moai-adk 0.4.1__py3-none-any.whl → 0.4.5__py3-none-any.whl

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

@@ -24,18 +24,21 @@ Automatically analyzes the project environment to create/update product/structur
 
 ## 📋 Execution flow
 
-1. **Environment Analysis**: Automatically detect project type (new/legacy) and language
+0. **Conversation Language Selection**: User selects the language for all dialogs and documentation
+1. **Environment Analysis**: Automatically detect project type (new/legacy) and codebase language
 2. **Establishment of interview strategy**: Select question tree suited to project characteristics
 3. **User Verification**: Review and approve interview plan
-4. **Create project documentation**: Create product/structure/tech.md
+4. **Create project documentation**: Create product/structure/tech.md in the selected language
 5. **Create configuration file**: config.json auto-configuration
 
-## 🧠 Skill Loadout Overview
+## 🧠 Associated Skills & Agents
 
-| Agent | Auto core skill | Conditional skills |
-| ----- | ---------------- | ------------------ |
-| project-manager | Skill("moai-alfred-language-detection") | Skill("moai-foundation-ears"), Skill("moai-foundation-langs"), Detected domain skill (e.g., Skill("moai-domain-backend")), Skill("moai-alfred-tag-scanning"), Skill("moai-alfred-trust-validation"), Skill("moai-alfred-tui-survey") |
-| trust-checker | Skill("moai-alfred-trust-validation") | Skill("moai-alfred-tag-scanning"), Skill("moai-foundation-trust"), Skill("moai-alfred-code-reviewer"), Skill("moai-alfred-performance-optimizer"), Skill("moai-alfred-tui-survey") |
+| Agent | Core Skill | Purpose |
+| ----- | -------- | ------- |
+| project-manager | `moai-alfred-language-detection` | Initialize project and interview requirements |
+| trust-checker | `moai-alfred-trust-validation` | Verify initial project structure (optional) |
+
+**Note**: TUI Survey Skill is used for user confirmations during project initialization and is shared across all interactive prompts.
 
 ## 🔗 Associated Agent
 
@@ -77,12 +80,70 @@ The user executes the `/alfred:8-project` command to start analyzing the project
 
 **Expressions to use**:
 
-- ✅ “High/medium/low priority”
-- ✅ “Immediately needed”, “step-by-step improvements”
+- ✅ "High/medium/low priority"
+- ✅ "Immediately needed", "step-by-step improvements"
 - ✅ Current facts
 - ✅ Existing technology stack
 - ✅ Real problems
 
+---
+
+## 🚀 STEP 0: Conversation Language Selection (NEW in v0.4.2)
+
+**Purpose**: Establish the conversation language before project initialization begins. This selection applies to all Alfred prompts, interview questions, and generated documentation.
+
+### 0.1 Display Language Selection Menu
+
+Alfred displays a language selection menu as the **very first interaction** using `Skill("moai-alfred-tui-survey")`:
+
+**Question**:
+```
+Which language would you like to use for the project initialization and documentation?
+```
+
+**Options** (AskUserQuestion with moai-alfred-tui-survey):
+- **English** (en) — All dialogs and documentation in English
+- **한국어** (ko) — All dialogs and documentation in Korean
+- **日本語** (ja) — All dialogs and documentation in Japanese
+- **中文** (zh) — All dialogs and documentation in Chinese
+- **Other** — User can specify custom language (e.g., "Español", "Français", "Deutsch")
+
+### 0.2 Store Language Preference
+
+Alfred records the selected language:
+
+```json
+{
+  "conversation_language": "ko",
+  "conversation_language_name": "한국어",
+  "selected_at": "2025-10-22T12:34:56Z"
+}
+```
+
+This language preference is:
+- Passed to all sub-agents as a context parameter
+- Stored in `.moai/config.json` under `language` field
+- Used to generate all documentation in the selected language
+- Displayed in CLAUDE.md under "## Project Information"
+
+### 0.3 Transition to STEP 1
+
+After language selection, all subsequent interactions proceed in the selected language:
+- Alfred's prompts are translated
+- project-manager sub-agent receives language parameter
+- Interview questions are in the selected language
+- Generated documents (product.md, structure.md, tech.md) are in the selected language
+- CLAUDE.md displays the selected language prominently
+
+**Example output for Korean selection**:
+```markdown
+✅ 언어 선택 완료: 한국어 (ko)
+
+이제 프로젝트 환경 분석으로 진행하겠습니다...
+```
+
+---
+
 ## 🚀 STEP 1: Environmental analysis and interview plan development
 
