musubi-sdd 6.0.0 → 6.1.1

package/bin/musubi-init.js

@@ -1253,7 +1253,7 @@ async function main(agent, agentKey, options = {}) {
     'templates',
     'storage/specs',
     'storage/changes',
-    'storage/features',
+    'storage/archive',
   ];
 
   // Add agent-specific directories

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "musubi-sdd",
-  "version": "6.0.0",
+  "version": "6.1.1",
   "description": "Ultimate Specification Driven Development Tool with 27 Agents for 7 AI Coding Platforms + MCP Integration (Claude Code, GitHub Copilot, Cursor, Gemini CLI, Windsurf, Codex, Qwen Code)",
   "main": "src/index.js",
   "bin": {

package/src/templates/agents/claude-code/skills/constitution-enforcer/SKILL.md

@@ -616,4 +616,4 @@ Before finishing:
 - [ ] Failures documented with severity
 - [ ] Remediation plan provided
 - [ ] Overall status determined (APPROVED/BLOCKED)
-- [ ] Report saved to `storage/features/[feature]/constitutional-compliance.md`
+- [ ] Report saved to `storage/specs/[feature]/constitutional-compliance.md`

package/src/templates/agents/claude-code/skills/constitution-enforcer/phase-minus-one-gates.md

@@ -192,9 +192,9 @@ def validate_traceability_setup(feature_name):
     Verify traceability chain is ready.
     """
     required_artifacts = {
-        "requirements": f"storage/features/{feature_name}/requirements.md",
-        "design": f"storage/features/{feature_name}/design.md",
-        "tasks": f"storage/features/{feature_name}/tasks.md",
+        "requirements": f"storage/specs/{feature_name}/requirements.md",
+        "design": f"storage/specs/{feature_name}/design.md",
+        "tasks": f"storage/specs/{feature_name}/tasks.md",
     }
 
     for artifact, path in required_artifacts.items():

package/src/templates/agents/claude-code/skills/site-reliability-engineer/SKILL.md

@@ -318,7 +318,7 @@ app.get('/health/live', (req, res) => {
 
 ### Phase 1: SLO Definition (Based on Requirements)
 
-1. Read `storage/features/[feature]/requirements.md`
+1. Read `storage/specs/[feature]-requirements.md`
 2. Identify non-functional requirements (performance, availability)
 3. Define SLIs and SLOs
 4. Calculate error budgets

package/src/templates/agents/claude-code/skills/steering/auto-update-rules.md

@@ -107,7 +107,7 @@ git diff --name-only | grep -E "(webpack|vite|rollup|esbuild)\.config\."
 
 ```bash
 # New feature directories
-git diff --name-only --diff-filter=A | grep "storage/features/"
+git diff --name-only --diff-filter=A | grep "storage/specs/"
 
 # New requirement files
 git diff --name-only --diff-filter=A | grep "requirements\.md"
@@ -154,7 +154,7 @@ git diff --name-only --diff-filter=A | grep "requirements\.md"
 
 ### memories/architecture_decisions.md
 
-**Trigger**: New ADR created in `storage/features/*/design.md`
+**Trigger**: New ADR created in `storage/specs/*/design.md`
 
 **Action**:
 
@@ -245,8 +245,8 @@ diff <(grep "dependencies" steering/tech.md) <(cat package.json | jq '.dependenc
 # 2. Check if structure.md directories match actual structure
 diff <(grep -E "^-\s+" steering/structure.md | cut -d' ' -f2) <(find src -type d -maxdepth 2)
 
-# 3. Check if product.md features match storage/features/
-diff <(grep "Feature" steering/product.md) <(ls storage/features/)
+# 3. Check if product.md features match storage/specs/
+diff <(grep "Feature" steering/product.md) <(ls storage/specs/)
 ```
 
