universal-dev-standards 5.17.0 → 6.0.0

package/bundled/skills/commands/COMMAND-INDEX.json

@@ -9,12 +9,12 @@
     "core": {
       "description": "Foundation commands every AI tool should know",
       "descriptionZh": "基礎命令，所有 AI 工具都應知道",
-      "commands": ["commit", "review", "sdd", "check", "init", "update", "config"]
+      "commands": ["commit", "code-review", "sdd", "check", "init", "update", "config"]
     },
     "testing": {
       "description": "Testing-related commands",
       "descriptionZh": "測試相關命令",
-      "commands": ["tdd", "bdd", "atdd", "e2e", "coverage", "ac-coverage", "derive", "derive-bdd", "derive-tdd", "derive-atdd", "derive-all"]
+      "commands": ["tdd", "bdd", "atdd", "e2e", "coverage", "ac-coverage", "derive", "derive-bdd", "derive-tdd", "derive-atdd", "derive-all", "journey-test"]
     },
     "quality": {
       "description": "Quality and refactoring commands",
@@ -34,7 +34,7 @@
     "methodology": {
       "description": "Methodology and workflow commands",
       "descriptionZh": "方法論與工作流程命令",
-      "commands": ["methodology", "dev-workflow", "discover", "release", "audit", "migrate"]
+      "commands": ["methodology", "dev-workflow", "discover", "release", "audit", "migrate", "skill-builder"]
     },
     "reference": {
       "description": "Reference guide commands (read-only)",

package/bundled/skills/commands/README.md

@@ -33,7 +33,7 @@ Commands for development workflow automation.
 |---------|-------------|------|
 | [`/brainstorm`](./brainstorm.md) | Structured AI-assisted brainstorming | AI 輔助腦力激盪 |
 | [`/commit`](./commit.md) | Generate conventional commit messages | 產生 commit message |
-| [`/review`](./review.md) | Perform systematic code review | 執行程式碼審查 |
+| [`/code-review`](./code-review.md) | Perform systematic code review | 執行程式碼審查 |
 | [`/release`](./release.md) | Guide through release process | 引導發布流程 |
 | [`/changelog`](./changelog.md) | Update CHANGELOG.md | 更新 CHANGELOG |
 | [`/requirement`](./requirement.md) | Write user stories and requirements | 撰寫需求文件 |
@@ -89,7 +89,7 @@ Commands for development methodology workflows.
 | `/check` | — | — | Standards Management |
 | `/config` | — | — | Standards Management |
 | `/commit` | commit-standards | `commit-message-guide.md` | Development Workflow |
-| `/review` | code-review | `code-review-checklist.md` | Development Workflow |
+| `/code-review` | code-review | `code-review-checklist.md` | Development Workflow |
 | `/checkin` | — | `checkin-standards.md` | Development Workflow |
 | `/release` | release-standards | `versioning.md` | Development Workflow |
 | `/changelog` | — | `changelog-standards.md` | Development Workflow |

package/bundled/skills/commands/ac-coverage.md

@@ -129,7 +129,7 @@ After `/ac-coverage` completes, the AI assistant should suggest:
 
 ## References | 參考
 
-- [AC Coverage Assistant Skill](../ac-coverage-assistant/SKILL.md)
+- [AC Coverage Assistant Skill](../ac-coverage/SKILL.md)
 - [Core Standard: Acceptance Criteria Traceability](../../core/acceptance-criteria-traceability.md)
 - Related: [/coverage](./coverage.md) (code-level coverage)
 - Related: [/checkin](./checkin.md) (quality gates)

package/bundled/skills/commands/atdd.md

@@ -31,7 +31,7 @@ When `/atdd` is invoked:
 3. **追蹤階段轉換**隨著工作進展
 4. **在回應中顯示階段指示器**（🤝 工作坊、🧪 提煉、💻 開發、🎬 展示、✅ 完成）
 
-See [methodology-system](../methodology-system/SKILL.md) for full methodology tracking.
+See [methodology-system](../dev-methodology/SKILL.md) for full methodology tracking.
 