 Analyze the project environment and develop a systematic interview plan.
@@ -343,15 +404,37 @@ After Alfred receives the project-manager's interview plan report, calls `Skill(
 
 After user approval, the project-manager agent performs initialization.
 
-### 2.1 Call project-manager agent (when user selects “New”)
+### 2.1 Call project-manager agent (when user selects "New")
+
+Alfred starts project initialization by calling the project-manager agent with the following parameters:
 
-Alfred starts project initialization by calling the project-manager agent. We will proceed based on the following information:
-- Detected Languages: [Language List]
+**Parameters passed to project-manager**:
+- **conversation_language** (from STEP 0): Language code selected by user (e.g., "ko", "en", "ja", "zh")
+- **language_name** (from STEP 0): Display name of selected language (e.g., "Korean", "English")
+- Detected Languages: [Language List from codebase detection]
 - Project Type: [New/Existing]
 - Existing Document Status: [Existence/Absence]
 - Approved Interview Plan: [Plan Summary]
 
-Agents conduct structured interviews and create/update product/structure/tech.md documents.
+**Execution**:
+```bash
+# Pseudo-code showing parameter flow
+Task(
+    subagent_type="project-manager",
+    description="Initialize project with conversation language support",
+    prompt=f"""You are project-manager. Initialize project with these parameters:
+    - conversation_language: "{conversation_language}"  # e.g., "ko"
+    - language_name: "{language_name}"  # e.g., "Korean"
+    - project_type: "{project_type}"  # e.g., "new"
+    - detected_languages: {detected_languages}
+
+    All interviews and documentation must be generated in the conversation_language.
+    Update .moai/config.json with these language parameters.
+    """
+)
+```
+
+**Outcome**: The project-manager agent conducts structured interviews entirely in the selected language and creates/updates product/structure/tech.md documents in that language.
 
 ### 2.2 Automatic activation of Alfred Skills (optional)
 

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

@@ -66,13 +66,14 @@ allowed-tools:
 4. **Plan creation**: Generate specifications of EARS structure (spec.md, plan.md, acceptance.md)
 5. **Git operations**: Create branches/PRs via git-manager
 
-## 🧠 Skill Loadout Overview
+## 🧠 Associated Skills & Agents
 
-| Agent | Auto core skill | Conditional skills |
-| ----- | ---------------- | ------------------ |
-| implementation-planner | Skill("moai-alfred-language-detection") | Skill("moai-foundation-langs"), Skill("moai-alfred-performance-optimizer"), Skill("moai-alfred-tag-scanning"), Detected domain skill (e.g., Skill("moai-domain-backend")), Skill("moai-alfred-trust-validation"), Skill("moai-alfred-tui-survey") |
-| spec-builder | Skill("moai-foundation-ears") | Skill("moai-alfred-ears-authoring"), Skill("moai-foundation-specs"), Skill("moai-alfred-spec-metadata-validation"), Skill("moai-alfred-tag-scanning"), Skill("moai-foundation-trust"), Skill("moai-alfred-trust-validation"), Skill("moai-alfred-tui-survey") |
-| git-manager | Skill("moai-alfred-git-workflow") | Skill("moai-foundation-git"), Skill("moai-alfred-trust-validation"), Skill("moai-alfred-tag-scanning"), Skill("moai-alfred-tui-survey") |
+| Agent | Core Skill | Purpose |
+| ----- | -------- | ------- |
+| spec-builder | `moai-foundation-ears` | Write SPEC with EARS syntax |
+| git-manager | `moai-alfred-git-workflow` | Create branch and PR |
+
+**Note**: TUI Survey Skill is used for user confirmations during the plan phase and is shared across all interactive prompts.
 