 ### Report Divergence
@@ -268,7 +268,7 @@ diff <(grep "Feature" steering/product.md) <(ls storage/features/)
 
 ### product.md
 
-- ⚠️ Missing feature: payment-integration (in storage/features/)
+- ⚠️ Missing feature: payment-integration (in storage/specs/)
 
 ## Recommendations
 
@@ -310,7 +310,7 @@ on:
     paths:
       - 'package.json'
       - 'src/**'
-      - 'storage/features/**'
+      - 'storage/specs/**'
 
 jobs:
   check-steering:

package/src/templates/agents/claude-code/skills/traceability-auditor/SKILL.md

@@ -101,9 +101,9 @@ Test Suite (tests/auth/service.test.ts)
 
 ### Phase 1: Collect Artifacts
 
-1. Read `storage/features/[feature]/requirements.md`
-2. Read `storage/features/[feature]/design.md`
-3. Read `storage/features/[feature]/tasks.md`
+1. Read `storage/specs/[feature]-requirements.md`
+2. Read `storage/specs/[feature]-design.md`
+3. Read `storage/specs/[feature]-tasks.md`
 4. Scan source code for implementation
 5. Scan test files for test cases
 
@@ -290,7 +290,7 @@ coverage_test = (requirements_with_tests / requirements_total) * 100
 - **After**:
   - If gaps found → orchestrator triggers missing skills
   - If complete → quality-assurance approves release
-- **Uses**: All spec files in `storage/features/` and `storage/changes/`
+- **Uses**: All spec files in `storage/specs/` and `storage/changes/`
 
 ## Gap Detection Rules
 

package/src/templates/agents/claude-code/skills/traceability-auditor/coverage-matrix-template.md

@@ -99,9 +99,9 @@ Template for creating traceability coverage matrices that ensure 100% compliance
 def generate_traceability_matrix(feature_name):
     """Generate traceability matrix for a feature."""
 
-    requirements = parse_requirements(f"storage/features/{feature_name}/requirements.md")
-    design = parse_design(f"storage/features/{feature_name}/design.md")
-    tasks = parse_tasks(f"storage/features/{feature_name}/tasks.md")
+    requirements = parse_requirements(f"storage/specs/{feature_name}-requirements.md")
+    design = parse_design(f"storage/specs/{feature_name}-design.md")
+    tasks = parse_tasks(f"storage/specs/{feature_name}-tasks.md")
     code_files = find_code_files(f"src/{feature_name}/")
     test_files = find_test_files(f"tests/{feature_name}/")
 

package/src/templates/agents/claude-code/skills/traceability-auditor/gap-detection-rules.md

@@ -94,8 +94,8 @@ for ref in all_references:
 #!/bin/bash
 # find-orphaned-requirements.sh
 
-REQ_FILE="storage/features/$1/requirements.md"
-DESIGN_FILE="storage/features/$1/design.md"
+REQ_FILE="storage/specs/$1-requirements.md"
+DESIGN_FILE="storage/specs/$1-design.md"
 
 # Extract requirement IDs
 grep -oP 'REQ-[\w-]+' "$REQ_FILE" | sort -u > /tmp/reqs.txt
@@ -212,7 +212,7 @@ name: Traceability Check
 on:
   pull_request:
     paths:
-      - 'storage/features/**'
+      - 'storage/specs/**'
       - 'src/**'
       - 'tests/**'
 

package/src/templates/agents/github-copilot/commands/sdd-requirements.prompt.md

@@ -1,10 +1,10 @@
 # SDD Requirements Command
 
-Create EARS-format requirements specification.
+Create EARS-format requirements specification through interactive dialogue.
 
 ---
 
-## Instructions for Claude
+## Instructions for AI Agent
 
 You are executing the `/sdd-requirements [feature-name]` command to create a requirements specification.
 