 ## ATDD Cycle | ATDD 循環
 
@@ -229,4 +229,4 @@ ATDD Level (Business Acceptance)
 - Core Standard: [acceptance-test-driven-development.md](../../core/acceptance-test-driven-development.md)
 - Skill: [atdd-assistant](../atdd-assistant/SKILL.md)
 - Methodology: [atdd.methodology.yaml](../../methodologies/atdd.methodology.yaml)
-- Methodology System: [methodology-system](../methodology-system/SKILL.md)
+- Methodology System: [methodology-system](../dev-methodology/SKILL.md)

package/bundled/skills/commands/bdd.md

@@ -68,7 +68,7 @@ When `/bdd` is invoked:
 3. **追蹤階段轉換**隨著工作進展
 4. **在回應中顯示階段指示器**（🔍 探索、📝 制定、🤖 自動化、📚 活文件）
 
-See [methodology-system](../methodology-system/SKILL.md) for full methodology tracking.
+See [methodology-system](../dev-methodology/SKILL.md) for full methodology tracking.
 
 ## BDD Cycle | BDD 循環
 
@@ -240,4 +240,4 @@ BDD works best with collaboration:
 ## Reference | 參考
 
 - Methodology: [bdd.methodology.yaml](../../methodologies/bdd.methodology.yaml)
-- Methodology System: [methodology-system](../methodology-system/SKILL.md)
+- Methodology System: [methodology-system](../dev-methodology/SKILL.md)