 ## 🔗 Associated Agent
 

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

@@ -65,14 +65,16 @@ Analyze SPEC documents to execute planned tasks. It supports not only TDD implem
 4. **Execute work**: Perform work according to the approved plan
 5. **Git Operations**: Creating step-by-step commits with git-manager
 
-## 🧠 Skill Loadout Overview
-
-| Agent | Auto core skill | Conditional skills |
-| ----- | ---------------- | ------------------ |
-| implementation-planner | Skill("moai-alfred-language-detection") | Skill("moai-foundation-langs"), Skill("moai-alfred-performance-optimizer"), Skill("moai-alfred-tag-scanning"), Detected domain skill (e.g., Skill("moai-domain-backend")), Skill("moai-alfred-trust-validation"), Skill("moai-alfred-tui-survey") |
-| tdd-implementer | Skill("moai-essentials-debug") | Detected language skill (e.g., Skill("moai-lang-python")), Skill("moai-essentials-refactor"), Skill("moai-alfred-git-workflow"), Skill("moai-essentials-perf"), Skill("moai-alfred-performance-optimizer"), Skill("moai-alfred-tui-survey") |
-| quality-gate | Skill("moai-alfred-trust-validation") | Skill("moai-alfred-tag-scanning"), Skill("moai-alfred-code-reviewer"), Skill("moai-essentials-review"), Skill("moai-essentials-perf"), Skill("moai-alfred-performance-optimizer"), Skill("moai-foundation-trust"), Skill("moai-alfred-tui-survey") |
-| git-manager | Skill("moai-alfred-git-workflow") | Skill("moai-foundation-git"), Skill("moai-alfred-trust-validation"), Skill("moai-alfred-tag-scanning"), Skill("moai-alfred-tui-survey") |
+## 🧠 Associated Skills & Agents
+
+| Agent | Core Skill | Purpose |
+| ----- | -------- | ------- |
+| implementation-planner | `moai-alfred-language-detection` | Detect language and design architecture |
+| tdd-implementer | `moai-essentials-debug` | Implement TDD (RED → GREEN → REFACTOR) |
+| quality-gate | `moai-alfred-trust-validation` | Verify TRUST 5 principles |
+| git-manager | `moai-alfred-git-workflow` | Commit and manage Git workflows |
+
+**Note**: TUI Survey Skill is used for user confirmations during the run phase and is shared across all interactive prompts.
 
 ## 🔗 Associated Agent
 

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

@@ -19,6 +19,16 @@ allowed-tools:
 # 📚 MoAI-ADK Step 3: Document Synchronization (+Optional PR Ready)
 > Interactive prompts rely on `Skill("moai-alfred-tui-survey")` so AskUserQuestion renders TUI selection menus for user surveys and approvals.
 
+## 🚀 START HERE
+
+**CRITICAL**: Load the TUI Survey Skill FIRST before any user interaction:
+
+```
+Skill("moai-alfred-tui-survey")
+```
+
+This Skill MUST be loaded at the very beginning to enable TUI menu rendering for AskUserQuestion calls throughout this workflow.
+
 ## 🎯 Command Purpose
 
 Synchronize code changes to Living Documents and verify @TAG system to ensure complete traceability.
@@ -29,20 +39,31 @@ Synchronize code changes to Living Documents and verify @TAG system to ensure co
 
