             │
+│       Status: [In Progress/Done]                            │
+│       Files: [Active Files]                                 │
+│                                                             │
+│       👉 Continue? [Y]es / [C]hange Task"                   │
+│                                                             │
 └─────────────────────────────────────────────────────────────┘
-
-👉 Gõ 1, 2, hoặc 3:
 ```
 
-⛔ **STOP. Wait for user to type 1, 2, or 3. Do not proceed until user responds.**
+## Setup Steps (New Project)
 
----
+If folder is empty:
 
-## ▶️ STEP 3: Execute Preset Setup
+1. Detect Tech Stack (Node, Python, Go...)
+2. Suggest Best Preset
+3. Run `npx anchi-toolkit init`
 
-After user selects preset (1/2/3):
+## Memory Schema (For Recall)
 
-1. Create project folder if needed
-2. Initialize project with selected preset
-3. Copy preset-specific .cursorrules
-4. Setup documentation templates
-5. Show completion message
-
----
-
-## Agent & Skill Summary
-
-| Agent | Role |
-|-------|------|
-| `scout` | Scan codebase |
-| `researcher` | Deep analysis |
-| `planner` | Preset detection |
-| `docs-manager` | Fill templates |
-
-| Detected Tech | Skills |
-|---------------|--------|
-| Next.js/React | `frontend-development/` |
-| Prisma/DB | `databases/` |
-| TailwindCSS | `ui-styling/` |
-
----
-
-## Dynamic Orchestration
-
-> **AI MUST read orchestration config before execution**
+AI looks for `.ai-memory/session.json`:
 
+```json
+{
+  "last_active": "2024-12-27T10:00:00Z",
+  "current_task": "Dashboard UI Implementation",
+  "active_files": ["src/dashboard.tsx", "src/api.ts"],
+  "next_step": "Implement chart component"
+}
 ```
-1. READ .antigravity/agent-skill-index.yaml
-2. CHECK command_mapping for this command
-3. APPLY skill activation rules
-4. CHECK .antigravity/failure-modes.yaml
-5. LOG decision to .ai-audit/
-```
-
-📖 [docs/ORCHESTRATION_RUNTIME.md](../docs/ORCHESTRATION_RUNTIME.md)

package/.antigravity/workflows/status.md

@@ -92,11 +92,11 @@ argument-hint: [optional: specific area]
   2. Update 3 outdated dependencies
   
 💡 Suggestions:
-  • /test:coverage - View coverage details
-  • /fix "update dependencies"
-  • /cook "payment-integration Phase 3"
+  • /test --coverage - View coverage details
+  • /do "update dependencies"
+  • /do "payment-integration Phase 3"
 
-📌 Next: /auto:pro "continue payment integration"
+📌 Next: /do "continue payment integration"
 ```
 
 ---
@@ -119,8 +119,8 @@ argument-hint: [optional: specific area]
 ## Agent & Skill Activation
 
 **Agents:**
-- `.antigravity/agents/project-manager.md` - Status overview
-- `.antigravity/agents/scout.md` - Code analysis
+- `.cursor/agents/project-manager.md` - Status overview
+- `.cursor/agents/scout.md` - Code analysis
 
 **Skills:**
 - `devops/` - Build and deploy
@@ -153,10 +153,10 @@ status:
 > **AI MUST read orchestration config before execution**
 
 ```
-1. READ .antigravity/agent-skill-index.yaml
+1. READ .cursor/agent-skill-index.yaml
 2. CHECK command_mapping for this command
 3. APPLY skill activation rules
-4. CHECK .antigravity/failure-modes.yaml
+4. CHECK .cursor/failure-modes.yaml
 5. LOG decision to .ai-audit/
 ```
 

package/.antigravity/workflows/undo.md

@@ -61,14 +61,14 @@ argument-hint: [optional: steps to undo or commit hash]
 ╔═════════════════════════════════════════════════════════════╗
 ║ # │ Time     │ Action            │ Files Changed            ║