package/bundled/skills/commands/brainstorm.md

@@ -23,13 +23,17 @@ PRE-FLIGHT ──► FRAME ──► DIVERGE ──────────► C
   防錨定        定義問題    persona 集成+透鏡     多評審面板+硬角色反駁   輸出提案
 ```
 
-| Phase | Goal | Key Techniques (v3) | 目標 |
-|-------|------|---------------------|------|
-| **PRE-FLIGHT** | Prevent AI anchoring | User writes 3 ideas first; no analogy seed | 防止錨定 |
-| **FRAME** | Define problem clearly | 5 Whys, HMW, Stakeholder Map | 清楚定義問題 |
-| **DIVERGE** | Force viewpoint diversity | Persona ensemble + diversity lenses | 逼出視角多樣性 |
-| **CONVERGE** | Bias-checked selection | Multi-critic panel + Devil's Advocate/Steelman | 降偏誤選擇 |
-| **OUTPUT** | Actionable report | Brainstorm Report template | 可執行的報告 |
+| Phase | Goal | Key Techniques (v3) + BQS gate (v4) | 目標 |
+|-------|------|--------------------------------------|------|
+| **PRE-FLIGHT** | Prevent AI anchoring | User writes 3 ideas first; no analogy seed; **BQS Layer 0 intent (explore/exploit)** | 防止錨定 |
+| **FRAME** | Define problem clearly | 5 Whys, HMW, Stakeholder Map; **D1 frame purity** | 清楚定義問題 |
+| **DIVERGE** | Force viewpoint diversity | Persona ensemble + diversity lenses; **BQS Layer 1 D1–D4, hard gate hides D5–D8** | 逼出視角多樣性 |
+| **CONVERGE** | Bias-checked selection | Multi-critic panel + Devil's Advocate/Steelman; **BQS Layer 2 D5–D8 on Top 3, D4 judge≠generator** | 降偏誤選擇 |
+| **OUTPUT** | Actionable report | Brainstorm Report + Seeds + Contested Zone + **Layer 3 Judgment Override** | 可執行的報告 |
+
+> **BQS v1 (XSPEC-296):** v4 layers a four-layer × timeline quality contract on v3. Full oracles and structural rules are in the skill — see [Brainstorm Assistant Skill](../brainstorm-assistant/SKILL.md#bqs-v1--quality-contract--bqs-v1--品質契約).
+>
+> **BQS v1（XSPEC-296）：** v4 在 v3 上疊加四層 × 時間軸品質契約。完整 oracle 與結構規則見 skill：[Brainstorm Assistant Skill](../brainstorm-assistant/SKILL.md#bqs-v1--quality-contract--bqs-v1--品質契約)。
 
 ## Techniques | 技法
 
@@ -92,34 +96,39 @@ After brainstorming, the typical workflow is:
 | `/brainstorm "topic"` | 以指定主題啟動 PRE-FLIGHT，再進入 FRAME |
 | `/brainstorm --personas "a,b,c"` | 以自訂 persona 組進入 DIVERGE |
 | `/brainstorm --lens <name>` | 以指定多樣性透鏡為主進入 DIVERGE |
-| `/brainstorm --enhanced` | 若宿主支援子代理則平行跑 persona/評審，否則靜默退回 baseline |
+| `/brainstorm --enhanced` | 若宿主支援子代理則平行跑 persona/評審，否則靜默退回 baseline；此模式下 BQS D4 方可 pass |
+| `/brainstorm --intent exploit` | 以 exploit 意圖啟動（BQS Layer 0），D2 低覆蓋不扣分 |
 
 ### Interaction Script | 互動腳本
 
 #### PRE-FLIGHT Phase
 1. 請使用者先寫 問題（一句）＋3 個初始想法＋最不想要的解法類型
 2. 拒絕「像 X 但給 Y」種子，改寫為底層問題
+3. **BQS Layer 0**：宣告本次 explore/exploit 配比與賭注類型（未宣告預設偏 explore）
 
 🛑 **STOP**: 收到三項輸入前不生成任何想法（`--skip-preflight` 例外，顯示錨定警告）
 
 #### FRAME Phase
 1. 釐清問題陳述（5 Whys 找根因）
 2. 重構為 HMW 問題；識別利害關係人
+3. **BQS D1 框架純度**：問題不得內嵌特定方案或「像 X 給 Y」，須到根因
 
 🛑 **STOP**: 問題定義後等待使用者確認
 
-#### DIVERGE Phase
+#### DIVERGE Phase (BQS Layer 1 — D1–D4 leading, visible)
 1. 逐一以預設 persona（領域專家／懷疑者／跨域類比者／成本約束者／使用者代言）思維鏈生成想法
 2. **分支隔離**：生成各 persona 時不互相預覽，全部產完才一起呈現
 3. 至少套用一個多樣性透鏡（類比／假設反轉／形態矩陣）
-4. 以多樣性（覆蓋的 persona/透鏡數）而非數量為繼續門檻
+4. 以多樣性（覆蓋的 persona/透鏡數，D2/D3）而非數量為繼續門檻