@@ -18,7 +18,14 @@ You are executing the `/sdd-requirements [feature-name]` command to create a req
 
 ### Your Task
 
-Generate a comprehensive requirements specification in EARS format for the specified feature.
+**CRITICAL**: Before generating requirements, you MUST engage in an interactive 1-on-1 dialogue with the user to uncover the TRUE PURPOSE behind their request. Surface-level requirements often hide deeper needs.
+
+### Output Directory
+
+**Requirements documents are saved to**: `storage/specs/`
+
+- English: `storage/specs/{{feature-name}}-requirements.md`
+- Japanese: `storage/specs/{{feature-name}}-requirements.ja.md`
 
 ---
 
@@ -44,28 +51,142 @@ steering/tech.md         # Technology stack
 
 ---
 
-### 2. Gather Requirements
+### 2. Interactive True Purpose Discovery (1-on-1 Dialogue)
+
+**CRITICAL RULE**: You MUST ask exactly ONE question, then STOP and WAIT for the user's response. Do NOT ask multiple questions at once. Do NOT list all questions. Do NOT proceed until the user answers.
+
+#### Dialogue Rules (MANDATORY)
 
-**Methods** (use as appropriate):
+1. **ONE QUESTION ONLY**: Ask a single question per turn
+2. **STOP AND WAIT**: After asking, end your response immediately
+3. **NO QUESTION LISTS**: Never show "Q1, Q2, Q3..." format
+4. **SEQUENTIAL FLOW**: Move to next question only after receiving an answer
 
-#### A. Stakeholder Interview (if user is available)
+#### Phase 1: Surface Purpose → True Purpose Discovery
 
-Use `AskUserQuestion` tool to ask:
+**Question Sequence** (Ask ONE at a time, wait for answer before next):
 
-- Who are the users of this feature?
-- What problem does this solve?
-- What are the critical workflows?
-- What are the acceptance criteria?
-- Are there any constraints (performance, security, compliance)?
+**Turn 1**: Start with the WHY question
+```
+この機能で解決したい『本当の課題』は何ですか？
+```
+→ STOP HERE. Wait for user response.
 
-#### B. Research Existing System (brownfield)
+**Turn 2**: Based on answer, ask WHO question
+```
+この機能を最も必要としているのは誰ですか？
+```
+→ STOP HERE. Wait for user response.
+
+**Turn 3**: Ask WHAT-IF question
+```
+もしこの機能が完璧に動作したら、何が変わりますか？
+```
+→ STOP HERE. Wait for user response.
+
+**Turn 4**: Ask CONSTRAINT question
+```
+この機能で『絶対にやってはいけないこと』はありますか？
+```
+→ STOP HERE. Wait for user response.
+
+**Turn 5**: Ask SUCCESS CRITERIA question
+```
+この機能が『成功した』と言えるのはどんな状態ですか？
+```
+→ STOP HERE. Wait for user response.
+
+**After 5+ turns**: Summarize and confirm
+```
+ここまでの理解を確認させてください：
+[Summary]
+この理解で正しいですか？
+```
+
+#### Example Dialogue Flow
+
+**AI Turn 1**:
+> まず、この機能について教えてください。
+> 
+> **この機能で解決したい『本当の課題』は何ですか？**
+
+**User**: "CSVから社員データをインポートしたい"
+
+**AI Turn 2**:
+> なるほど、社員データのCSVインポートですね。
+> 
+> **このインポート機能を最も必要としているのは誰ですか？**（人事部？IT管理者？）
+
+**User**: "人事部です"
+
+**AI Turn 3**:
+> 人事部の方が使うのですね。
+> 
+> **もしこの機能が完璧に動作したら、人事部の業務はどう変わりますか？**
+
+...(continues one question at a time)
+
+---
+
+### 3. MECE Analysis (Comprehensive Coverage)
+
+**After understanding the TRUE PURPOSE, apply MECE to ensure completeness.**
+
+#### MECE Dimensions for Requirements
+
+**Dimension 1: User Journey (Who × When × Where)**
+| Stage | Questions to Cover |
+|-------|--------------------|
+| Before | How do users discover/access this feature? |
+| During | What is the core interaction flow? |
+| After | What happens after completion? Notifications? |
+| Error | What happens when something goes wrong? |
+
+**Dimension 2: Data Lifecycle (CRUD)**
+| Operation | Check |
+|-----------|-------|
+| Create | What data is created? By whom? |
+| Read | Who can view? What format? |
+| Update | What can be modified? By whom? |
+| Delete | Soft delete? Hard delete? Retention? |
+
+**Dimension 3: Cross-Cutting Concerns**
+| Concern | Requirements |
+|---------|-------------|
+| Security | Authentication, Authorization, Encryption |
+| Performance | Response time, Throughput, Concurrency |
+| Reliability | Error handling, Recovery, Failover |
+| Scalability | Load limits, Growth capacity |
+| Compliance | GDPR, SOC2, PCI-DSS (if applicable) |
+
+**Dimension 4: Integration Points**
+| Integration | Check |
+|-------------|-------|
+| Upstream | What systems feed data to this feature? |
+| Downstream | What systems consume this feature's output? |
+| External | Any third-party APIs or services? |
+
+**MECE Completeness Check**:
+- [ ] All user types covered?
+- [ ] All states (normal, edge, error) covered?
+- [ ] All data flows covered?
+- [ ] All integration points covered?
+- [ ] No overlapping requirements?
+
+---
+
+### 4. Research Existing System (Brownfield)
+
+**If modifying existing functionality**:
 
