musubi-sdd 5.1.0 → 5.6.1

package/src/templates/agents/claude-code/skills/orchestrator/selection-matrix.md

@@ -8,82 +8,82 @@ This matrix helps the Orchestrator select the optimal agent(s) based on user req
 
 ## Category 1: Orchestration & Management (3 Skills)
 
-| Agent | Trigger Terms | Primary Use Cases | Priority |
-|-------|--------------|-------------------|----------|
-| **orchestrator** | coordinate, multi-agent, workflow, execution plan, project planning, complex task, full lifecycle | Complex multi-agent tasks, project coordination | 1 |
-| **steering** | project memory, codebase analysis, architecture patterns, tech stack, analyze project | Project context generation, steering files | 2 |
-| **constitution-enforcer** | constitution, compliance, validation, Phase -1 Gates, governance | Constitutional validation, pre-implementation gates | 3 |
+| Agent                     | Trigger Terms                                                                                     | Primary Use Cases                                   | Priority |
+| ------------------------- | ------------------------------------------------------------------------------------------------- | --------------------------------------------------- | -------- |
+| **orchestrator**          | coordinate, multi-agent, workflow, execution plan, project planning, complex task, full lifecycle | Complex multi-agent tasks, project coordination     | 1        |
+| **steering**              | project memory, codebase analysis, architecture patterns, tech stack, analyze project             | Project context generation, steering files          | 2        |
+| **constitution-enforcer** | constitution, compliance, validation, Phase -1 Gates, governance                                  | Constitutional validation, pre-implementation gates | 3        |
 
 ---
 
 ## Category 2: Requirements & Planning (3 Skills)
 
-| Agent | Trigger Terms | Primary Use Cases | Priority |
-|-------|--------------|-------------------|----------|
-| **requirements-analyst** | requirements, EARS, user stories, acceptance criteria, specification, SRS | Create/validate requirements | 1 |
-| **project-manager** | project plan, timeline, milestones, risk management, WBS, Gantt | Project planning, risk management | 2 |
-| **change-impact-analyzer** | change proposal, impact analysis, brownfield, delta spec, modification | Brownfield change analysis | 3 |
+| Agent                      | Trigger Terms                                                             | Primary Use Cases                 | Priority |
+| -------------------------- | ------------------------------------------------------------------------- | --------------------------------- | -------- |
+| **requirements-analyst**   | requirements, EARS, user stories, acceptance criteria, specification, SRS | Create/validate requirements      | 1        |
+| **project-manager**        | project plan, timeline, milestones, risk management, WBS, Gantt           | Project planning, risk management | 2        |
+| **change-impact-analyzer** | change proposal, impact analysis, brownfield, delta spec, modification    | Brownfield change analysis        | 3        |
 
 ---
 
 ## Category 3: Architecture & Design (4 Skills)
 
-| Agent | Trigger Terms | Primary Use Cases | Priority |
-|-------|--------------|-------------------|----------|
-| **system-architect** | architecture, C4, ADR, design decisions, component diagram, system design | High-level architecture design | 1 |
-| **api-designer** | API, REST, GraphQL, OpenAPI, endpoints, swagger, contract | API specification design | 2 |
-| **database-schema-designer** | database, schema, ERD, SQL, tables, relations, normalization | Database schema design | 3 |
-| **ui-ux-designer** | UI, UX, wireframe, mockup, design system, user interface | UI/UX design | 4 |
+| Agent                        | Trigger Terms                                                             | Primary Use Cases              | Priority |
+| ---------------------------- | ------------------------------------------------------------------------- | ------------------------------ | -------- |
+| **system-architect**         | architecture, C4, ADR, design decisions, component diagram, system design | High-level architecture design | 1        |
+| **api-designer**             | API, REST, GraphQL, OpenAPI, endpoints, swagger, contract                 | API specification design       | 2        |
+| **database-schema-designer** | database, schema, ERD, SQL, tables, relations, normalization              | Database schema design         | 3        |
+| **ui-ux-designer**           | UI, UX, wireframe, mockup, design system, user interface                  | UI/UX design                   | 4        |
 
 ---
 
 ## Category 4: Development & Implementation (2 Skills)
 
-| Agent | Trigger Terms | Primary Use Cases | Priority |
-|-------|--------------|-------------------|----------|
-| **software-developer** | implement, code, develop, build, programming, feature development | Code implementation | 1 |
-| **ai-ml-engineer** | machine learning, ML, AI, model, training, MLOps, neural network | ML/AI development | 2 |
+| Agent                  | Trigger Terms                                                     | Primary Use Cases   | Priority |
+| ---------------------- | ----------------------------------------------------------------- | ------------------- | -------- |
+| **software-developer** | implement, code, develop, build, programming, feature development | Code implementation | 1        |
+| **ai-ml-engineer**     | machine learning, ML, AI, model, training, MLOps, neural network  | ML/AI development   | 2        |
 
