moai-adk 0.5.2__py3-none-any.whl → 0.5.6__py3-none-any.whl

moai_adk/templates/.claude/agents/alfred/tdd-implementer.md

@@ -18,6 +18,24 @@ You are a TDD expert who strictly adheres to the RED-GREEN-REFACTOR cycle and ke
 **Role**: Executor who translates implementation plans into actual code
 **Goal**: 100% test coverage and compliance with TRUST principles Code generation
 
+## 🌍 Language Handling
+
+**IMPORTANT**: You will ALWAYS receive prompts in **English**, regardless of user's original conversation language.
+
+Alfred translates SPEC references and implementation requirements to English before invoking you. This ensures:
+- ✅ Perfect skill trigger matching (English Skill names match English requests 100%)
+- ✅ Consistent TDD cycle communication
+- ✅ Global multilingual support
+
+**Example**:
+- User says (any language): Translated to "Implement JWT-based authentication following SPEC-AUTH-001"
+- You receive (English): "Implement user authentication with JWT tokens, 30-minute expiry, email+password login"
+- You implement entirely in English-documented code
+- Test cases use English variable names and descriptions
+- Alfred translates status updates back to user's language for response
+
+**Do not try to infer user's original language.** Always work in English, use English in code comments, test descriptions, and commit messages.
+
 ## 🧰 Required Skills
 
 **Automatic Core Skills**

moai_adk/templates/.claude/agents/alfred/trust-checker.md

@@ -18,6 +18,12 @@ You are the agent responsible for the TRUST 5 principles, code standards, and se
 **Role**: QA lead who comprehensively verifies code quality, security, performance, and traceability based on TRUST 5 principles
 **Goal**: Differential scan Efficient and accurate quality assurance and improvement direction suggested through the system (Level 1→2→3)
 
+## 🌍 Language Handling
+
+**IMPORTANT**: You will ALWAYS receive prompts in **English**, regardless of user's original conversation language.
+
+Alfred translates quality verification requests to English before invoking you. Your reports use English terminology.
+
 ## 🧰 Required Skills
 
 **Automatic Core Skills**

moai_adk/templates/.claude/commands/alfred/0-project.md

@@ -1,6 +1,10 @@
 ---
 name: alfred:0-project
-description: Initialize project document - create product/structure/tech.md and set optimization for each language
+description: "Initialize project document - create product/structure/tech.md and set optimization for each language"
+# Translations:
+# - ko: "프로젝트 문서 초기화 - product/structure/tech.md 생성 및 언어별 최적화 설정"
+# - ja: "プロジェクト文書の初期化 - product/structure/tech.mdの作成と言語別最適化設定"
+# - zh: "初始化项目文档 - 创建product/structure/tech.md并设置语言优化"
 allowed-tools:
   - Read
   - Write

moai_adk/templates/.claude/commands/alfred/1-plan.md

@@ -1,6 +1,10 @@
 ---
 name: alfred:1-plan
-description: Planning (brainstorming, plan writing, design discussion) + Branch/PR creation
+description: "Planning (brainstorming, plan writing, design discussion) + Branch/PR creation"
+# Translations:
+# - ko: "계획 수립 (브레인스토밍, 설계 논의) + 브랜치/PR 생성"
+# - ja: "計画策定（ブレインストーミング、設計議論）+ ブランチ/PR作成"
+# - zh: "规划（头脑风暴、设计讨论）+ 分支/PR创建"
 argument-hint: "Title 1 Title 2 ... | SPEC-ID modifications"
 allowed-tools:
   - Read

moai_adk/templates/.claude/commands/alfred/2-run.md

@@ -1,7 +1,11 @@
 ---
 name: alfred:2-run
-description: "Implement all SPECs with SPEC ID to implement (e.g. SPEC-001) or all - Execute planned work (TDD implementation, prototyping, documentation, etc.)" 
-argument-hint: "SPEC-ID - All with SPEC ID to implement (e.g. SPEC-001) or all “SPEC Implementation”
+description: "Execute planned work (TDD implementation, prototyping, documentation, etc.)"
+# Translations:
+# - ko: "계획된 작업 실행 (TDD 구현, 프로토타이핑, 문서화 등)"
+# - ja: "計画されたタスクの実行（TDD実装、プロトタイピング、ドキュメント作成など）"
+# - zh: "执行计划任务（TDD实现、原型开发、文档编写等）"
+argument-hint: "SPEC-ID - All with SPEC ID to implement (e.g. SPEC-001) or all \"SPEC Implementation\""
 allowed-tools:
   - Read
   - Write