 - Search for existing implementation: `grep -r "{{feature}}" src/`
 - Read related code
 - Identify current behavior
 - Document what needs to change (delta spec)
 
-#### C. Infer from Context
+---
+
+### 5. Contextual Research
 
 - Analyze steering/product.md for user types
 - Review existing requirements docs
@@ -73,7 +194,9 @@ Use `AskUserQuestion` tool to ask:
 
 ---
 
-### 3. Generate Requirements Document
+### 6. Generate Requirements Document
+
+**Output Directory**: `storage/specs/`
 
 Use template from `templates/requirements.md`:
 
@@ -84,13 +207,41 @@ Use template from `templates/requirements.md`:
 
 ## Overview
 
-- Purpose
+- Purpose (True Purpose discovered through dialogue)
 - Scope (in/out)
 - Business context (from steering/product.md)
 
+## True Purpose Statement
+
+[Summary of TRUE PURPOSE uncovered through dialogue]
+
+- Surface Request: [What user initially asked for]
+- True Purpose: [What user actually needs]
+- Key Insight: [Critical understanding gained]
+
 ## Stakeholders
 
-[Table of roles]
+[Table of roles identified through dialogue]
+
+## MECE Coverage Summary
+
+### User Journey Coverage
+- [ ] Before: Entry/Discovery
+- [ ] During: Core Flow
+- [ ] After: Completion
+- [ ] Error: Exception Handling
+
+### Data Lifecycle Coverage
+- [ ] Create
+- [ ] Read
+- [ ] Update
+- [ ] Delete
+
+### Cross-Cutting Concerns
+- [ ] Security
+- [ ] Performance
+- [ ] Reliability
+- [ ] Scalability
 
 ## Functional Requirements
 
@@ -98,6 +249,8 @@ Use template from `templates/requirements.md`:
 
 [EARS Pattern - choose appropriate pattern]
 
+**MECE Category**: [User Journey Stage | Data Operation | etc.]
+
 **Acceptance Criteria**:
 
 - [Testable criterion 1]
@@ -119,6 +272,10 @@ Use template from `templates/requirements.md`:
 
 ### REQ-AVAIL-001: Availability
 
+## MECE Gap Analysis
+
+[List any gaps identified during MECE analysis]
+
 ## Requirements Coverage Matrix
 
 [Initial table - will be filled during design/implementation]
@@ -126,7 +283,7 @@ Use template from `templates/requirements.md`:
 