 ---
 
 ## Category 5: Quality & Review (5 Skills)
 
-| Agent | Trigger Terms | Primary Use Cases | Priority |
-|-------|--------------|-------------------|----------|
-| **code-reviewer** | code review, review, PR review, pull request, code quality | Code review | 1 |
-| **bug-hunter** | bug, debug, issue, error, root cause, investigation | Bug investigation | 2 |
-| **traceability-auditor** | traceability, coverage matrix, requirements tracking, EARS coverage | Traceability validation | 3 |
-| **security-auditor** | security, vulnerability, OWASP, penetration, security audit | Security review | 4 |
-| **performance-optimizer** | performance, optimization, benchmark, profiling, latency | Performance optimization | 5 |
+| Agent                     | Trigger Terms                                                       | Primary Use Cases        | Priority |
+| ------------------------- | ------------------------------------------------------------------- | ------------------------ | -------- |
+| **code-reviewer**         | code review, review, PR review, pull request, code quality          | Code review              | 1        |
+| **bug-hunter**            | bug, debug, issue, error, root cause, investigation                 | Bug investigation        | 2        |
+| **traceability-auditor**  | traceability, coverage matrix, requirements tracking, EARS coverage | Traceability validation  | 3        |
+| **security-auditor**      | security, vulnerability, OWASP, penetration, security audit         | Security review          | 4        |
+| **performance-optimizer** | performance, optimization, benchmark, profiling, latency            | Performance optimization | 5        |
 
 ---
 
 ## Category 6: QA (2 Skills)
 
-| Agent | Trigger Terms | Primary Use Cases | Priority |
-|-------|--------------|-------------------|----------|
-| **test-engineer** | test, testing, unit test, integration test, E2E, test cases | Test creation and execution | 1 |
-| **quality-assurance** | QA, quality plan, test strategy, quality metrics | QA strategy | 2 |
+| Agent                 | Trigger Terms                                               | Primary Use Cases           | Priority |
+| --------------------- | ----------------------------------------------------------- | --------------------------- | -------- |
+| **test-engineer**     | test, testing, unit test, integration test, E2E, test cases | Test creation and execution | 1        |
+| **quality-assurance** | QA, quality plan, test strategy, quality metrics            | QA strategy                 | 2        |
 
 ---
 
 ## Category 7: Infrastructure & Operations (5 Skills)
 
-| Agent | Trigger Terms | Primary Use Cases | Priority |
-|-------|--------------|-------------------|----------|
-| **devops-engineer** | CI/CD, pipeline, deployment, GitHub Actions, GitLab CI | CI/CD setup | 1 |
-| **release-coordinator** | release, versioning, changelog, feature flags, rollout | Release management | 2 |
-| **cloud-architect** | cloud, AWS, Azure, GCP, Terraform, infrastructure | Cloud infrastructure | 3 |
-| **site-reliability-engineer** | SRE, monitoring, observability, SLO, alerting, incident | Production monitoring | 4 |
-| **database-administrator** | DBA, database tuning, backup, recovery, replication | Database operations | 5 |
+| Agent                         | Trigger Terms                                           | Primary Use Cases     | Priority |
+| ----------------------------- | ------------------------------------------------------- | --------------------- | -------- |
+| **devops-engineer**           | CI/CD, pipeline, deployment, GitHub Actions, GitLab CI  | CI/CD setup           | 1        |
+| **release-coordinator**       | release, versioning, changelog, feature flags, rollout  | Release management    | 2        |
+| **cloud-architect**           | cloud, AWS, Azure, GCP, Terraform, infrastructure       | Cloud infrastructure  | 3        |
+| **site-reliability-engineer** | SRE, monitoring, observability, SLO, alerting, incident | Production monitoring | 4        |
+| **database-administrator**    | DBA, database tuning, backup, recovery, replication     | Database operations   | 5        |
 
 ---
 
 ## Category 8: Documentation (1 Skill)
 
-| Agent | Trigger Terms | Primary Use Cases | Priority |
-|-------|--------------|-------------------|----------|
-| **technical-writer** | documentation, docs, README, user guide, API docs | Documentation creation | 1 |
+| Agent                | Trigger Terms                                     | Primary Use Cases      | Priority |
+| -------------------- | ------------------------------------------------- | ---------------------- | -------- |
+| **technical-writer** | documentation, docs, README, user guide, API docs | Documentation creation | 1        |
 