 ╠═════════════════════════════════════════════════════════════╣
-║ 1 │ 2 min    │ /cook LoginForm   │ 3 files                  ║
-║ 2 │ 10 min   │ /generate:api     │ 2 files                  ║
+║ 1 │ 2 min    │ /do LoginForm     │ 3 files                  ║
+║ 2 │ 10 min   │ /generate --api   │ 2 files                  ║
 ║ 3 │ 15 min   │ /theme dark       │ 2 files                  ║
-║ 4 │ 30 min   │ /auto:rapid       │ 8 files                  ║
+║ 4 │ 30 min   │ /do "feature"     │ 8 files                  ║
 ╚═════════════════════════════════════════════════════════════╝
 
 📋 Latest Action Details (#1):
-  Command: /cook "Add LoginForm"
+  Command: /do "Add LoginForm"
   Time: 2 minutes ago
   
   Files to restore:
@@ -132,7 +132,7 @@ argument-hint: [optional: steps to undo or commit hash]
 ## Agent & Skill Activation
 
 **Agents:**
-- `.antigravity/agents/git-manager.md` - Git operations
+- `.cursor/agents/git-manager.md` - Git operations
 
 **Skills:**
 - `devops/` - Version control
@@ -156,10 +156,10 @@ undo:
 > **AI MUST read orchestration config before execution**
 
 ```
-1. READ .antigravity/agent-skill-index.yaml
+1. READ .cursor/agent-skill-index.yaml
 2. CHECK command_mapping for this command
 3. APPLY skill activation rules
-4. CHECK .antigravity/failure-modes.yaml
+4. CHECK .cursor/failure-modes.yaml
 5. LOG decision to .ai-audit/
 ```
 

package/.cursor/agent-skill-index.yaml

@@ -38,6 +38,7 @@ agents:
       - error_analysis
       - performance_diagnosis
       - log_analysis
+      - interactive_probing # Inject logs -> Test -> Analyze
     boundaries:
       - NOT: code_writing → fullstack-developer
     primary_skills:
@@ -141,6 +142,7 @@ agents:
       - devops
     typical_commands:
       - /do (deployment-related)
+      - /demo
       
   git-manager:
     capabilities:
@@ -183,6 +185,7 @@ agents:
       - web-search
     typical_commands:
       - /scout --external
+      - /skill-learn
       
   scout:
     capabilities:
@@ -197,6 +200,7 @@ agents:
       - task_breakdown
       - estimation
       - dependency_analysis
+      - parallel_workstream_planning
     typical_commands:
       - /do --plan-only
       
@@ -207,6 +211,36 @@ agents:
       - team_coordination
     typical_commands:
       - /status
+      
+  # ─────────────────────── Optimization ───────────────────────
+  failure-analyst:
+    capabilities:
+      - root_cause_analysis
+      - pattern_recognition
+    typical_commands:
+      - /audit
+      
+  rules-architect:
+    capabilities:
+      - rule_definition
+      - failure_mode_prevention
+    escalation_from:
+      - failure-analyst
+
+  # ─────────────────────── Intelligence ───────────────────────
+  graph-architect:
+    capabilities:
+      - dependency_analysis
+      - graph_maintenance
+    typical_commands:
+      - /do (refactor)
+
+  trend-watcher:
+    capabilities:
+      - trend_monitoring
+      - skill_updates
+    typical_commands:
+      - /skill-learn --auto
 
 # ═══════════════════════════════════════════════════════════════
 # SKILL INDEX
@@ -385,3 +419,8 @@ command_mapping:
     default: docs-manager
     skills:
       - document-skills
+
+  /config:
+    default: project-manager
+    skills:
+      - document-skills

package/.cursor/agents/graph-architect.md

@@ -0,0 +1,30 @@
+---
+name: graph-architect
+description: Agent chuyên gia về cấu trúc đồ thị và phân tích phụ thuộc (Dependency Graph).
