universal-dev-standards 5.0.0-rc.8 → 5.0.0

package/bundled/skills/dev-workflow-guide/SKILL.md

@@ -14,6 +14,10 @@ Map your current software development phase to the right UDS commands and skills
 
 將你目前的軟體開發階段對應到正確的 UDS 指令與技能。即時了解在開發的每個階段應該使用哪些工具。
 
+> **Related**: To choose or switch between development methodologies (SDD, BDD, TDD), use `/methodology` instead.
+>
+> **相關**：如需選擇或切換開發方法論（SDD、BDD、TDD），請改用 `/methodology`。
+
 ## Software Development Phases Overview | 軟體開發階段總覽
 
 ```
@@ -28,13 +32,13 @@ V. Release ──► VI. Documentation ──► VII. Standards ──► VIII.
 
 | Phase | UDS Commands | Purpose | 用途 |
 |-------|-------------|---------|------|
-| **I. Planning & Design** | `/brainstorm` `/requirement` `/sdd` `/reverse` | Requirements, specs, reverse engineering | 需求、規格、逆向工程 |
-| **II. Test-Driven Development** | `/bdd` `/atdd` `/tdd` `/coverage` `/derive` | Design tests before code | 先寫測試再寫程式 |
-| **III. Implementation** | `/refactor` `/reverse` | Write and improve code | 撰寫與改善程式碼 |
-| **IV. Quality Gates** | `/checkin` `/review` | Pre-commit and code review | 提交前檢查與程式碼審查 |
-| **V. Release & Commit** | `/commit` `/changelog` `/release` | Version, commit, publish | 版本、提交、發布 |
-| **VI. Documentation** | `/docs` `/docgen` `/struct` | Docs and project structure | 文件與專案結構 |
-| **VII. Tools & Standards** | `/discover` `/testing` `/guide` `/git` | Reference guides | 參考指南 |
+| **I. Planning & Design** | `/brainstorm` `/requirement` `/sdd` `/reverse` `/api-design` `/database` | Requirements, specs, API/DB design | 需求、規格、API/DB 設計 |
+| **II. Test-Driven Development** | `/bdd` `/atdd` `/tdd` `/coverage` `/derive` `/ac-coverage` | Design tests before code | 先寫測試再寫程式 |
+| **III. Implementation** | `/refactor` `/reverse` `/migrate` `/durable` | Write, improve, and migrate code | 撰寫、改善與遷移程式碼 |
+| **IV. Quality Gates** | `/checkin` `/review` `/security` `/scan` `/incident` | Quality, security, incident response | 品質、安全、事故回應 |
+| **V. Release & Commit** | `/commit` `/changelog` `/release` `/pr` `/ci-cd` | Version, commit, PR, CI/CD | 版本、提交、PR、CI/CD |
+| **VI. Documentation** | `/docs` `/docgen` | Docs and project structure | 文件與專案結構 |
+| **VII. Tools & Standards** | `/discover` `/guide` `/metrics` `/audit` | Reference guides, metrics, audit | 參考指南、指標、審計 |
 | **VIII. Advanced Analysis** | `/methodology` | Cross-methodology workflows | 跨方法論工作流程 |
 
 ## Common Scenarios | 常見場景
@@ -96,6 +100,42 @@ Recommended flow for code refactoring:
 | 5 | `/checkin` | Verify quality gates | 驗證品質關卡 |
 | 6 | `/commit` | Create conventional commit | 建立規範化提交 |
 
+### Scenario 4: Security Review | 安全審查
+
+Recommended flow for security review and vulnerability remediation:
+
+安全審查與漏洞修復的推薦流程：
+
+```
+/scan → /security → /checkin → /commit
+```
+
+| Step | Command | What to Do | 做什麼 |
+|------|---------|-----------|--------|
+| 1 | `/scan` | Run automated security scans (deps, secrets) | 執行自動化安全掃描 |
+| 2 | `/security` | Deep security review (OWASP) | 深入安全審查 |
+| 3 | `/checkin` | Verify quality gates | 驗證品質關卡 |
+| 4 | `/commit` | Create conventional commit | 建立規範化提交 |
+
+### Scenario 5: API Design & Implementation | API 設計與實作
+
+Recommended flow for designing and implementing APIs:
+
+API 設計與實作的推薦流程：
+
+```
+/brainstorm → /api-design → /sdd → /derive → /tdd → /pr
+```
+
+| Step | Command | What to Do | 做什麼 |
+|------|---------|-----------|--------|
+| 1 | `/brainstorm` | Explore API approaches | 探索 API 方案 |
+| 2 | `/api-design` | Design endpoints and schemas | 設計端點與 schema |
+| 3 | `/sdd` | Create specification document | 建立規格文件 |
+| 4 | `/derive` | Generate test skeletons | 產生測試骨架 |
+| 5 | `/tdd` | Implement with tests | 搭配測試實作 |
+| 6 | `/pr` | Create pull request | 建立 Pull Request |
+
 ## Usage | 使用方式
 