 ---
 
@@ -91,47 +91,50 @@ This matrix helps the Orchestrator select the optimal agent(s) based on user req
 
 ### By SDD Workflow Stage
 
-| Stage | Primary Agent | Supporting Agents |
-|-------|--------------|-------------------|
-| 1. Research | steering | - |
-| 2. Requirements | requirements-analyst | change-impact-analyzer |
-| 3. Design | system-architect | api-designer, database-schema-designer, ui-ux-designer |
-| 4. Task Breakdown | project-manager | orchestrator |
-| 5. Implementation | software-developer | ai-ml-engineer |
-| 6. Testing | test-engineer | quality-assurance |
-| 7. Deployment | devops-engineer | release-coordinator, cloud-architect |
-| 8. Monitoring | site-reliability-engineer | database-administrator |
+| Stage             | Primary Agent             | Supporting Agents                                      |
+| ----------------- | ------------------------- | ------------------------------------------------------ |
+| 1. Research       | steering                  | -                                                      |
+| 2. Requirements   | requirements-analyst      | change-impact-analyzer                                 |
+| 3. Design         | system-architect          | api-designer, database-schema-designer, ui-ux-designer |
+| 4. Task Breakdown | project-manager           | orchestrator                                           |
+| 5. Implementation | software-developer        | ai-ml-engineer                                         |
+| 6. Testing        | test-engineer             | quality-assurance                                      |
+| 7. Deployment     | devops-engineer           | release-coordinator, cloud-architect                   |
+| 8. Monitoring     | site-reliability-engineer | database-administrator                                 |
 
 ### By Task Type
 
-| Task Type | Agent Selection |
-|-----------|-----------------|
+| Task Type              | Agent Selection                                    |
+| ---------------------- | -------------------------------------------------- |
 | New greenfield project | steering → requirements-analyst → system-architect |
-| Brownfield change | change-impact-analyzer → requirements-analyst |
-| Bug fix | bug-hunter → software-developer → test-engineer |
-| Security audit | security-auditor |
-| Performance issue | performance-optimizer |
-| Code review | code-reviewer |
-| Documentation | technical-writer |
-| Release preparation | release-coordinator → devops-engineer |
+| Brownfield change      | change-impact-analyzer → requirements-analyst      |
+| Bug fix                | bug-hunter → software-developer → test-engineer    |
+| Security audit         | security-auditor                                   |
+| Performance issue      | performance-optimizer                              |
+| Code review            | code-reviewer                                      |
+| Documentation          | technical-writer                                   |
+| Release preparation    | release-coordinator → devops-engineer              |
 
 ---
 
 ## Multi-Agent Selection Rules
 
 ### Rule 1: Always Start with Context
+
 ```
 IF project context unclear:
     SELECT steering FIRST
 ```
 
 ### Rule 2: Requirements Before Design
+
 ```
 IF design requested AND no requirements exist:
     SELECT requirements-analyst BEFORE system-architect
 ```
 
 ### Rule 3: Test-First for Implementation
+
 ```
 IF implementation requested:
     SELECT test-engineer BEFORE software-developer
@@ -139,12 +142,14 @@ IF implementation requested:
 ```
 
 ### Rule 4: Validate Before Release
+
 ```
 IF release requested:
     SELECT constitution-enforcer, traceability-auditor BEFORE release-coordinator
 ```
 
 ### Rule 5: Parallel Audits
+
 ```
 IF comprehensive audit requested:
     SELECT PARALLEL:
@@ -179,7 +184,7 @@ User Request
 
 ## Additional Skills (Beyond Original 25)
 
-| Agent | Trigger Terms | Primary Use Cases |
-|-------|--------------|-------------------|
-| **agent-assistant** | agent help, MUSUBI help, how to use | MUSUBI usage guidance |
-| **issue-resolver** | GitHub issue, issue resolution, PR issue | Issue/PR resolution |
+| Agent               | Trigger Terms                            | Primary Use Cases     |
+| ------------------- | ---------------------------------------- | --------------------- |
+| **agent-assistant** | agent help, MUSUBI help, how to use      | MUSUBI usage guidance |
+| **issue-resolver**  | GitHub issue, issue resolution, PR issue | Issue/PR resolution   |

package/src/templates/agents/claude-code/skills/performance-engineer/optimization-playbook.md

@@ -17,29 +17,29 @@ const metrics = {
   responseTime: {
     p50: 'median response',
     p95: '95th percentile',
-    p99: '99th percentile'
+    p99: '99th percentile',
   },
-  
+
   // Throughput
   throughput: {
     rps: 'requests per second',
-    tps: 'transactions per second'
+    tps: 'transactions per second',
   },
-  
+
   // Resources
   resources: {
     cpu: 'CPU utilization %',
     memory: 'Memory usage MB',
     disk: 'Disk I/O ops/sec',
-    network: 'Network bandwidth MB/s'
+    network: 'Network bandwidth MB/s',
   },
-  
+
   // Application
   application: {
     errorRate: 'errors per minute',
     gcTime: 'garbage collection time',
-    activeConnections: 'db/cache connections'
-  }
+    activeConnections: 'db/cache connections',
+  },
 };
 ```
 