+5. **硬序列閘**：D5–D8 在最後一個 persona 產完前**不得揭示或評分**；CONVERGE critic 不得提前呼叫
 
-#### CONVERGE Phase
+#### CONVERGE Phase (BQS Layer 2 — D5–D8 on Top 3 only)
 1. 以 3 個獨立評審（工程可行性／使用者影響／策略一致）各自評分後聚合
-2. 對前 3 名跑硬角色 Devil's Advocate（論證會失敗）+ Steelman；使用者以 (a)修改/(b)反駁/(c)移除 回應
-3. 排序並標記通過反駁的想法
+2. 對前 3 名跑硬角色 Devil's Advocate（論證會失敗）+ Steelman；使用者以 (a)修改/(b)反駁/(c)移除 回應。**D4 判官≠產生者**：評審須在獨立 context（`--enhanced`）方可 pass，否則標 `[degraded]` 不得 pass
+3. **僅對 Top 3** 套用 D5 接地（外部事實需 file:line／來源、跨級地板；假說免接地）、D6 淨值（解誰問題／真有嗎／不做代價＋掛 lagging 欄）、D7 二態證偽（「需先做 X」轉 next-step、不算 fail）、D8 next-step 裁決
+4. **Meta 停止規則**：維度全綠且再跑一輪 Top 3 集合成員不變→停；硬上限 2 輪
 
-🛑 **STOP**: 展示 Brainstorm Report 後等待使用者決定下一步
+🛑 **STOP**: 展示 Brainstorm Report（含 Seeds／爭議區／Judgment Override）後等待使用者決定下一步
 
 ### Stop Points | 停止點
 
@@ -139,6 +148,8 @@ After brainstorming, the typical workflow is:
 | 指定的 persona/透鏡不存在 | 列出可用選項供選擇 |
 | `--enhanced` 但宿主不支援子代理 | 靜默退回 baseline，照常進行 |
 | 前 3 名全來自同一 persona/透鏡 | 標示並在輸出前再跑一個透鏡 |
+| baseline 單 context 跑評審（無獨立 context） | BQS D4 標 `[degraded]`，不得標 pass |
+| 外部事實宣稱無 file:line／來源 | D5 接地 fail，要求補來源或改標 `[假說]` |
 
 ## References | 參考
 

package/bundled/skills/commands/{review.md → code-review.md}

@@ -40,9 +40,9 @@ Perform systematic code review using standardized checklists and comment prefixe
 
 ## Usage | 使用方式
 
-- `/review` - Review all changes in current branch
-- `/review src/auth.js` - Review specific file
-- `/review feature/login` - Review specific branch
+- `/code-review` - Review all changes in current branch
+- `/code-review src/auth.js` - Review specific file
+- `/code-review feature/login` - Review specific branch
 
 ## AI Agent Behavior | AI 代理行為
 
@@ -52,9 +52,9 @@ Perform systematic code review using standardized checklists and comment prefixe
 
 | Input | AI Action |
 |-------|-----------|
-| `/review` | 執行 `git diff` 取得當前分支所有變更，開始審查 |
-| `/review <file>` | 僅審查指定檔案 |
-| `/review <branch>` | 審查指定分支相對於 main 的差異 |
+| `/code-review` | 執行 `git diff` 取得當前分支所有變更，開始審查 |
+| `/code-review <file>` | 僅審查指定檔案 |
+| `/code-review <branch>` | 審查指定分支相對於 main 的差異 |
 
 ### Interaction Script | 互動腳本
 

package/bundled/skills/commands/derive-all.md

@@ -88,6 +88,6 @@ SPEC-XXX.md ──► /derive-bdd ──► /derive-tdd ──► [/derive-atdd]
 
 ## Reference | 參考
 
-- Parent command: [/derive](../forward-derivation/SKILL.md)
+- Parent command: [/derive](../spec-derivation/SKILL.md)
 - Core standard: [forward-derivation-standards.md](../../core/forward-derivation-standards.md)
 - Sub-commands: [/derive-bdd](./derive-bdd.md), [/derive-tdd](./derive-tdd.md), [/derive-atdd](./derive-atdd.md)

package/bundled/skills/commands/derive-atdd.md

@@ -78,5 +78,5 @@ SPEC-XXX.md ──► Parse AC ──► Generate acceptance.md ──► Review
 
 ## Reference | 參考
 
-- Parent command: [/derive](../forward-derivation/SKILL.md)
+- Parent command: [/derive](../spec-derivation/SKILL.md)
 - Core standard: [forward-derivation-standards.md](../../core/forward-derivation-standards.md)

package/bundled/skills/commands/derive-bdd.md

@@ -24,10 +24,9 @@ SPEC-XXX.md ──► Parse AC ──► Generate .feature ──► Review
 ## Output Format | 輸出格式
 