 ```bash
@@ -122,6 +162,8 @@ Recommended flow for code refactoring:
 | `new-feature` | Scenario: New feature workflow | 場景：新功能開發 |
 | `bug-fix` | Scenario: Bug fix workflow | 場景：修復錯誤 |
 | `refactoring` | Scenario: Refactoring workflow | 場景：重構 |
+| `security` | Scenario: Security review workflow | 場景：安全審查 |
+| `api` | Scenario: API design workflow | 場景：API 設計 |
 
 ## Workflow Behavior | 工作流程行為
 
@@ -148,6 +190,9 @@ After `/dev-workflow` completes, the AI assistant should suggest based on user's
 > - 修復錯誤 → 執行 `/discover` 評估受影響區域 — Bug fix → Run `/discover` to assess affected area
 > - 重構程式碼 → 執行 `/discover` 評估健康度 — Refactoring → Run `/discover` to assess health
 > - 遺留系統 → 執行 `/reverse` 進行系統考古 — Legacy system → Run `/reverse` for system archeology
+> - 安全審查 → 執行 `/scan` 掃描漏洞 — Security review → Run `/scan` to find vulnerabilities
+> - API 開發 → 執行 `/api-design` 設計端點 — API development → Run `/api-design` to design endpoints
+> - 事故回應 → 執行 `/incident` 啟動回應流程 — Incident → Run `/incident` to start response
 
 ## References | 參考
 
@@ -162,6 +207,7 @@ After `/dev-workflow` completes, the AI assistant should suggest based on user's
 
 | Version | Date | Changes |
 |---------|------|---------|
+| 1.1.0 | 2026-03-24 | Add 11 new commands, 2 new scenarios (Security Review, API Design) |
 | 1.0.0 | 2026-03-04 | Initial: 8 development phases, 3 scenarios, phase-based navigation |
 
 ---

package/bundled/skills/dev-workflow-guide/workflow-phases.md

@@ -18,6 +18,8 @@
 | `/requirement` | Write user stories (INVEST) | Defining what to build | 定義要建立什麼 |
 | `/sdd` | Create specification document | Before implementation | 實作前 |
 | `/reverse` | Reverse engineer existing code | Understanding brownfield codebase | 理解既有程式碼 |
+| `/api-design` | Design APIs (REST, GraphQL, gRPC) | Designing new API endpoints | 設計新 API 端點 |
+| `/database` | Database design and migration | Schema design, migration planning | Schema 設計、遷移規劃 |
 
 ### Typical Flow | 典型流程
 
@@ -32,6 +34,8 @@ Idea → /brainstorm → /requirement → /sdd → Ready for Phase II
 - **`/requirement`**: You know what to build but need formal user stories. Outputs INVEST-compliant stories with acceptance criteria.
 - **`/sdd`**: You have requirements and need a technical specification. Creates a structured spec document with API design, data models, and acceptance criteria.
 - **`/reverse`**: You need to understand existing code before modifying it. Generates specs, BDD scenarios, or TDD coverage maps from existing code.
+- **`/api-design`**: You need to design API endpoints following REST, GraphQL, or gRPC best practices. Guides you through DEFINE→DESIGN→VALIDATE→DOCUMENT.
+- **`/database`**: You need to design a database schema, plan a migration, or optimize queries. Guides through PLAN→WRITE→TEST→DEPLOY→VERIFY.
 