 ## 📋 Execution flow
 
+**Phase 0: Skill Loading** (IMMEDIATE)
+- Load `Skill("moai-alfred-tui-survey")` at the very start
+- This enables TUI menu rendering for all user interactions
+
+**Phase 1: Analysis & Planning**
 1. **Project status analysis**: Git changes and TAG system verification
 2. **Determine the scope of synchronization**: Full/partial/selective synchronization strategy
-3. **User Confirmation**: Review and approve synchronization plan
-4. **Document Synchronization**: Living Document updates and TAG integrity guaranteed
-5. **Git operations**: Commit and PR state transitions via git-manager
-
-## 🧠 Skill Loadout Overview
-
-| Agent | Auto core skill | Conditional skills |
-| ----- | ---------------- | ------------------ |
-| tag-agent | Skill("moai-alfred-tag-scanning") | Skill("moai-foundation-tags"), Skill("moai-alfred-trust-validation"), Skill("moai-foundation-specs"), Skill("moai-alfred-tui-survey") |
-| quality-gate | Skill("moai-alfred-trust-validation") | Skill("moai-alfred-tag-scanning"), Skill("moai-alfred-code-reviewer"), Skill("moai-essentials-review"), Skill("moai-essentials-perf"), Skill("moai-alfred-performance-optimizer"), Skill("moai-foundation-trust"), Skill("moai-alfred-tui-survey") |
-| doc-syncer | Skill("moai-alfred-tag-scanning") | Skill("moai-foundation-tags"), Skill("moai-alfred-trust-validation"), Skill("moai-foundation-specs"), Skill("moai-alfred-git-workflow"), Skill("moai-alfred-code-reviewer"), Skill("moai-alfred-tui-survey") |
-| git-manager | Skill("moai-alfred-git-workflow") | Skill("moai-foundation-git"), Skill("moai-alfred-trust-validation"), Skill("moai-alfred-tag-scanning"), Skill("moai-alfred-tui-survey") |
+3. **User Confirmation**: Review and approve synchronization plan via AskUserQuestion (TUI menu)
+
+**Phase 2: Conditional Execution** (based on user choice)
+4. **Document Synchronization**: Living Document updates and TAG integrity guaranteed (IF user selects "Proceed")
+5. **Git operations**: Commit and PR state transitions via git-manager (IF user selects "Proceed")
+   - OR abort workflow (IF user selects "Abort")
+   - OR revise plan (IF user selects "Modify")
+
+## 🧠 Associated Skills & Agents
+
+| Agent | Core Skill | Purpose |
+| ----- | -------- | ------- |
+| tag-agent | `moai-alfred-tag-scanning` | Verify TAG system integrity |
+| quality-gate | `moai-alfred-trust-validation` | Check code quality before sync |
+| doc-syncer | `moai-alfred-tag-scanning` | Synchronize Living Documents |
+| git-manager | `moai-alfred-git-workflow` | Handle Git operations |
+
+**Note**: TUI Survey Skill is loaded once at Phase 0 and reused throughout all user interactions.
 