 ```gherkin
-@SPEC-001
 Feature: [Feature Name]
 
-  @AC-1
+  @SPEC-001 @AC-1
   Scenario: [AC-1 description]
     Given [context]
     When [action]
@@ -82,5 +81,5 @@ Feature: [Feature Name]
 
 ## Reference | 參考
 
-- Parent command: [/derive](../forward-derivation/SKILL.md)
+- Parent command: [/derive](../spec-derivation/SKILL.md)
 - Core standard: [forward-derivation-standards.md](../../core/forward-derivation-standards.md)

package/bundled/skills/commands/derive-tdd.md

@@ -84,5 +84,5 @@ describe('SPEC-001: [Feature Name]', () => {
 
 ## Reference | 參考
 
-- Parent command: [/derive](../forward-derivation/SKILL.md)
+- Parent command: [/derive](../spec-derivation/SKILL.md)
 - Core standard: [forward-derivation-standards.md](../../core/forward-derivation-standards.md)

package/bundled/skills/commands/derive.md

@@ -123,5 +123,5 @@ Generate derived artifacts (BDD scenarios, TDD skeletons, ATDD tables) from appr
 
 ## References | 參考
 
-*   [Forward Derivation Standard](../forward-derivation/SKILL.md)
+*   [Forward Derivation Standard](../spec-derivation/SKILL.md)
 *   [Core Standard](../../core/forward-derivation-standards.md)

package/bundled/skills/commands/dev-workflow.md

@@ -82,7 +82,7 @@ If active specs exist, highlight them and suggest the appropriate workflow phase
 | **I. Planning** | `/brainstorm` `/requirement` `/sdd` `/reverse` `/api-design` `/database` | 需求、規格、API/DB 設計 |
 | **II. Testing** | `/bdd` `/atdd` `/tdd` `/coverage` `/derive` `/ac-coverage` | 先寫測試再寫程式 |
 | **III. Implementation** | `/refactor` `/reverse` `/migrate` `/durable` | 撰寫、改善與遷移程式碼 |
-| **IV. Quality** | `/checkin` `/review` `/security` `/scan` `/incident` | 品質、安全、事故回應 |
+| **IV. Quality** | `/checkin` `/code-review` `/security` `/scan` `/incident` | 品質、安全、事故回應 |
 | **V. Release** | `/commit` `/changelog` `/release` `/pr` `/ci-cd` | 版本、提交、PR、CI/CD |
 | **VI. Docs** | `/docs` `/docgen` | 文件與專案結構 |
 | **VII. Standards** | `/discover` `/guide` `/metrics` `/audit` | 參考指南、指標、審計 |

package/bundled/skills/commands/journey-test.md

@@ -0,0 +1,45 @@
+---
+name: journey-test
+description: [UDS] Generate coherent user journey test plans (TESTPLAN) and E2E skeletons from a project description.
+allowed-tools: Read, Write, Grep, Glob
+argument-hint: "[project description | --analyze | --archetype A1|A2|A3]"
+status: stable
+---
+
+# /journey-test Command
+
+The `/journey-test` command turns a project description into a coherent user
+journey test plan (`TESTPLAN-NNN.md`) plus matching E2E skeletons, so a new
+project has a complete, ordered test journey from day one.
+
+It is backed by the `journey-test-assistant` skill
+(`skills/journey-test-assistant/SKILL.md`).
+
+## Usage
+
+```bash
+/journey-test [project description]
+/journey-test --analyze
+/journey-test --archetype A1|A2|A3
+```
+
+## What It Produces
+
+| Output | Description |
+|--------|-------------|
+| `TESTPLAN-NNN.md` | Ordered journey steps (T-000 reset → T-001 login → T-010 core flows) with personas, environment, and a dependency graph |
+| `*.journey.spec.ts` | E2E skeletons aligned to each TESTPLAN step |
+
+## Difference from `/e2e`
+
+- `/e2e` generates E2E skeletons from individual BDD scenarios.
+- `/journey-test` plans a **connected, cross-feature journey** (a sequence of
+  steps with ordering and dependencies) and then generates the skeletons.
+
+## Implementation Note for AI
+
+When the user invokes `/journey-test`:
+1. Read `skills/journey-test-assistant/SKILL.md` for the full workflow,
+   TESTPLAN format (T-NNN), personas, environment, and archetype rules.
+2. Follow that skill's workflow to produce the TESTPLAN and E2E skeletons.
+3. Respect the skill's `allowed-tools` and stop points.