 ---
 
@@ -85,11 +89,15 @@ SDD 規格 → /derive → /bdd → /tdd → 測試就緒
 |---------|---------|-------------|----------|
 | `/refactor` | Refactoring guidance | Improving code structure | 改善程式碼結構 |
 | `/reverse` | Reverse engineer code | Understanding code before changes | 修改前理解程式碼 |
+| `/migrate` | Code migration guidance | Framework upgrades, tech modernization | 框架升級、技術現代化 |
+| `/durable` | Failure recovery patterns | Checkpoints, retries, rollback | 檢查點、重試、回滾 |
 
 ### When to Use Each | 各指令適用場景
 
 - **`/refactor`**: Code works but needs structural improvement. Guides you through extract method, rename, move, and other refactoring patterns with safety checks.
 - **`/reverse`**: You're working in unfamiliar code and need to understand data flow, runtime behavior, or module boundaries before making changes.
+- **`/migrate`**: You need to upgrade a framework (e.g., Vue 2→3), modernize dependencies, or move to a new tech stack. Guides through ASSESS→PLAN→PREPARE→MIGRATE→VERIFY→CLEANUP.
+- **`/durable`**: Your workflow has failure points that need resilience. Helps design checkpoint, retry, and rollback strategies for long-running operations.
 
 ---
 
@@ -103,6 +111,9 @@ SDD 規格 → /derive → /bdd → /tdd → 測試就緒
 |---------|---------|-------------|----------|
 | `/checkin` | Pre-commit verification | Before every commit | 每次提交前 |
 | `/review` | Systematic code review | Before merging PRs | 合併 PR 前 |
+| `/security` | Security review (OWASP) | Auditing for vulnerabilities | 審計漏洞 |
+| `/scan` | Automated security scanning | Dependency audit, secret detection | 相依掃描、機密偵測 |
+| `/incident` | Incident response | Production issues, post-mortems | 生產事故、事後檢討 |
 
 ### Checkin Verification | 提交前驗證
 
@@ -140,6 +151,8 @@ SDD 規格 → /derive → /bdd → /tdd → 測試就緒
 | `/commit` | Conventional Commits format | Creating each commit | 建立每次提交 |
 | `/changelog` | Generate changelog entries | Before releases | 發布前 |
 | `/release` | Release process management | Publishing versions | 發布版本 |
+| `/pr` | Pull request automation | Creating and reviewing PRs | 建立與審查 PR |
+| `/ci-cd` | CI/CD pipeline guidance | Designing/optimizing pipelines | 設計/優化管線 |
 