 ---
 
-### 4. Apply EARS Format (Article IV)
+### 7. Apply EARS Format (Article IV)
 
 **CRITICAL**: All requirements MUST use one of 5 EARS patterns.
 
@@ -150,10 +307,11 @@ Each requirement MUST have:
 - [ ] Testable acceptance criteria
 - [ ] Priority (P0/P1/P2/P3)
 - [ ] Status (Draft initially)
+- [ ] MECE Category (for traceability)
 
 ---
 
-### 5. Assign Requirement IDs
+### 8. Assign Requirement IDs
 
 **Format**: `REQ-[COMPONENT]-[NUMBER]`
 
@@ -172,7 +330,7 @@ Each requirement MUST have:
 
 ---
 
-### 6. Add Non-Functional Requirements
+### 9. Add Non-Functional Requirements (from MECE Cross-Cutting Concerns)
 
 Always include these categories:
 
@@ -221,7 +379,7 @@ The {{COMPONENT}} SHALL maintain 99.9% uptime.
 
 ---
 
-### 7. Brownfield: Create Delta Specification
+### 10. Brownfield: Create Delta Specification
 
 If this is a change to existing system, add delta sections:
 
@@ -266,7 +424,7 @@ The authentication system SHALL hash passwords using bcrypt cost 12.
 
 ---
 
-### 8. Constitutional Validation
+### 11. Constitutional Validation
 
 Validate requirements against constitutional articles:
 
@@ -290,10 +448,12 @@ Run validation:
 
 ---
 
-### 9. Save Document (Bilingual)
+### 12. Save Document (Bilingual)
 
 **IMPORTANT**: Create BOTH English and Japanese versions.
 
+**Output Directory**: `storage/specs/`
+
 **English version (Primary/Reference)**:
 Save to: `storage/specs/{{feature-name}}-requirements.md`
 
@@ -323,7 +483,7 @@ Save to: `storage/specs/{{feature-name}}-requirements.ja.md`
 
 ---
 
-### 10. Generate Summary
+### 13. Generate Summary
 
 Present summary to user:
 
@@ -331,11 +491,25 @@ Present summary to user:
 ## ✅ Requirements Specification Complete
 
 **Feature**: {{FEATURE_NAME}}
+**Output Directory**: `storage/specs/`
 **Files**:
 
 - English: storage/specs/{{feature-name}}-requirements.md
 - Japanese: storage/specs/{{feature-name}}-requirements.ja.md
 
+### True Purpose Discovery:
+
+- Surface Request: [What user initially asked]
+- True Purpose: [What user actually needs]
+- Key Insight: [Critical understanding gained]
+
+### MECE Coverage:
+
+- User Journey: ✅ All stages covered
+- Data Lifecycle: ✅ CRUD covered
+- Cross-Cutting: ✅ Security/Performance/Reliability/Scalability
+- Integrations: ✅ Upstream/Downstream/External
+
 ### Summary:
 
 - **Total Requirements**: [N]
@@ -381,28 +555,54 @@ Present summary to user:
 ### User Command:
 
 ```bash
-/sdd-requirements authentication
+#sdd-requirements authentication
 ```
 
-### Claude Actions:
+### AI Agent Actions:
 
 1. **Read Steering**:
    - `steering/product.md` → Target users: B2B SaaS companies
    - `steering/tech.md` → Stack: Next.js, PostgreSQL, Prisma
    - `steering/structure.md` → Pattern: Library-first
 