 ## 🔗 Associated Agent
 

moai_adk/templates/.moai/memory/spec-metadata.md

@@ -245,6 +245,86 @@ labels:
   - maintenance
 ```
 
+### Updating config.json for Language Support (v0.4.2+)
+
+**Background**: MoAI-ADK v0.4.2 introduces conversation language selection in `/alfred:0-project`. Existing projects need to add language metadata to `.moai/config.json`.
+
+#### Migration Steps
+
+**For Existing Projects** (before v0.4.2):
+
+Current config.json structure:
+```json
+{
+  "project": {
+    "locale": "en",
+    "mode": "personal",
+    "language": "python"
+  }
+}
+```
+
+**Updated Structure** (v0.4.2+):
+```json
+{
+  "project": {
+    "locale": "en",
+    "mode": "personal",
+    "language": "python",
+    "conversation_language": "en",
+    "conversation_language_name": "English",
+    "codebase_languages": ["python"]
+  }
+}
+```
+
+#### New Fields
+
+| Field | Type | Required | Description | Example |
+|-------|------|----------|-------------|---------|
+| `conversation_language` | string (ISO 639-1 code) | ✅ Yes | Two-letter language code for Alfred dialogs | `"ko"`, `"en"`, `"ja"`, `"zh"` |
+| `conversation_language_name` | string | ✅ Yes | Display name of conversation language | `"Korean"`, `"English"` |
+| `codebase_languages` | array of strings | ✅ Yes | List of programming languages detected | `["python"]`, `["typescript", "python"]` |
+
+#### Manual Update Process
+
+1. Open `.moai/config.json`
+2. Add the three new fields under `project`:
+   ```json
+   "conversation_language": "en",
+   "conversation_language_name": "English",
+   "codebase_languages": ["python"]
+   ```
+3. Save and commit:
+   ```bash
+   git add .moai/config.json
+   git commit -m "chore: add language metadata to config.json for v0.4.2+"
+   ```
+
+#### Automated Update (via `/alfred:0-project`)
+
+Running `/alfred:0-project` on an existing project will:
+1. Detect current language settings
+2. Add new fields automatically
+3. Preserve existing values
+
+**No manual action required if running `/alfred:0-project` after upgrade.**
+
+#### Field Mapping (Legacy → New)
+
+| Old Field | New Field | Migration Rule |
+|-----------|-----------|-----------------|
+| `locale` | `conversation_language` | Keep as-is (or run `/alfred:0-project` to re-select) |
+| (none) | `conversation_language_name` | Auto-populate from locale mapping |
+| `language` | `codebase_languages` | Wrap in array: `"python"` → `["python"]` |
+
+#### Backward Compatibility
+
+- ✅ Projects without new fields will continue working
+- ⚠️ New language features (multilingual documentation) unavailable without migration
+- ✅ `/alfred:0-project` automatically migrates on next run
+- ✅ Auto-detection will prefer new fields if present
+
 ---
 
 ## Design Principles

moai_adk/templates/CLAUDE.md

@@ -295,6 +295,221 @@ Refs: @TAG-ID (if applicable)
 - Use `/alfred:3-sync` to update Living Docs and TAG references.
 - Record rationale for deviations from the SPEC.
 
+## Clarification & Interactive Prompting
+
+### The "Vibe Coding" Challenge
+
+**Vibe Coding** refers to requesting AI assistance with minimal context, expecting the AI to infer intent from incomplete instructions. While this approach works for experienced developers with high-context understanding of their codebase, it often results in:
+
+- ❌ Ambiguous or conflicting implementations
+- ❌ Unnecessary modifications to existing code
+- ❌ Multiple rounds of back-and-forth refinement
+- ❌ Wasted time clarifying intent
+
+**Root cause**: AI must *guess* user intent without explicit guidance.
+
+### Solution: Interactive Question Tool + TUI Survey Skill
+
+Claude Code now features an **Interactive Question Tool** powered by the `moai-alfred-tui-survey` Skill that transforms vague requests into precise, contextual specifications through guided clarification. Instead of AI making assumptions, the tool actively:
+
+1. **Analyzes** existing code and project context
+2. **Identifies** ambiguity and competing approaches
+3. **Presents** concrete options with clear trade-offs via **TUI menu**
+4. **Captures** explicit user choices (arrow keys, enter)
+5. **Executes** with certainty based on confirmed intent
+
+**Implementation**: The `moai-alfred-tui-survey` Skill provides interactive survey menus that render as terminal UI elements, allowing users to navigate options with arrow keys and confirm with enter.
+
+### How It Works
+
+When you provide a high-level request, Alfred may invoke the `moai-alfred-tui-survey` Skill to clarify implementation details through structured TUI menus:
+
+```
+User: "Add a completion page for the competition."
+         ↓
+Alfred analyzes codebase & context
+         ↓
+[QUESTION 1] How should the completion page be implemented?