 ### Commit Message Format | 提交訊息格式
 
@@ -190,6 +203,8 @@ Types: `feat`, `fix`, `docs`, `chore`, `test`, `refactor`, `style`
 | Command | Purpose | When to Use | 使用時機 |
 |---------|---------|-------------|----------|
 | `/discover` | Project health assessment | Before major changes | 重大變更前 |
+| `/metrics` | Development metrics tracking | Monitoring project health | 監控專案健康 |
+| `/audit` | UDS health check | Checking standards adoption | 檢查標準採用 |
 | `/guide` | Access all UDS guides | Looking up standards | 查找標準 |
 | `/guide testing` | Testing standards | Setting up tests | 設定測試 |
 | `/guide error-codes` | Error code standards | Designing error codes | 設計錯誤碼 |
@@ -237,13 +252,22 @@ Start here | 從這裡開始
 │
 ├─ "I have a vague idea"          → /brainstorm
 ├─ "I know what to build"         → /requirement → /sdd
+├─ "I need to design an API"      → /api-design
+├─ "I need to design a database"  → /database
 ├─ "I have a spec, need tests"    → /derive
 ├─ "I'm writing tests"            → /tdd or /bdd
 ├─ "I'm writing code"             → (just code, or /refactor)
+├─ "I need to migrate/upgrade"    → /migrate
 ├─ "I'm done coding"              → /checkin → /commit
 ├─ "I need to review code"        → /review
+├─ "I need a security check"      → /scan → /security
+├─ "There's a production issue"   → /incident
+├─ "I need to create a PR"        → /pr
 ├─ "I'm preparing a release"      → /changelog → /release
+├─ "I need to set up CI/CD"       → /ci-cd
 ├─ "I need to understand code"    → /reverse or /discover
+├─ "I want project metrics"       → /metrics
 ├─ "I need a reference guide"     → /guide [topic]
+├─ "I need to audit standards"    → /audit
 └─ "I need a complex workflow"    → /methodology
 ```

package/bundled/skills/durable-execution-assistant/SKILL.md

@@ -0,0 +1,116 @@
+---
+name: durable
+scope: partial
+description: "[UDS] Guide workflow failure recovery with checkpoints, retries, and rollback"
+allowed-tools: Read, Write, Grep, Glob
+argument-hint: "[workflow name or failure context | 工作流名稱或失敗情境]"
+---
+
+# Durable Execution Assistant | 持久執行助手
+
+Guide fault-tolerant workflow design with automatic recovery, checkpoints, and retry strategies.
+
+引導容錯工作流程設計，包含自動恢復、檢查點與重試策略。
+
+## Usage | 使用方式
+
+| Command | Purpose | 用途 |
+|---------|---------|------|
+| `/durable` | Start interactive failure recovery guide | 啟動互動式故障恢復引導 |
+| `/durable --checkpoint` | Design checkpoint strategy | 設計檢查點策略 |
+| `/durable --retry` | Configure retry policies | 配置重試策略 |
+| `/durable --rollback` | Plan rollback procedures | 規劃回滾程序 |
+| `/durable <workflow>` | Analyze specific workflow for durability | 分析特定工作流的持久性 |
+
+## Core Concepts | 核心概念
+
+| Concept | Definition | 定義 |
+|---------|-----------|------|
+| **Checkpoint** | Save execution state at known-good points | 在已知正確的位置儲存執行狀態 |
+| **Retry** | Automatically re-attempt failed operations | 自動重新嘗試失敗的操作 |
+| **Rollback** | Revert to last known-good state on failure | 失敗時回復到上一個已知正確狀態 |
+| **Idempotency** | Operations produce same result on re-execution | 操作重新執行時產生相同結果 |
+| **Circuit Breaker** | Stop retries when failure rate exceeds threshold | 失敗率超過閾值時停止重試 |
+
+## Failure Recovery Decision Tree | 故障恢復決策樹