moai_adk/templates/.claude/commands/alfred/3-sync.md

@@ -1,6 +1,10 @@
 ---
 name: alfred:3-sync
-description: Document synchronization + PR Ready conversion
+description: "Document synchronization + PR Ready conversion"
+# Translations:
+# - ko: "문서 동기화 + PR Ready 전환"
+# - ja: "ドキュメント同期 + PR Ready変換"
+# - zh: "文档同步 + PR Ready转换"
 argument-hint: "Mode target path - Mode: auto (default)|force|status|project, target path: Synchronization target path"
 allowed-tools:
   - Read
@@ -99,7 +103,9 @@ Users can run the command as follows:
 
 Analyze project status to determine synchronization scope, develop a systematic synchronization plan, and receive user confirmation.
 
-**The doc-syncer agent automatically scans the TAG chain and identifies and analyzes Git changes.**
+**The tag-agent performs comprehensive TAG verification (full project scope), and doc-syncer analyzes Git changes and establishes synchronization plan.**
+
+⚠️ **Important**: Tag-agent must verify the ENTIRE PROJECT for TAG orphans, not just changed files. Full-project scope is MANDATORY.
 
 ### 🔍 TAG chain navigation (optional)
 
@@ -129,12 +135,27 @@ Invoking the Task tool (Explore agent):
 **In STEP 1, call doc-syncer and tag-agent using the Task tool**:
 
 ```
-1. Tag-agent call (TAG verification):
+1. Tag-agent call (TAG verification - FULL PROJECT SCOPE):
    - subagent_type: "tag-agent"
-- description: "Verify TAG system"
- - prompt: "Please verify the integrity of the entire TAG chain.
- Please verify the integrity of @SPEC, @TEST, @CODE, @DOC TAGs
- and orphan TAGs.
+- description: "Verify TAG system across entire project"
+ - prompt: "Please perform a COMPREHENSIVE TAG system verification across the ENTIRE PROJECT.
+
+ **Required scope**: Scan all source files, not just changed files.
+
+ **Verification items**:
+ 1. @SPEC TAGs in .moai/specs/ directory
+ 2. @TEST TAGs in tests/ directory
+ 3. @CODE TAGs in src/ directory
+ 4. @DOC TAGs in docs/ directory
+
+ **Orphan detection** (MANDATORY):
+ - Detect @CODE TAGs without matching @SPEC
+ - Detect @SPEC TAGs without matching @CODE
+ - Detect @TEST TAGs without matching @SPEC
+ - Detect @DOC TAGs without matching @SPEC/@CODE
+
+ **Output format**: Provide complete list of orphan TAGs with locations.
+
  (Optional) Explore results: $EXPLORE_RESULTS"
 
 2. doc-syncer call (synchronization plan):

moai_adk/templates/.claude/hooks/alfred/alfred_hooks.py

@@ -118,7 +118,11 @@ def main() -> None:
     try:
         # Read JSON from stdin
         input_data = sys.stdin.read()
-        data = json.loads(input_data)
+        # Handle empty stdin gracefully (return empty dict)
+        if not input_data or not input_data.strip():
+            data = {}
+        else:
+            data = json.loads(input_data)
 
         cwd = data.get("cwd", ".")
 

moai_adk/templates/.claude/output-styles/alfred/agentic-coding.md

@@ -1,6 +1,10 @@
 ---
 name: Agentic Coding
-description: Agent-based coding mode that integrates hands-on development and collaboration
+description: "Agent-based coding mode that integrates hands-on development and collaboration"
+# Translations:
+# - ko: "실무 개발과 협업을 통합하는 에이전트 기반 코딩 모드"
+# - ja: "実務開発とコラボレーションを統合するエージェントベースのコーディングモード"
+# - zh: "集成实战开发和协作的基于代理的编码模式"
 ---
 
 # Agentic Coding

moai_adk/templates/.claude/output-styles/alfred/moai-adk-learning.md

@@ -1,6 +1,10 @@
 ---
 name: MoAI ADK Learning
-description: Learning mode to easily learn MoAI-ADK concepts and workflow
+description: "Learning mode to easily learn MoAI-ADK concepts and workflow"
+# Translations:
+# - ko: "MoAI-ADK 개념과 워크플로우를 쉽게 학습하는 학습 모드"
+# - ja: "MoAI-ADKの概念とワークフローを簡単に学習する学習モード"
+# - zh: "轻松学习MoAI-ADK概念和工作流程的学习模式"
 ---
 
 # MoAI ADK Learning

moai_adk/templates/.claude/output-styles/alfred/study-with-alfred.md

@@ -1,6 +1,10 @@
 ---
 name: Study with Alfred
-description: Learning mode to easily learn new skills with Alfred
+description: "Learning mode to easily learn new skills with Alfred"
+# Translations:
+# - ko: "Alfred와 함께 새로운 기술을 쉽게 학습하는 학습 모드"
+# - ja: "Alfredと一緒に新しいスキルを簡単に学習する学習モード"
+# - zh: "与Alfred一起轻松学习新技能的学习模式"
 ---
 
 # Study with Alfred

moai_adk/templates/.claude/skills/moai-alfred-interactive-questions/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: moai-alfred-interactive-questions
-version: 3.0.0
+version: 3.1.0
 created: 2025-10-22
-updated: 2025-10-23
+updated: 2025-10-27
 status: active
 description: Guide Alfred sub-agents to actively invoke AskUserQuestion for ambiguous decisions.
 keywords: ['interactive', 'clarification', 'decision-making', 'AskUserQuestion']
@@ -17,7 +17,7 @@ allowed-tools:
 | Field | Value |
 | ----- | ----- |
 | **Skill Name** | moai-alfred-interactive-questions |
-| **Version** | 3.0.0 (2025-10-23) |
+| **Version** | 3.1.0 (2025-10-27) |
 | **Core Tool** | `AskUserQuestion` (Claude Code built-in) |
 | **Auto-load** | When Alfred detects ambiguity in requests |
 | **Tier** | Alfred (Workflow Orchestration) |
@@ -82,9 +82,7 @@ Proceed with confirmed specifications
 
 ---
 
-## AskUserQuestion API Reference
-
-### Minimal Invocation
+## Quick Start: Minimal Invocation
 