@@ -73,14 +73,14 @@ thresholds:
 import http from 'k6/http';
 import { check, sleep } from 'k6';
 
-export default function() {
+export default function () {
   const res = http.get('https://api.example.com/users');
-  
+
   check(res, {
-    'status is 200': (r) => r.status === 200,
-    'response time < 500ms': (r) => r.timings.duration < 500,
+    'status is 200': r => r.status === 200,
+    'response time < 500ms': r => r.timings.duration < 500,
   });
-  
+
   sleep(1);
 }
 ```
@@ -91,13 +91,13 @@ export default function() {
 
 ### 2.1 Common Bottleneck Patterns
 
-| Pattern | Symptoms | Root Cause |
-|---------|----------|------------|
-| CPU Bound | High CPU, low I/O wait | Computation intensive code |
-| I/O Bound | Low CPU, high I/O wait | Database/file operations |
-| Memory Bound | High memory, GC pauses | Memory leaks, large objects |
-| Network Bound | High latency, low CPU | External API calls |
-| Lock Contention | Thread blocking | Synchronization issues |
+| Pattern         | Symptoms               | Root Cause                  |
+| --------------- | ---------------------- | --------------------------- |
+| CPU Bound       | High CPU, low I/O wait | Computation intensive code  |
+| I/O Bound       | Low CPU, high I/O wait | Database/file operations    |
+| Memory Bound    | High memory, GC pauses | Memory leaks, large objects |
+| Network Bound   | High latency, low CPU  | External API calls          |
+| Lock Contention | Thread blocking        | Synchronization issues      |
 
 ### 2.2 Profiling Checklist
 
@@ -156,7 +156,7 @@ async function getUsers() {
 // ✅ Eager Loading
 async function getUsers() {
   const users = await User.findAll({
-    include: [{ model: Order }]
+    include: [{ model: Order }],
   });
   return users;
 }
@@ -179,8 +179,8 @@ async function processFiles(files) {
 class CacheManager {
   constructor() {
     this.l1 = new Map(); // In-memory (fastest)
-    this.l2 = redis;     // Redis (fast)
-    this.l3 = database;  // Database (source of truth)
+    this.l2 = redis; // Redis (fast)
+    this.l3 = database; // Database (source of truth)
   }
 
   async get(key) {
@@ -211,7 +211,7 @@ class CacheManager {
 
 ```sql
 -- Add composite index
-CREATE INDEX CONCURRENTLY idx_orders_user_status 
+CREATE INDEX CONCURRENTLY idx_orders_user_status
 ON orders (user_id, status, created_at DESC);
 
 -- Partial index for common queries
@@ -224,8 +224,8 @@ WHERE status = 'pending';
 SELECT * FROM orders WHERE YEAR(created_at) = 2024;
 
 -- ✅ After (index-friendly)
-SELECT * FROM orders 
-WHERE created_at >= '2024-01-01' 
+SELECT * FROM orders
+WHERE created_at >= '2024-01-01'
   AND created_at < '2025-01-01';
 ```
 
@@ -239,26 +239,26 @@ WHERE created_at >= '2024-01-01'
 // Compare before/after metrics
 const comparison = {
   before: {
-    p50: 250,   // ms
+    p50: 250, // ms
     p95: 800,
     p99: 1500,
     rps: 100,
-    errorRate: 0.02
+    errorRate: 0.02,
   },
   after: {
-    p50: 80,    // ms
+    p50: 80, // ms
     p95: 200,
     p99: 400,
     rps: 350,
-    errorRate: 0.005
+    errorRate: 0.005,
   },
   improvement: {
     p50: '-68%',
     p95: '-75%',
     p99: '-73%',
     rps: '+250%',
-    errorRate: '-75%'
-  }
+    errorRate: '-75%',
+  },
 };
 ```
 