+role: Knowledge Graph Manager
+capabilities:
+  - dependency_analysis
+  - impact_assessment
+  - refactor_planning
+  - circular_dependency_detection
+
+boundaries:
+  - condition: "Always ensure graph consistency before committing changes"
+  - condition: "Do not modify code logic, only structure analysis"
+
+instruction: |
+  Bạn là Graph Architect. Nhiệm vụ của bạn là xây dựng và duy trì 'Knowledge Graph' (Đồ thị kiến thức) của dự án.
+
+  Khi dev muốn refactor một module lớn, bạn phải:
+  1.  Scan toàn bộ codebase để tìm các node phụ thuộc (Function calls, Improvements).
+  2.  Vẽ ra bản đồ tác động (Impact Map).
+  3.  Cảnh báo nếu thay đổi A làm gãy B, C ở file khác.
+
+  Format báo cáo:
+  ```mermaid
+  graph TD
+      A[AuthService] -->|calls| B[Database]
+      C[LoginComponent] -->|imports| A
+      D[RegisterComponent] -->|imports| A
+  ```
+---

package/.cursor/agents/trend-watcher.md

@@ -0,0 +1,24 @@
+---
+name: trend-watcher
+description: Agent chuyên theo dõi xu hướng công nghệ và cập nhật kiến thức cho hệ thống.
+role: Tech Trend Scout
+capabilities:
+  - web_scraping (release notes)
+  - skill_synthesis
+  - breaking_change_detection
+  - documentation_update
+
+boundaries:
+  - condition: "Never update dependencies automatically if 'major version' changes without approval"
+  - condition: "Verify source credibility (Official Docs, GitHub Releases)"
+
+instruction: |
+  Bạn là Trend Watcher. Nhiệm vụ của bạn là đảm bảo kiến thức của Anchi Toolkit không bao giờ lỗi thời.
+
+  Quy trình làm việc (Weekly):
+  1.  Check version mới nhất của các thư viện core (Next.js, React, Tailwind).
+  2.  Đọc Changelog/Release Notes.
+  3.  Nếu có Breaking Change hoặc Feature mới hay ho -> Tạo Pull Request để update vào thư mục `.cursor/skills/`.
+
+  Ví dụ: "Next.js 15 ra mắt `run` prop mới" -> Update skill `nextjs-development`.
+---

package/.cursor/commands/config.md

@@ -0,0 +1,144 @@
+---
+description: ⚡⚡ View and edit anchi-toolkit configuration
+argument-hint: [optional: --edit | --reset | key=value]
+---
+
+# /config - Configuration Management
+
+**What:** View and edit anchi-toolkit.config.yaml settings.
+
+## Usage
+```
+/config                        # Show current config
+/config --edit                 # Open config in editor
+/config preset=professional    # Change specific setting
+/config --reset                # Reset to defaults
+```
+
+---
+
+## 💰 Model Selection
+
+| Action | Recommended Model | Cost |
+|--------|-------------------|------|
+| View config | GPT-5.1 Codex Mini | 💚 Low |
+| Edit config | GPT-5.1 Codex Mini | 💚 Low |
+
+> Config operations are simple - always use cheapest models.