-2. **Ask User** (if needed):
+2. **Interactive Dialogue (1-on-1)**:
 
-   ```
-   Questions about authentication feature:
-   1. Authentication methods: Email/password, OAuth, SSO, or all?
-   2. Required features: 2FA, password reset, session management?
-   3. Security: Any compliance requirements (SOC2, HIPAA)?
-   ```
+   **AI**: 「認証機能について、この機能で解決したい『本当の課題』は何ですか？」
+
+   **User**: 「ユーザーがログインできるようにしたい」
+
+   **AI**: 「なるほど。では、この機能がないと、誰がどのように困りますか？」
+
+   **User**: 「顧客がサービスを使えない。また、管理者が顧客データを保護できない」
+
+   **AI**: 「顧客データの保護が重要なのですね。この機能で『絶対にやってはいけないこと』はありますか？」
+
+   **User**: 「データ漏洩。SOC2準拠が必要」
+
+   **AI**: 「SOC2準拠が必要とのこと。この機能が『成功した』と言えるのはどんな状態ですか？」
+
+   **User**: 「ログイン成功率99%以上、不正アクセスゼロ」
+
+   **AI**: 「理解しました。確認させてください：
+   - **表面的要求**: ユーザーがログインできること
+   - **真の目的**: SOC2準拠でセキュアな顧客データ保護
+   - **成功基準**: ログイン成功率99%以上、不正アクセスゼロ
+   この理解で正しいですか？」
 
-3. **Generate Requirements**:
+3. **MECE Analysis**:
+   - User Journey: Login → Session → Logout → Error handling
+   - Data: Credentials(C), Session(RUD), Audit Log(CR)
+   - Security: Authentication, Authorization, Encryption, Audit
+
+4. **Generate Requirements**:
 
    ```markdown
+   ## True Purpose Statement
+
+   - Surface Request: ユーザーログイン機能
+   - True Purpose: SOC2準拠のセキュアな顧客データ保護基盤
+   - Key Insight: 単なるログインではなく、コンプライアンス要件が重要
+
    ### REQ-AUTH-001: User Login
 
    WHEN a user provides valid credentials,
@@ -410,19 +610,19 @@ Present summary to user:
    AND the system SHALL create a session
    AND the system SHALL redirect to dashboard.
 
-   ### REQ-AUTH-002: Password Strength
+   **MECE Category**: User Journey - During
 
-   The authentication system SHALL enforce password requirements:
+   ### REQ-AUTH-002: Audit Logging (SOC2)
 
-   - Minimum 12 characters
-   - At least 1 uppercase, 1 lowercase, 1 number, 1 special char
+   The authentication system SHALL log all authentication events
+   with timestamp, user ID, IP address, and result.
 
-   [... more requirements ...]
+   **MECE Category**: Cross-Cutting - Security/Compliance
    ```
 
-4. **Save**: `storage/specs/authentication-requirements.md`
+5. **Save to Output Directory**: `storage/specs/authentication-requirements.md`
 
-5. **Summarize**: Present summary to user
+6. **Summarize**: Present summary with MECE coverage report
 
 ---
 
@@ -446,15 +646,18 @@ Present summary to user:
 
 Before completing, verify:
 
+- [ ] Interactive dialogue conducted (TRUE PURPOSE discovered)
+- [ ] MECE analysis completed (all dimensions covered)
 - [ ] Steering context read and applied
 - [ ] All requirements in EARS format
 - [ ] Requirement IDs assigned (REQ-XXX-NNN)
+- [ ] MECE category assigned to each requirement
 - [ ] Acceptance criteria defined for each requirement
 - [ ] Priority assigned (P0/P1/P2/P3)
 - [ ] Non-functional requirements included
 - [ ] Constitutional validation passed
 - [ ] Document saved to storage/specs/
-- [ ] Summary presented to user
+- [ ] Summary with MECE coverage presented to user
 
 ---
 
@@ -486,4 +689,14 @@ If `storage/specs/{{feature-name}}-requirements.md` exists:
 
 ---
 
+**Output Directory Summary**:
+- Requirements documents: `storage/specs/{{feature-name}}-requirements.md`
+- Japanese version: `storage/specs/{{feature-name}}-requirements.ja.md`
+
+---
+
+**Execution**: Begin interactive dialogue now for the specified feature.
+
+---
+
 **Execution**: Begin requirements generation now for the specified feature.