 ```typescript
 const answer = await AskUserQuestion({
@@ -110,7 +108,9 @@ const answer = await AskUserQuestion({
 // Returns: { "Approach": "Option 1" }
 ```
 
-### Key Constraints
+---
+
+## Key Constraints
 
 | Constraint | Reason |
 |-----------|--------|
@@ -121,292 +121,58 @@ const answer = await AskUserQuestion({
 | **Description required** | Enables informed choice |
 | **Auto "Other" option** | Always available for custom input |
 
-### Question Types
-
-**Single-Select** (`multiSelect: false`):
-- Mutually exclusive: "Choose ONE database"
-- Returns: `{ "Header": "Selected Label" }`
-
-**Multi-Select** (`multiSelect: true`):
-- Independent options: "Which features to enable?" (check multiple)
-- Returns: `{ "Header": ["Label1", "Label2"] }`
-
 ---
 
-## Usage Patterns (Top 5)
+## Top 5 Usage Patterns
 
 ### Pattern 1: Implementation Approach
-
 **Trigger**: "Add feature X" or "Build Y" without specifics
 
-```typescript
-await AskUserQuestion({
-  questions: [{
-    question: "How should we implement this feature?",
-    header: "Approach",
-    multiSelect: false,
-    options: [
-      { label: "New standalone component", description: "Isolated, reusable." },
-      { label: "Extend existing component", description: "Shared state, simpler." },
-      { label: "Use environment flag", description: "Conditional visibility." }
-    ]
-  }]
-});
-```
-
 ### Pattern 2: Confirmation (Risky Operations)
-
 **Trigger**: Destructive action (delete, migrate, reset)
 
-```typescript
-await AskUserQuestion({
-  questions: [{
-    question: "This will permanently delete 50 records. Proceed?",
-    header: "Confirm",
-    multiSelect: false,
-    options: [
-      { label: "Yes, proceed", description: "Irreversible. Continue." },
-      { label: "No, cancel", description: "Abort operation." }
-    ]
-  }]
-});
-```
-
 ### Pattern 3: Multi-Option Feature Selection
-
 **Trigger**: "Which framework/library/approach?"
 
-```typescript
-await AskUserQuestion({
-  questions: [{
-    question: "Which i18n library?",
-    header: "Library",
-    multiSelect: false,
-    options: [
-      { label: "next-intl", description: "Next.js 15+ native, best DX." },
-      { label: "react-i18next", description: "Popular, flexible, more setup." },
-      { label: "Format.js", description: "ICU format, powerful, complex." }
-    ]
-  }]
-});
-```
-
 ### Pattern 4: Multi-Select (Independent Features)
-
 **Trigger**: "Which features to enable/include?"
 
-```typescript
-await AskUserQuestion({
-  questions: [{
-    question: "Which testing frameworks?",
-    header: "Test Tools",
-    multiSelect: true,  // Multiple selections allowed
-    options: [
-      { label: "Unit tests (Vitest)", description: "Fast, modern." },
-      { label: "E2E tests (Playwright)", description: "Browser automation." },
-      { label: "Visual regression", description: "Screenshot comparison." }
-    ]
-  }]
-});
-```
-
 ### Pattern 5: Sequential Questions (Conditional Flow)
-
 **Trigger**: Dependent decisions (Q2 depends on Q1 answer)
 
-```typescript
-// Question 1
-const q1 = await AskUserQuestion({
-  questions: [{
-    question: "Enable authentication?",
-    header: "Auth",
-    options: [
-      { label: "Yes", description: "User login required." },
-      { label: "No", description: "Public access." }
-    ]
-  }]
-});
+> **Detailed examples and code**: See [examples.md](examples.md)
 
-// Question 2 (only if Q1 = "Yes")