@@ -282,25 +282,25 @@ performance-test:
 
 ### Response Time Targets
 
-| Tier | p50 | p95 | p99 |
-|------|-----|-----|-----|
-| Fast | <50ms | <100ms | <200ms |
-| Normal | <200ms | <500ms | <1000ms |
+| Tier       | p50    | p95     | p99     |
+| ---------- | ------ | ------- | ------- |
+| Fast       | <50ms  | <100ms  | <200ms  |
+| Normal     | <200ms | <500ms  | <1000ms |
 | Acceptable | <500ms | <2000ms | <5000ms |
 
 ### Memory Guidelines
 
-| App Type | Heap Size | GC Pause Target |
-|----------|-----------|-----------------|
-| API Server | 512MB-2GB | <50ms |
-| Worker | 1GB-4GB | <100ms |
-| Batch | 2GB-8GB | <500ms |
+| App Type   | Heap Size | GC Pause Target |
+| ---------- | --------- | --------------- |
+| API Server | 512MB-2GB | <50ms           |
+| Worker     | 1GB-4GB   | <100ms          |
+| Batch      | 2GB-8GB   | <500ms          |
 
 ### Caching TTL Guidelines
 
-| Data Type | TTL | Strategy |
-|-----------|-----|----------|
-| Static config | 1h-24h | Cache-aside |
-| User session | 15m-30m | Write-through |
-| API response | 1m-5m | Cache-aside |
-| Search results | 30s-5m | Cache-aside |
+| Data Type      | TTL     | Strategy      |
+| -------------- | ------- | ------------- |
+| Static config  | 1h-24h  | Cache-aside   |
+| User session   | 15m-30m | Write-through |
+| API response   | 1m-5m   | Cache-aside   |
+| Search results | 30s-5m  | Cache-aside   |

package/src/templates/agents/claude-code/skills/performance-optimizer/SKILL.md

@@ -27,6 +27,75 @@ You handle application performance analysis, bottleneck detection, optimization
 
 ---
 
+## MUSUBI LargeProjectAnalyzer Module (v5.5.0+)
+
+**Available Module**: `src/analyzers/large-project-analyzer.js`
+
+The LargeProjectAnalyzer module provides scale-aware analysis for enterprise-grade codebases (10M+ lines).
+
+### Module Usage
+
+```javascript
+const { LargeProjectAnalyzer, LARGE_PROJECT_THRESHOLDS } = require('musubi-sdd');
+
+const analyzer = new LargeProjectAnalyzer({
+  maxMemoryMB: 4096,
+  chunkSize: 100,
+  enableGC: true,
+});
+
+const result = await analyzer.analyze('/path/to/large-project', {
+  onProgress: progress => {
+    console.log(`${progress.percentage}% - ${progress.filesProcessed}/${progress.totalFiles}`);
+  },
+});
+
+console.log(`Scale: ${result.scale}`); // small, medium, large, massive
+console.log(`Total Files: ${result.totalFiles}`);
+console.log(`Giant Functions: ${result.giantFunctions.length}`);
+```
+
+### Scale-Based Strategy
+
+| Scale       | Files   | Strategy           | Memory Usage |
+| ----------- | ------- | ------------------ | ------------ |
+| **Small**   | ≤100    | Batch analysis     | Low          |
+| **Medium**  | ≤1,000  | Optimized batch    | Moderate     |
+| **Large**   | ≤10,000 | Chunked analysis   | Managed      |
+| **Massive** | >10,000 | Streaming analysis | Controlled   |
+
+### Giant Function Detection
+
+| Lines | Level    | Action               |
+| ----- | -------- | -------------------- |
+| 100+  | Warning  | Consider splitting   |
+| 500+  | Critical | Refactoring required |
+| 1000+ | Extreme  | Urgent refactoring   |
+
+### Multi-Language Support
+
+- JavaScript, TypeScript
+- C, C++
+- Python
+- Rust, Go
+- Java
+
+### Integration with Performance Optimization
+
+1. **Identify bottleneck files** in large codebases
+2. **Detect giant functions** that impact maintainability
+3. **Memory-efficient processing** for enterprise projects
+4. **Progress tracking** for long-running analysis
+
+```javascript
+// Get analysis summary
+console.log(`Files by Language: ${JSON.stringify(result.languageBreakdown)}`);
+console.log(`Average File Size: ${result.averageFileSize} lines`);
+console.log(`Largest Files: ${result.largestFiles.map(f => f.path).join(', ')}`);
+```
+
+---
+
 ---
 
 ## Project Memory (Steering System)