+
+---
+
+## Output
+
+```
+⚙️ /config
+
+═══════════ ANCHI-TOOLKIT CONFIG ═══════════
+
+📂 File: .cursor/anchi-toolkit.config.yaml
+
+┌─────────────────────────────────────────────────────────────┐
+│ CURRENT SETTINGS                                            │
+├─────────────────────────────────────────────────────────────┤
+│                                                             │
+│ 📋 Preset: professional                                     │
+│ 🤖 Agents: all (19 agents)                                  │
+│ 🛠️ Skills: all (35 skills)                                  │
+│ 📦 Commands: all (18 commands)                              │
+│                                                             │
+│ ⚙️ Settings:                                                │
+│   ├── auto_commit: false                                    │
+│   ├── auto_test: true                                       │
+│   ├── language: vi                                          │
+│   └── model_preference: cost-optimized                      │
+│                                                             │
+└─────────────────────────────────────────────────────────────┘
+
+💡 Quick Commands:
+  /config preset=rapid           # Switch preset
+  /config auto_commit=true       # Enable auto-commit
+  /config --edit                 # Full editor mode
+```
+
+---
+
+## Editable Settings
+
+| Key | Values | Default |
+|-----|--------|---------|
+| `preset` | rapid, professional, enterprise | professional |
+| `auto_commit` | true, false | false |
+| `auto_test` | true, false | true |
+| `language` | en, vi | vi |
+| `model_preference` | cost-optimized, balanced, quality | cost-optimized |
+
+---
+
+## Flags
+
+| Flag | Action |
+|------|--------|
+| `--edit` | Open config file in editor |
+| `--reset` | Reset to default settings |
+| `--show-all` | Show all available options |
+| `--validate` | Validate config syntax |
+
+---
+
+## Config File Location
+
+```
+.cursor/anchi-toolkit.config.yaml    # Cursor AI
+.antigravity/anchi-toolkit.config.yaml  # Antigravity
+```
+
+---
+
+## Example Config
+
+```yaml
+# anchi-toolkit.config.yaml
+preset: professional
+
+agents: all  # or list: [fullstack-developer, debugger]
+skills: all  # or list: [databases, frontend-development]
+commands: all
+
+settings:
+  auto_commit: false
+  auto_test: true
+  language: vi
+  model_preference: cost-optimized
+  
+overrides:
+  test_coverage_threshold: 80
+  max_file_changes: 20
+```
+
+---
+
+## Agent & Skill Activation
+
+**Primary Agents:**
+- `.cursor/agents/project-manager.md` - Config management
+
+**Skills:**
+- `document-skills/` - Config parsing
+
+> Config uses minimal AI - mostly file operations.
+
+---
+
+## 🔄 Dynamic Orchestration
+
+> **AI MUST read orchestration config before execution**
+
+```
+1. READ .cursor/agent-skill-index.yaml
+2. CHECK command_mapping for this command
+3. APPLY skill activation rules
+4. CHECK .cursor/failure-modes.yaml
+5. LOG decision to .ai-audit/
+```
+
+📖 [docs/ORCHESTRATION_RUNTIME.md](../docs/ORCHESTRATION_RUNTIME.md)

package/.cursor/commands/demo.md

@@ -0,0 +1,50 @@
+---
+description: 📺 One-Click Demo / Preview
+argument-hint: [optional: port]
+---
+
+# /demo - Instant Preview
+
+**What:** Auto-detects and runs the project dev server.
+
+## Logic
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│ 📺 /demo - AUTO LAUNCHER                                    │
+├─────────────────────────────────────────────────────────────┤
+│                                                             │
+│  [1] SCAN: package.json scripts                             │
+│      ├── Look for: "dev", "start", "serve", "preview"       │
+│      └── Priority: dev > start > serve                      │
+│                                                             │
+│  [2] CHECK PORT:                                            │
+│      ├── Default: 3000, 8080, 5173                          │
+│      └── Check if port is in use (kill if needed?)          │
+│                                                             │
+│  [3] EXECUTE:                                               │
+│      Run detected command (e.g., `npm run dev`)             │
+│                                                             │
+│  [4] VERIFY:                                                │
+│      Wait for "Ready" or "Listening" in stdout              │
+│                                                             │
+│  [5] OUTPUT:                                                │
+│      "🚀 Project is LIVE!                                   │
+│       👉 http://localhost:3000                              │
+│       (Ctrl+C to stop)"                                     │
+│                                                             │
+└─────────────────────────────────────────────────────────────┘
+```
+
+## Agent Capabilities
+
+- **Agent:** `devops-engineer` or `fullstack-developer`
+- **Skill:** `terminal-management`
+
+## Usage
+
+```
+/demo           # Auto-detect and run
+/demo 8080      # Run on specific port (if supported)
+/demo --prod    # Run production build
+```