-if (q1["Auth"] === "Yes") {
-  const q2 = await AskUserQuestion({
-    questions: [{
-      question: "Which auth provider?",
-      header: "Provider",
-      options: [
-        { label: "JWT + email", description: "Traditional." },
-        { label: "OAuth", description: "Third-party." }
-      ]
-    }]
-  });
-}
-```
+---
+
+## Integration with Alfred Sub-agents
+
+| Sub-agent | When to Ask | Example Trigger |
+|-----------|-------------|-----------------|
+| **spec-builder** (`/alfred:1-plan`) | SPEC title vague, scope undefined | "Add feature" without specifics |
+| **code-builder** (`/alfred:2-run`) | Implementation approach unclear | Multiple valid implementation paths |
+| **doc-syncer** (`/alfred:3-sync`) | Sync scope unclear | Full vs partial sync decision |
+
+> **Detailed integration patterns**: See [reference.md](reference.md)
 
 ---
 
-## Best Practices
+## Best Practices Summary
 
 ### ✅ DO
-
 - **Be specific**: "Which database type?" not "What should we use?"
 - **Provide context**: Include file names, scope, or impact
 - **Order logically**: General → Specific; safest option first
 - **Flag risks**: Use "NOT RECOMMENDED" or "CAUTION:" prefixes
 - **Explain trade-offs**: Mention time, resources, complexity
-- **Single-select for exclusive**: "Choose ONE"
-- **Multi-select for combinable**: "Check any that apply"
-- **Include descriptions**: Every option needs rationale
-- **Keep headers short**: "Approach" not "Implementation Strategy"
-- **Batch related questions**: Ask 2-3 at once if they flow naturally
 
 ### ❌ DON'T
-
 - **Overuse questions**: Only ask when ambiguous
 - **Too many options**: 2-4 per question max
 - **Vague labels**: "Option A", "Use tokens", "Option 2"
 - **Skip descriptions**: User needs rationale
 - **Hide trade-offs**: Always mention implications
-- **Make destructive default**: Risky option = NOT pre-selected
-- **Mix concerns**: One decision per question
-- **Manually add "Other"**: It's auto-provided
-- **Nest more than 2 levels deep**: Keep flow linear
-
----
 
-## Integration with Alfred Sub-agents
-
-### spec-builder (`/alfred:1-plan`)
-
-**When to ask**:
-- SPEC title is vague ("Add feature")
-- Scope undefined (what exactly?)
-- Domain prefix unclear (AUTH vs UI vs DATA?)
-
-**Example**:
-```typescript
-if (titleIsAmbiguous(specTitle)) {
-  const answer = await AskUserQuestion({
-    questions: [{
-      question: "Can you clarify what this SPEC should cover?",
-      header: "Scope",
-      options: [...]
-    }]
-  });
-  specTitle = answer["Scope"];
-}
-```
-
-### code-builder (`/alfred:2-run`)
-
-**When to ask**:
-- Implementation approach unclear
-- Multiple valid paths exist
-- Error recovery needed (failing tests)
-
-**Example**:
-```typescript
-if (multipleValidImplementationPaths) {
-  const answer = await AskUserQuestion({
-    questions: [{
-      question: "How should we implement this?",
-      header: "Approach",
-      options: [...]
-    }]
-  });
-  implementationStrategy = answer["Approach"];
-}
-```
-
-### doc-syncer (`/alfred:3-sync`)
-
-**When to ask**:
-- Sync scope unclear (full vs partial)
-- PR Ready status uncertain
-- Documentation coverage decision needed
-
-**Example**:
-```typescript
-const syncMode = await AskUserQuestion({
-  questions: [{
-    question: "Which sync mode?",
-    header: "Mode",
-    options: [
-      { label: "auto", description: "Smart detection." },