package/bundled/skills/commands/methodology.md

@@ -185,7 +185,7 @@ Use '/methodology switch <id>' to change.
 /methodology create
 ```
 
-Starts the interactive methodology creation wizard. See [create-methodology.md](../methodology-system/create-methodology.md) for details.
+Starts the interactive methodology creation wizard. See [create-methodology.md](../dev-methodology/create-methodology.md) for details.
 
 ---
 
@@ -342,9 +342,9 @@ You can also configure methodology settings using:
 
 ## Reference | 參考
 
-- [Methodology System Skill](../methodology-system/SKILL.md) - Full skill documentation
-- [Runtime Guide](../methodology-system/runtime.md) - AI behavior specification
-- [Create Custom](../methodology-system/create-methodology.md) - Custom methodology guide
+- [Methodology System Skill](../dev-methodology/SKILL.md) - Full skill documentation
+- [Runtime Guide](../dev-methodology/runtime.md) - AI behavior specification
+- [Create Custom](../dev-methodology/create-methodology.md) - Custom methodology guide
 
 ---
 

package/bundled/skills/commands/pr.md

@@ -47,7 +47,7 @@ CREATE ──► REVIEW ──► APPROVE ──► MERGE ──► CLEANUP
 
 #### REVIEW
 1. 取得 PR 差異
-2. 執行程式碼審查（套用 `/review` 標準）
+2. 執行程式碼審查（套用 `/code-review` 標準）
 3. 展示審查結果
 
 🛑 **STOP**: 審查結果展示後等待使用者決定

package/bundled/skills/commands/skill-builder.md

@@ -0,0 +1,42 @@
+---
+name: skill-builder
+description: [UDS] Identify repeated processes and build Skills with the right development depth.
+allowed-tools: Read, Glob, Grep, Write, Edit, Bash
+argument-hint: "[process description | 流程描述]"
+---
+
+# /skill-builder Command
+
+The `/skill-builder` command guides you from "I keep doing this manually" to
+"I have a properly-built Skill", applying the right amount of process
+governance along the way.
+
+It is backed by the `skill-builder` skill (`skills/skill-builder/SKILL.md`).
+
+## Usage
+
+```bash
+/skill-builder [process description]
+```
+
+## When to Use
+
+- You have manually performed the same multi-step process 3+ times.
+- A teammate asks "how do we do X?" for the 3rd time.
+- You hacked together an ad-hoc skill and now want to formalize it.
+
+## Path Selection
+
+| Path | Trigger | Action |
+|------|---------|--------|
+| Simple | ≤7 steps, no branching, <3 standards, no source-code output | Fill a Skill Brief, create `SKILL.md` directly |
+| Complex | any of the above is exceeded | Create an XSPEC first (`/sdd`), then build |
+| Delta | modifying an existing Skill | Append `## MODIFIED` / `## ADDED`, bump version |
+
+## Implementation Note for AI
+
+When the user invokes `/skill-builder`:
+1. Read `skills/skill-builder/SKILL.md` for the full decision tree, placement
+   rules, workflow steps, and output checklist.
+2. Walk the user through path selection (Simple / Complex / Delta) and produce
+   the `SKILL.md` (plus `SKILL-CANDIDATES.md` update) per that skill.

package/bundled/skills/commands/tdd.md

@@ -64,7 +64,7 @@ When `/tdd` is invoked:
 3. **追蹤階段轉換**隨著工作進展
 4. **在回應中顯示階段指示器**（🔴 紅燈、🟢 綠燈、🔵 重構）
 
-See [methodology-system](../methodology-system/SKILL.md) for full methodology tracking.
+See [methodology-system](../dev-methodology/SKILL.md) for full methodology tracking.
 
 ## TDD Cycle | TDD 循環
 

package/bundled/skills/dev-methodology/create-methodology.md

@@ -1,6 +1,6 @@
 # Create Custom Methodology Guide
 
-> **Language**: English | [繁體中文](../../locales/zh-TW/skills/methodology-system/create-methodology.md)
+> **Language**: English | [繁體中文](../../locales/zh-TW/skills/dev-methodology/create-methodology.md) | [简体中文](../../locales/zh-CN/skills/dev-methodology/create-methodology.md)
 
 > [!WARNING]
 > **Experimental Feature / 實驗性功能**

package/bundled/skills/dev-methodology/guide.md