+
+```
+Failure detected
+├── Is it transient? (network, timeout)
+│   ├── Yes → Retry with backoff
+│   └── No → Is state corrupted?
+│       ├── Yes → Rollback to checkpoint
+│       └── No → Is it a logic error?
+│           ├── Yes → Stop, report, fix code
+│           └── No → Escalate with diagnostics
+```
+
+## Retry Strategy Guide | 重試策略指南
+
+| Strategy | When to Use | Config | 使用時機 |
+|----------|-------------|--------|---------|
+| **Immediate** | Rare glitches, fast ops | max 2 retries | 罕見故障、快速操作 |
+| **Exponential Backoff** | Network/API calls | base 1s, max 30s | 網路/API 呼叫 |
+| **Circuit Breaker** | Downstream service issues | threshold 50%, window 60s | 下游服務問題 |
+| **Dead Letter** | Unrecoverable after retries | max 5 retries then queue | 重試後仍不可恢復 |
+
+## Checkpoint Granularity | 檢查點粒度
+
+| Granularity | Use Case | 使用場景 |
+|-------------|----------|---------|
+| **Per-step** | Long pipelines (> 5 steps) | 長管線（> 5 步驟） |
+| **Per-batch** | Bulk data processing | 批量資料處理 |
+| **Per-phase** | Multi-phase workflows | 多階段工作流程 |
+| **Start/End** | Short, atomic operations | 短暫的原子操作 |
+
+## Workflow | 工作流程
+
+1. **DETECT** - Identify failure type and scope
+2. **DIAGNOSE** - Determine root cause category
+3. **RECOVER** - Apply appropriate recovery strategy
+4. **VERIFY** - Confirm system state is consistent
+5. **RESUME** - Continue from last checkpoint
+
+---
+
+1. **偵測** - 識別故障類型與範圍
+2. **診斷** - 判定根本原因類別
+3. **恢復** - 套用適當的恢復策略
+4. **驗證** - 確認系統狀態一致
+5. **繼續** - 從上一個檢查點繼續
+
+## Usage Examples | 使用範例
+
+```
+User: /durable deploy-pipeline
+AI: Analyzing deploy-pipeline for durability...
+    Steps: build → test → deploy → verify
+    Risk: deploy step has no rollback strategy.
+    Recommendation: Add checkpoint after test,
+    configure rollback for deploy using blue-green strategy.
+```
+
+## Next Steps Guidance | 下一步引導
+
+After `/durable` completes, the AI assistant should suggest:
+
+> **持久性分析完成。建議下一步 / Durability analysis complete. Suggested next steps:**
+> - 執行 `/methodology` 選擇適合的開發方法論 — Choose suitable methodology
+> - 執行 `/commit` 提交持久化設計變更 — Commit durability design changes
+
+## Version History | 版本歷史
+
+| Version | Date | Changes | 變更 |
+|---------|------|---------|------|
+| 1.0.0 | 2026-03-24 | Initial release | 初始版本 |
+
+
+## AI Agent Behavior | AI 代理行為
+
+> 完整的 AI 行為定義請參閱對應的命令文件：[`/durable`](../commands/durable.md#ai-agent-behavior--ai-代理行為)
+>
+> For complete AI agent behavior definition, see the corresponding command file: [`/durable`](../commands/durable.md#ai-agent-behavior--ai-代理行為)
+
+## License | 授權
+
+CC BY 4.0

package/bundled/skills/forward-derivation/SKILL.md

@@ -69,3 +69,10 @@ After `/derive` completes, the AI assistant should suggest:
 
 - Detailed guide: [guide.md](./guide.md)
 - Core standard: [forward-derivation-standards.md](../../core/forward-derivation-standards.md)
+
+
+## AI Agent Behavior | AI 代理行為
+
+> 完整的 AI 行為定義請參閱對應的命令文件：[`/derive`](../commands/derive.md#ai-agent-behavior--ai-代理行為)
+>
+> For complete AI agent behavior definition, see the corresponding command file: [`/derive`](../commands/derive.md#ai-agent-behavior--ai-代理行為)

package/bundled/skills/incident-response-assistant/SKILL.md