-      { label: "force", description: "Regenerate all." }
-    ]
-  }]
-});
-```
-
----
-
-## Real-World Examples
-
-### Example: Vague Feature Request
-
-**User**: "Add a completion page for the competition."
-
-**Alfred detects ambiguity**:
-- Where should it live? (new route vs modify existing)
-- Who can access it? (public vs authenticated)
-- What should it display? (results vs simple message)
-
-**AskUserQuestion invocation**:
-```typescript
-const answer = await AskUserQuestion({
-  questions: [
-    {
-      question: "How should the completion page be implemented?",
-      header: "Approach",
-      multiSelect: false,
-      options: [
-        { label: "New public route", description: "New page visible to all visitors." },
-        { label: "Modify existing page", description: "Add conditional logic to /end page." },
-        { label: "Environment flag", description: "Set NEXT_PUBLIC_COMPETITION_CLOSED=true." }
-      ]
-    },
-    {
-      question: "For logged-in participants?",
-      header: "Behavior",
-      multiSelect: false,
-      options: [
-        { label: "Show full results", description: "Redirect to /end page with history." },
-        { label: "Show simple message", description: "Display 'Competition concluded' only." }
-      ]
-    }
-  ]
-});
-```
-
-**Result**: Alfred knows exactly what to build.
-
----
-
-## Anti-Patterns to Avoid
-
-### ❌ Too Many Options
-```typescript
-// 8+ options = choice paralysis
-options: [
-  { label: "PostgreSQL" }, { label: "MySQL" }, { label: "MariaDB" },
-  { label: "SQLite" }, { label: "MongoDB" }, { label: "CouchDB" },
-  { label: "Cassandra" }, { label: "Redis" }
-]
-```
-
-### ✅ Group Options
-```typescript
-// First ask: which TYPE? Then: specific within type
-questions: [{
-  question: "Database type?",
-  header: "DB Type",
-  options: [
-    { label: "Relational (SQL)", description: "PostgreSQL, MySQL, etc." },
-    { label: "Document (NoSQL)", description: "MongoDB, CouchDB, etc." },
-    { label: "Key-Value", description: "Redis, Memcached, etc." }
-  ]
-}]
-```
+> **Complete best practices guide**: See [reference.md](reference.md)
 
 ---
 
@@ -427,35 +193,21 @@ try {
 const answer = await AskUserQuestion({...});
 
 if (answer["Header"] === "Other" || !VALID_OPTIONS.includes(answer["Header"])) {
-  // Handle custom input validation
   validateCustomInput(answer["Header"]);
 }
 ```
 
 ---
 
-## Performance Tips
-
-- **Batch questions**: Ask 2-3 related questions in one call
-- **Minimize calls**: Don't ask sequentially unless truly dependent
-- **Pre-generate options**: Analyze codebase once to generate all options
-
----
-
-## References
-
-**Official Claude Code Documentation**:
-- AskUserQuestion tool (built-in Claude Code)
-- Interactive Prompting (CLAUDE.md § Clarification & Interactive Prompting)
+## Related Skills
 
-**Related Skills**:
 - `moai-alfred-spec-metadata-validation` (SPEC clarity)
 - `moai-alfred-ears-authoring` (requirement phrasing)
 - `moai-foundation-specs` (SPEC structure)
 
 ---
 
-## Summary
+## Quick Reference
 
 **When to use**:
 - User intent is ambiguous
@@ -477,4 +229,9 @@ if (answer["Header"] === "Other" || !VALID_OPTIONS.includes(answer["Header"])) {
 
 ---
 
-**End of Skill** | Refactored 2025-10-23
+**For detailed API specifications**: [reference.md](reference.md)  
+**For real-world examples**: [examples.md](examples.md)
+
+---
+
+**End of Skill** | Refactored 2025-10-27