+┌─────────────────────────────────────────────────────┐
+│ ▶ Create a new public page                          │  ← arrow keys to select
+│   Modify existing page structure                    │
+│   Use environment-based gating                      │
+│                                                     │
+│ (press ↑↓ to navigate, enter to confirm)           │
+└─────────────────────────────────────────────────────┘
+         ↓
+[QUESTION 2] Who should see the completion page?
+┌─────────────────────────────────────────────────────┐
+│   Only participants (authenticated users)           │
+│ ▶ All visitors (public)                             │
+│   Based on time window                              │
+│                                                     │
+│ (press ↑↓ to navigate, enter to confirm)           │
+└─────────────────────────────────────────────────────┘
+         ↓
+[REVIEW] Summary of your selections
+┌─────────────────────────────────────────────────────┐
+│ ✓ Implementation: New public page                   │
+│ ✓ User experience: All visitors (public)            │
+│                                                     │
+│ Ready to submit?                                    │
+│  [Submit answers] [← Go back]                       │
+└─────────────────────────────────────────────────────┘
+         ↓
+Execution with confirmed specifications
+```
+
+**Where it's used**:
+- Sub-agents (spec-builder, code-builder pipeline) invoke this skill when ambiguity is detected
+- Alfred commands may trigger interactive surveys during Plan/Run/Sync phases
+- User approvals and architectural decisions benefit most from TUI-based selection
+
+### Key Benefits
+
+| Benefit | Impact |
+| --- | --- |
+| **Reduced ambiguity** | AI asks before acting; eliminates guess work |
+| **Faster iteration** | Choices are presented upfront, not discovered after implementation |
+| **Higher quality** | Implementation matches intent precisely |
+| **Lower communication cost** | Answering 3-5 specific questions beats endless refinement |
+| **Active collaboration** | AI becomes a partner, not just a code generator |
+
+### When to Use Interactive Questions
+
+**Ideal for**:
+- 🎯 Complex features with multiple valid approaches
+- 🎯 Architectural decisions with trade-offs
+- 🎯 Ambiguous or high-level requirements
+- 🎯 Requests that affect multiple existing components
+- 🎯 Decisions involving user experience or data flow
+
+**Example triggers**:
+- "Add a dashboard" → needs clarification on layout, data sources, authentication
+- "Refactor the auth system" → needs clarification on scope, backwards compatibility, migration strategy
+- "Optimize performance" → needs clarification on which bottleneck, acceptable trade-offs
+- "Add multi-language support" → needs clarification on scope, default language, i18n library
+
+### Best Practices for Interactive Prompting
+
+1. **Provide initial context** (even if vague)
+   - ✅ "Add a competition results page"
+   - ❌ "Do something"
+
+2. **Trust the guided questions**
+   - AI will ask if it detects ambiguity
+   - Answer each question honestly, don't over-explain
+   - Use "Other" option to provide custom input if preset options don't fit
+
+3. **Review before submission**
+   - The summary step lets you verify all choices
+   - Use "back" to revise any answer
+   - Only submit when you're confident in the selections
+
+4. **Iterative refinement is OK**
+   - If implementation doesn't match intent, re-run with clearer guidance
+   - Your answers inform Alfred's future prompting
+   - This feedback loop improves collaboration quality
+
+5. **Combine with Context Engineering**
+   - Provide high-level intent + let interactive questions fill in details
+   - Reference existing code patterns ("like the auth flow in `/src/auth.ts`")
+   - Mention constraints or non-negotiables upfront
+
+### Example: Competition Completion Page (TUI Survey)
+
+**User Request**: "Competition is over. Add a completion page."
+
+**Step 1: Code Analysis**
+Alfred scans the codebase and detects:
+- Existing `/end` page (auth required, shows results)
+- Need for clarification on scope and user behavior
+
+**Step 2: Interactive Survey (moai-alfred-tui-survey activated)**
+
+```
+────────────────────────────────────────────────────────────────
+ALFRED: How should the completion page be implemented?
+────────────────────────────────────────────────────────────────
+
+┌─ IMPLEMENTATION APPROACH ────────────────────────────────────┐
+│                                                              │
+│ ▶ Create a new public page (/competition-closed)            │
+│   • Unguarded route, visible to all visitors                │
+│   • No authentication required                              │