@@ -0,0 +1,132 @@
+---
+name: incident
+scope: universal
+description: |
+  Guide incident response, root cause analysis, and post-mortem documentation.
+  Use when: production incident, outage response, post-mortem writing, RCA.
+  Keywords: incident, outage, post-mortem, RCA, root cause, 事故, 故障, 根因分析.
+allowed-tools: Read, Write, Grep, Glob
+argument-hint: "[incident description or severity | 事故描述或嚴重程度]"
+---
+
+# Incident Response Assistant | 事故回應助手
+
+> **Language**: English | [繁體中文](../../locales/zh-TW/skills/incident-response-assistant/SKILL.md)
+
+Guide structured incident response from detection through post-mortem.
+
+引導結構化的事故回應流程，從偵測到事後檢討。
+
+## Severity Classification | 嚴重程度分類
+
+| Level | Name | Criteria | 標準 | Response Time |
+|-------|------|----------|------|---------------|
+| **SEV-1** | Critical 重大 | Full service outage, data loss | 全面服務中斷、資料遺失 | Immediate (< 15 min) |
+| **SEV-2** | High 高 | Major feature degraded, partial outage | 主要功能降級、部分中斷 | < 30 min |
+| **SEV-3** | Medium 中 | Minor feature affected, workaround exists | 次要功能受影響、有替代方案 | < 4 hours |
+| **SEV-4** | Low 低 | Cosmetic issue, minimal user impact | 外觀問題、最小用戶影響 | Next business day |
+
+## Response Workflow | 回應工作流程
+
+```
+DETECT ──► TRIAGE ──► MITIGATE ──► RESOLVE ──► POST-MORTEM
+偵測         分級        緩解          解決         事後檢討
+```
+
+### 1. Detect — Identify the Incident | 偵測事故
+- Monitor alerts, user reports, error spikes
+- 監控告警、使用者回報、錯誤量飆升
+
+### 2. Triage — Classify Severity | 分級嚴重程度
+- Assign SEV level, identify Incident Commander (IC)
+- 指定嚴重等級、識別事故指揮官（IC）
+
+### 3. Mitigate — Reduce Impact | 緩解影響
+- Apply temporary fix: rollback, feature flag, traffic shift
+- 套用暫時修復：回滾、功能開關、流量切換
+
+### 4. Resolve — Permanent Fix | 永久修復
+- Root cause analysis, implement proper fix, deploy
+- 根因分析、實作正確修復、部署
+
+### 5. Post-Mortem — Learn & Improve | 事後檢討
+- Document timeline, impact, root cause, action items
+- 記錄時間軸、影響範圍、根因、行動項目
+
+## Post-Mortem Template | 事後檢討模板
+
+```markdown
+## Post-Mortem: [Incident Title]
+**Date**: YYYY-MM-DD  |  **Severity**: SEV-N  |  **Duration**: Xh Ym
+
+### Timeline
+| Time | Event |
+|------|-------|
+| HH:MM | Alert triggered / 告警觸發 |
+| HH:MM | IC assigned / 指派事故指揮官 |
+| HH:MM | Mitigation applied / 套用緩解措施 |
+| HH:MM | Resolved / 解決 |
+
+### Impact
+- Users affected / 受影響用戶數: N
+- Revenue impact / 營收影響: $N
+- SLA breach / SLA 違反: Yes/No
+
+### Root Cause
+[Description of the underlying cause / 根本原因描述]
+
+### Action Items
+| Action | Owner | Due Date | Priority |
+|--------|-------|----------|----------|
+| [Fix] | @name | YYYY-MM-DD | P0 |
+```
+
+## Communication Template | 溝通模板
+
+```
+[SEV-N] [Service Name] — [Brief Description]
+Status: Investigating / Mitigating / Resolved
+Impact: [Who is affected and how]
+Next update: [Time]
+```
+
+## Usage | 使用方式
+
+```bash
+/incident                       # Show full incident response guide | 顯示完整事故回應指南
+/incident "API 500 errors"      # Guided response for specific incident | 特定事故引導回應
+/incident --post-mortem         # Generate post-mortem template | 產生事後檢討模板
+/incident --sev1                # SEV-1 rapid response checklist | SEV-1 快速回應清單
+```
+
+## Next Steps Guidance | 下一步引導