@@ -15,7 +15,7 @@ status: experimental
 
 # Methodology System Skill
 
-> **Language**: English | [繁體中文](../../locales/zh-TW/skills/methodology-system/SKILL.md)
+> **Language**: English | [繁體中文](../../locales/zh-TW/skills/dev-methodology/SKILL.md)
 
 **Version**: 2.0.0
 **Last Updated**: 2026-01-25

package/bundled/skills/dev-methodology/runtime.md

@@ -1,6 +1,6 @@
 # Methodology Runtime Guide
 
-> **Language**: English | [繁體中文](../../locales/zh-TW/skills/methodology-system/runtime.md)
+> **Language**: English | [繁體中文](../../locales/zh-TW/skills/dev-methodology/runtime.md) | [简体中文](../../locales/zh-CN/skills/dev-methodology/runtime.md)
 
 > [!WARNING]
 > **Experimental Feature / 實驗性功能**

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

@@ -35,7 +35,7 @@ V. Release ──► VI. Documentation ──► VII. Standards ──► VIII.
 | **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 |
+| **IV. Quality Gates** | `/checkin` `/code-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 |
@@ -198,8 +198,8 @@ After `/dev-workflow` completes, the AI assistant should suggest based on user's
 
 - [Detailed Phase Guide](./workflow-phases.md) - Complete phase-by-phase reference
 - [Daily Workflow Guide](../../adoption/DAILY-WORKFLOW-GUIDE.md) - Comprehensive daily workflow guide
-- [Feature Development Workflow](../workflows/feature-dev.yaml) - Automated feature dev workflow
-- [Integrated Flow Workflow](../workflows/integrated-flow.yaml) - Full ATDD/SDD/BDD/TDD workflow
+- [Feature Development Workflow](../workflows/feature-dev.workflow.yaml) - Automated feature dev workflow
+- [Integrated Flow Workflow](../workflows/integrated-flow.workflow.yaml) - Full ATDD/SDD/BDD/TDD workflow
 
 ---
 

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

@@ -110,7 +110,7 @@ SDD 規格 → /derive → /bdd → /tdd → 測試就緒
 | Command | Purpose | When to Use | 使用時機 |
 |---------|---------|-------------|----------|
 | `/checkin` | Pre-commit verification | Before every commit | 每次提交前 |
-| `/review` | Systematic code review | Before merging PRs | 合併 PR 前 |
+| `/code-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 |
@@ -126,7 +126,7 @@ SDD 規格 → /derive → /bdd → /tdd → 測試就緒
 
 ### Code Review | 程式碼審查
 
-`/review` evaluates 10 dimensions:
+`/code-review` evaluates 10 dimensions:
 1. Functionality
 2. Design & Architecture
 3. Code Quality
@@ -259,7 +259,7 @@ Start here | 從這裡開始
 ├─ "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 to review code"        → /code-review
 ├─ "I need a security check"      → /scan → /security
 ├─ "There's a production issue"   → /incident
 ├─ "I need to create a PR"        → /pr

package/bundled/skills/docs-generator/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: docgen
-scope: uds-specific
+scope: universal
 description: "[UDS] Generate usage documentation from project sources"
 allowed-tools: Read, Write, Grep, Glob, Bash(*)
 argument-hint: "[config file | 設定檔]"
@@ -82,7 +82,7 @@ Verify that generated documentation is up to date with source files.
 | Command    | Description               |
 |------------|---------------------------|
 | /commit    | Generate commit message    |
-| /review    | Run code review            |
+| /code-review    | Run code review            |
 | /sdd       | Create SDD specification   |
 | /discover  | Assess project health      |
 ```
@@ -94,7 +94,7 @@ After `/docgen` completes, the AI assistant should suggest:
 > **文件已產生。建議下一步 / Documentation generated. Suggested next steps:**
 > - 審查產生的文件內容是否完整 — Review generated content for completeness
 > - 執行 `/commit` 提交文件變更 ⭐ **Recommended / 推薦** — Commit documentation changes
-> - 執行 `/review` 審查文件品質 — Review documentation quality
+> - 執行 `/code-review` 審查文件品質 — Review documentation quality
 