+│                                                              │
+│   Modify existing /end page with conditional logic          │
+│   • Check if competition is active before showing results   │
+│                                                              │
+│   Use environment-based gating                              │
+│   • Set NEXT_PUBLIC_COMPETITION_CLOSED=true                │
+│   • Redirect all traffic to completion screen               │
+│                                                              │
+│ Use ↑↓ arrows to navigate, ENTER to select                 │
+│ Type custom answer or press ESC to cancel                   │
+└──────────────────────────────────────────────────────────────┘
+
+→ Selection: Create a new public page (/competition-closed)
+```
+
+```
+────────────────────────────────────────────────────────────────
+ALFRED: For logged-in participants accessing the new page?
+────────────────────────────────────────────────────────────────
+
+┌─ USER BEHAVIOR ──────────────────────────────────────────────┐
+│                                                              │
+│   Show submission history                                   │
+│   • Redirect to /end page, display results & timeline       │
+│                                                              │
+│ ▶ Show simple completion message only                       │
+│   • Display "Competition concluded" notice                  │
+│   • No historical data shown                                │
+│                                                              │
+│   Custom behavior based on user role                        │
+│   • Different experience per role type                      │
+│                                                              │
+│ Use ↑↓ arrows to navigate, ENTER to select                 │
+│ Type custom answer or press ESC to cancel                   │
+└──────────────────────────────────────────────────────────────┘
+
+→ Selection: Show simple completion message only
+```
+
+**Step 3: Review & Confirmation**
+
+```
+────────────────────────────────────────────────────────────────
+ALFRED: Review your answers
+────────────────────────────────────────────────────────────────
+
+┌─ SUMMARY ────────────────────────────────────────────────────┐
+│                                                              │
+│ ✓ Implementation approach:                                  │
+│   Create a new public page (/competition-closed)            │
+│                                                              │
+│ ✓ User behavior:                                            │
+│   Show simple completion message only                       │
+│                                                              │
+│ Ready to submit these answers?                              │
+│                                                              │
+│  [✓ Submit answers]  [← Go back and modify]                │
+│                                                              │
+└──────────────────────────────────────────────────────────────┘
+
+→ Action: Submit answers (enter)
+```
+
+**Step 4: Execution**
+
+Alfred now executes with **confirmed specifications**:
+- ✅ Creates `/app/competition-closed/page.tsx` (public route)
+- ✅ Implements simple "Competition concluded" message
+- ✅ Handles authenticated users appropriately
+- ✅ Generates with SPEC → TDD → Sync flow
+
+**Result**: Clean, intentional implementation that exactly matches confirmed specifications.
+No guessing. No ambiguity. Direct execution. 🎯
+
 ## Commands · Sub-agents · Skills · Hooks
 
 MoAI-ADK assigns every responsibility to a dedicated execution layer.
@@ -505,4 +720,16 @@ Alfred enforces these quality gates on every change:
 - **Description**: {{PROJECT_DESCRIPTION}}
 - **Version**: {{PROJECT_VERSION}}
 - **Mode**: {{PROJECT_MODE}}
+- **Conversation Language**: {{CONVERSATION_LANGUAGE}} ({{CONVERSATION_LANGUAGE_NAME}})
+- **Codebase Language**: {{CODEBASE_LANGUAGE}}
 - **Toolchain**: Automatically selects the best tools for the chosen language
+
+### Language Configuration
+
+- **Conversation Language** (`{{CONVERSATION_LANGUAGE}}`): All Alfred dialogs, documentation, and project interviews conducted in this language
+- **Codebase Language** (`{{CODEBASE_LANGUAGE}}`): Primary programming language(s) detected in this project
+- **Documentation**: Generated in the conversation language ({{CONVERSATION_LANGUAGE_NAME}})
+
+---
+
+**Note**: The conversation language is selected at the beginning of `/alfred:0-project` and applies to all subsequent project initialization steps. All generated documentation (product.md, structure.md, tech.md) will be created in the selected language.