+
+After `/incident` completes, the AI assistant should suggest:
+
+> **事故回應指引已提供。建議下一步 / Incident response guidance provided. Suggested next steps:**
+> - 提交修復 → 執行 `/commit` 建立修復提交 — Create fix commit
+> - 程式碼審查 → 執行 `/review` 審查修復變更 — Review fix changes
+> - 記錄學習 → 執行 `/docs` 更新文件 — Document learnings
+> - 安全審查 → 執行 `/security` 檢查安全影響 — Check security impact
+
+## Reference | 參考
+
+- Core standard: [deployment-standards.md](../../core/deployment-standards.md)
+- Core standard: [logging.md](../../core/logging.md)
+
+## Version History | 版本歷史
+
+| Version | Date | Changes | 變更說明 |
+|---------|------|---------|----------|
+| 1.0.0 | 2026-03-24 | Initial release | 初始版本 |
+
+
+## AI Agent Behavior | AI 代理行為
+
+> 完整的 AI 行為定義請參閱對應的命令文件：[`/incident`](../commands/incident.md#ai-agent-behavior--ai-代理行為)
+>
+> For complete AI agent behavior definition, see the corresponding command file: [`/incident`](../commands/incident.md#ai-agent-behavior--ai-代理行為)
+
+## License | 授權
+
+CC BY 4.0 — Documentation content

package/bundled/skills/methodology-system/SKILL.md

@@ -14,9 +14,24 @@ argument-hint: "[action] [argument]"
 > This feature is under active development and may change significantly in v4.0.
 > 此功能正在積極開發中，可能在 v4.0 中有重大變更。
 
-Manage the active development methodology for the current project with two independent systems.
+Select and manage the active development methodology for the current project. This skill focuses on **choosing which methodology to use** (SDD, BDD, TDD) and tracking phase progress within the chosen methodology.
 
-管理當前專案的開發方法論，支援兩個獨立系統。
+選擇並管理當前專案的開發方法論。此技能專注於**選擇使用哪種方法論**（SDD、BDD、TDD）並追蹤所選方法論內的階段進度。
+
+> **Related**: For navigating development phases and finding the right UDS command at each stage, use `/dev-workflow` instead.
+>
+> **相關**：如需查詢開發階段對應的 UDS 指令，請改用 `/dev-workflow`。
+
+### When to Use `/methodology` vs `/dev-workflow` | 何時使用
+
+| Scenario | `/methodology` | `/dev-workflow` |
+|----------|---------------|-----------------|
+| Choose SDD vs BDD vs TDD | ✅ | ❌ |
+| Switch between methodologies | ✅ | ❌ |
+| Track current phase progress | ✅ | ❌ |
+| Find the right UDS command for a task | ❌ | ✅ |
+| Get step-by-step workflow for new feature / bug fix | ❌ | ✅ |
+| Navigate 8 development phases | ❌ | ✅ |
 
 **Two Independent Systems / 兩個獨立系統：**
 - **System A: SDD** - Spec-Driven Development (AI-era, spec-first)
@@ -83,3 +98,10 @@ After `/methodology` completes, the AI assistant should suggest based on the sel
 ## Reference | 參考
 
 - Detailed guide: [guide.md](./guide.md)
+
+
+## AI Agent Behavior | AI 代理行為
+
+> 完整的 AI 行為定義請參閱對應的命令文件：[`/methodology`](../commands/methodology.md#ai-agent-behavior--ai-代理行為)
+>
+> For complete AI agent behavior definition, see the corresponding command file: [`/methodology`](../commands/methodology.md#ai-agent-behavior--ai-代理行為)

package/bundled/skills/metrics-dashboard-assistant/SKILL.md

@@ -0,0 +1,109 @@
+---
+name: metrics
+scope: universal
+description: "[UDS] Track development metrics, code quality indicators, and project health"
+allowed-tools: Read, Grep, Glob, Bash(npm:*, git:log)
+argument-hint: "[metric type or module | 指標類型或模組]"
+---
+
+# Metrics Dashboard Assistant | 開發指標助手