 ## Reference | 參考
 

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

@@ -150,7 +150,7 @@ 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 ⭐ **Recommended / 推薦** — Create fix commit
-> - 程式碼審查 → 執行 `/review` 審查修復變更 — Review fix changes
+> - 程式碼審查 → 執行 `/code-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
 > - 團隊回顧 → 執行 `/retrospective`（SEV-1/SEV-2 建議）— Team retrospective (recommended for SEV-1/2)
@@ -159,7 +159,7 @@ After `/incident` completes, the AI assistant should suggest:
 ## Reference | 參考
 
 - Core standard: [deployment-standards.md](../../core/deployment-standards.md)
-- Core standard: [logging.md](../../core/logging.md)
+- Core standard: [logging.md](../../core/logging-standards.md)
 
 ## Version History | 版本歷史
 

package/bundled/skills/logging-guide/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: logging-guide
 scope: universal
+anchor_standard: logging-standards
 description: |
   Implement structured logging with proper log levels and sensitive data handling.
   Use when: adding logging, debugging, setting up observability.
@@ -11,8 +12,8 @@ description: |
 
 > **Language**: English | [繁體中文](../../locales/zh-TW/skills/logging-guide/SKILL.md)
 
-**Version**: 1.1.0
-**Last Updated**: 2026-05-26
+**Version**: 1.4.0
+**Last Updated**: 2026-06-19
 **Applicability**: Claude Code Skills
 
 ---
@@ -57,6 +58,40 @@ App cannot continue?         → FATAL
 | **ERROR** | Failed operations, caught exceptions, integration failures |
 | **FATAL** | Unrecoverable errors, startup failures, lost critical resources |
 
+## Mandatory Events
+
+Formatting every log perfectly but **never firing at the moment that matters** is
+worse than useless — it gives false confidence during an incident. The core
+standard defines **9 canonical events that MUST produce a log entry**. A logging
+setup that follows the level/field rules but omits these is "compliant on paper,
+materially silent". Always implement all 9:
+
+| Event id | When | Level | Core required fields | Must NOT log |
+|----------|------|-------|----------------------|--------------|
+| `application_startup` | After boot, **before** accepting requests | INFO | app_name, version, git_sha, environment, hostname, pid, listening_endpoints | secrets, full connection strings |
+| `request_received` | First time middleware sees a request | INFO / DEBUG | method, path, source_ip, request_id | request body, auth headers |
+| `validation_failure` | schema / ModelState / DTO validation rejects | WARN | request_id, path, missing_fields[], payload_shape (keys only) | field **values**, PII |
+| `authentication_failure` | login / token verification fails | WARN | uid (attempted), source_ip, failure_reason | password, token value |
+| `outbound_call_start` | An outbound HTTP/RPC call is initiated | INFO | target_url (host+path), request_id propagated, timeout_ms | credentials, bearer tokens |
+| `outbound_call_complete` | An external call returns or fails | INFO / WARN / ERROR | status_code **or** failure_phase (dns/tcp/tls/http), elapsed_ms, retries | response body with PII |
+| `business_event` | A state-changing business operation completes | INFO | operation_name, actor, target ids, outcome | full record payload, PII |
+| `heartbeat` | Long-running background service, ≥ 1× / 60 s | INFO | service_name, queue_depth, items_processed_since_last_heartbeat | — |
+| `shutdown` | Process exits (graceful or fatal) | INFO / ERROR | app_name, signal/reason, uptime_seconds, pending_work_count | — |
+
+**Why these exact events** — each closes a real incident blind spot: a silent
+`validation_failure` hides un-logged payloads; `authentication_failure` without
+`uid`/`source_ip` is un-investigable; a missing `heartbeat` means a 0-byte log
+file goes unnoticed; absent `outbound_call_*` turns "send failed" into a 2-day
+hunt with no trace of the call.
+
+> A background service that writes no INFO/WARN/ERROR within 60 s MUST emit a
+> `heartbeat`; if none appears for ≥ 2× the interval (≥ 120 s), a silence detector
+> MUST alert.
+
+For the full catalog (each event's `when` / `must_log` / `must_NOT_log` /
+`rationale` and compliant examples), see the **Mandatory Events** section of the
+[core Logging Standards](../../core/logging-standards.md#mandatory-events).
+
 ## Structured Logging
 
 ### Required Fields
@@ -305,6 +340,7 @@ After `/logging` completes, the AI assistant should suggest:
 
 | Version | Date | Changes |
 |---------|------|---------|
+| 1.4.0 | 2026-06-19 | Added: Mandatory Events section (9 canonical events) to close skill↔standard content drift; aligned version with core Logging Standards v1.4.0 (XSPEC-070 Phase 2) |
 | 1.1.0 | 2026-05-26 | Added: Log File Rotation section with cross-link to core standard rotation policy; Rotation checklist (XSPEC-232) |
 | 1.0.0 | 2025-12-30 | Initial release |