+
+Track development metrics, code quality indicators, and project health over time.
+
+追蹤開發指標、程式碼品質指示器，以及專案隨時間的健康狀態。
+
+## Usage | 使用方式
+
+| Command | Purpose | 用途 |
+|---------|---------|------|
+| `/metrics` | Run full project health check | 執行完整專案健康檢查 |
+| `/metrics --quality` | Code quality metrics only | 僅程式碼品質指標 |
+| `/metrics --debt` | Technical debt summary | 技術債摘要 |
+| `/metrics --test` | Test health metrics | 測試健康指標 |
+| `/metrics src/` | Scope to specific module | 限定特定模組範圍 |
+
+## Metric Categories | 指標類別
+
+| Category | Metrics | 指標說明 |
+|----------|---------|----------|
+| **Code Quality** | Complexity, duplication, lint warnings | 複雜度、重複率、lint 警告 |
+| **Test Health** | Coverage %, pass rate, flaky count | 覆蓋率 %、通過率、不穩定測試數 |
+| **Commit Quality** | Size, frequency, conventional format | 大小、頻率、格式合規 |
+| **Debt Tracking** | TODO/FIXME counts, age of issues | TODO/FIXME 數量、問題存在時間 |
+| **Dependency Health** | Outdated packages, vulnerability count | 過時套件、漏洞數量 |
+
+## Quick Health Score | 快速健康分數
+
+The health score is a weighted composite:
+
+健康分數為加權組合：
+
+| Factor | Weight | Ideal | 理想值 |
+|--------|--------|-------|--------|
+| Test coverage | 30% | >= 80% | >= 80% |
+| Lint pass rate | 20% | 100% | 100% |
+| TODO/FIXME density | 15% | < 1 per 1K lines | < 每千行 1 個 |
+| Build success | 20% | 100% | 100% |
+| Dependency freshness | 15% | < 3 months | < 3 個月 |
+
+**Score = sum(factor_score * weight)**
+
+## Workflow | 工作流程
+
+1. **COLLECT** - Gather raw metrics from tools and git history
+2. **ANALYZE** - Compare against thresholds and historical trends
+3. **REPORT** - Generate summary with actionable highlights
+4. **TREND** - Show direction (improving / declining / stable)
+
+---
+
+1. **收集** - 從工具與 git 歷史收集原始指標
+2. **分析** - 與閾值及歷史趨勢比較
+3. **報告** - 產生含可行動重點的摘要
+4. **趨勢** - 顯示方向（改善 / 衰退 / 穩定）
+
+## Usage Examples | 使用範例
+
+```
+User: /metrics
+AI: Analyzing project health...
+    Code Quality:  B+ (complexity avg 8.2, 0 lint errors)
+    Test Health:   A  (coverage 87%, 0 flaky tests)
+    Debt Tracking: C  (42 TODOs, 3 FIXMEs)
+    Overall Score: 78/100 (Good)
+```
+
+```
+User: /metrics --debt
+AI: Technical Debt Summary:
+    TODO:  42 (12 in src/legacy/, 8 in src/utils/)
+    FIXME: 3  (all in src/parser/)
+    Oldest: 6 months (src/legacy/auth.js:45)
+    Trend:  +5 since last month (increasing)
+```
+
+## Next Steps Guidance | 下一步引導
+
+After `/metrics` completes, the AI assistant should suggest:
+
+> **指標分析完成。建議下一步 / Metrics analysis complete. Suggested next steps:**
+> - 執行 `/refactor` 處理高複雜度模組 — Address high-complexity modules
+> - 執行 `/coverage` 改善低覆蓋率區域 — Improve low-coverage areas
+> - 執行 `/audit` 檢視安全與依賴問題 — Review security & dependency issues
+
+## Version History | 版本歷史
+
+| Version | Date | Changes | 變更 |
+|---------|------|---------|------|
+| 1.0.0 | 2026-03-24 | Initial release | 初始版本 |
+
+
+## AI Agent Behavior | AI 代理行為
+
+> 完整的 AI 行為定義請參閱對應的命令文件：[`/metrics`](../commands/metrics.md#ai-agent-behavior--ai-代理行為)
+>
+> For complete AI agent behavior definition, see the corresponding command file: [`/metrics`](../commands/metrics.md#ai-agent-behavior--ai-代理行為)
+
+## License | 授權
+
+CC BY 4.0