universal-dev-standards 5.14.0 → 5.16.0

package/bundled/skills/ci-cd-assistant/SKILL.md

@@ -4,7 +4,7 @@ scope: universal
 description: |
   Guide CI/CD pipeline design, configuration, and optimization.
   Use when: setting up pipelines, optimizing build times, configuring deployment stages.
-  Keywords: CI/CD, pipeline, GitHub Actions, deployment, build, 持續整合, 持續部署.
+  Keywords: CI/CD, pipeline, GitHub Actions, deployment, build.
 allowed-tools: Read, Grep, Glob
 argument-hint: "[pipeline config or stage | Pipeline 配置或階段]"
 ---

package/bundled/skills/commands/brainstorm.md

@@ -6,9 +6,9 @@ argument-hint: "[problem or feature idea | 問題或功能構想]"
 
 # Brainstorm Assistant | 腦力激盪助手
 
-Structured ideation before specification writing. Transform vague ideas into actionable feature proposals through guided brainstorming.
+Structured ideation before specification writing. Transform vague ideas into actionable feature proposals through a persona-ensemble brainstorm.
 
-在撰寫規格前進行結構化發想。透過引導式腦力激盪，將模糊構想轉化為可執行的功能提案。
+在撰寫規格前進行結構化發想。透過 persona 集成式腦力激盪，將模糊構想轉化為可執行的功能提案。
 
 ## Usage | 用法
 
@@ -19,33 +19,37 @@ Structured ideation before specification writing. Transform vague ideas into act
 ## Workflow | 工作流程
 
 ```
-FRAME ──► DIVERGE ──► CONVERGE ──► OUTPUT
-定義問題     發散思考       收斂評估       輸出提案
+PRE-FLIGHT ──► FRAME ──► DIVERGE ──────────► CONVERGE ─────────► OUTPUT
+  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 | 目標 |
-|-------|------|----------------|------|
+| 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** | Generate many ideas | HMW, SCAMPER, Six Thinking Hats | 產生大量想法 |
-| **CONVERGE** | Evaluate and rank | Evaluation Matrix, Dot Voting | 評估與排序 |
+| **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 |
 
 ## Techniques | 技法
 
 | Technique | Best For | 適用場景 |
 |-----------|----------|----------|
-| **5 Whys** | Finding root causes | 找到根本原因 |
-| **HMW** | Reframing problems as opportunities | 將問題重構為機會 |
-| **SCAMPER** | Improving existing features | 改善現有功能 |
-| **Six Thinking Hats** | Multi-perspective analysis | 多角度分析 |
-| **Dot Voting** | Quick prioritization | 快速排序 |
+| **Persona ensemble** | Forced viewpoint diversity (v3 core) | 強制視角多樣性（v3 核心） |
+| **Diversity lenses** | Analogical / reversal / morphological | 突破顯而易見區 |
+| **Multi-critic panel** | Bias-reduced scoring (v3 core) | 降偏誤評分（v3 核心） |
+| **Devil's Advocate + Steelman** | Hard-role rebuttal | 硬角色反駁 |
+| **5 Whys / HMW / SCAMPER / Six Hats** | Classic framing & divergence | 經典框定與發散 |
 
 ## Examples | 範例
 
 ```bash
-/brainstorm                           # Start interactive session
-/brainstorm "user retention"          # Brainstorm around a topic
-/brainstorm --technique scamper       # Use a specific technique
+/brainstorm                                          # Start interactive session
+/brainstorm "user retention"                         # Brainstorm around a topic
+/brainstorm --enhanced "user retention"              # Parallel persona ensemble (if host supports it)
+/brainstorm --personas "designer,economist,skeptic"  # Custom personas
+/brainstorm --lens analogical "onboarding"           # Force the analogical lens
+/brainstorm --quick "reduce checkout friction"       # Fast 3-idea mode
 ```
 
 ## Output Format | 輸出格式
@@ -57,9 +61,10 @@ FRAME ──► DIVERGE ──► CONVERGE ──► OUTPUT
 [Refined problem from FRAME phase]
 
 ## Top 3 Recommendations
-1. **[Idea]** — Score: X.X — [Why recommended]
-2. **[Idea]** — Score: X.X — [Why recommended]
-3. **[Idea]** — Score: X.X — [Why recommended]
+1. **[Idea]** — Agg. X.X ✓ Passed rebuttal — Persona: [..] — [Why recommended]
+
+## Diversity Note
+[How many distinct personas/lenses the surviving ideas span]
 
 ## Next Steps
 - [ ] Proceed to `/requirement` with top idea
@@ -83,26 +88,36 @@ After brainstorming, the typical workflow is:
 
 | Input | AI Action |
 |-------|-----------|
-| `/brainstorm` | 詢問要探討的主題或問題，進入 FRAME 階段 |
-| `/brainstorm "topic"` | 以指定主題開始，進入 FRAME 階段 |
-| `/brainstorm --technique <name>` | 使用指定技法開始 DIVERGE 階段 |
+| `/brainstorm` | 啟動 PRE-FLIGHT，請使用者先寫 問題＋3 想法＋反向排除 |
+| `/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 |
 
 ### 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
+
+🛑 **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（使用 5 Whys 或 HMW）
-2. 確認問題定義
+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
 
 🛑 **STOP**: 問題定義後等待使用者確認
 
 #### DIVERGE Phase
-1. 使用選定技法生成想法
-2. 鼓勵數量優先於品質
-3. 列出所有想法
+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
 
 #### CONVERGE Phase
-1. 以評估矩陣（可行性、影響力、成本）評分
-2. 排序前 3 名
+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
 
 🛑 **STOP**: 展示 Brainstorm Report 後等待使用者決定下一步
 
@@ -110,7 +125,9 @@ After brainstorming, the typical workflow is:
 
 | Stop Point | 等待內容 |
 |-----------|---------|
+| PRE-FLIGHT 提交前 | 收到使用者三項輸入 |
 | 問題定義後 | 確認問題正確 |
+| 反駁輪每個反對理由 | 使用者 (a)/(b)/(c) 回應 |
 | 報告展示後 | 決定進入 `/requirement` 或 `/sdd` |
 
 ### Error Handling | 錯誤處理
@@ -118,10 +135,14 @@ After brainstorming, the typical workflow is:
 | Error Condition | AI Action |
 |-----------------|-----------|
 | 主題太廣泛 | 引導縮小範圍 |
-| 指定的技法不存在 | 列出可用技法供選擇 |
+| 使用「像 X 但給 Y」種子 | 改寫為底層問題再繼續（反種子 guardrail） |
+| 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 |
 
 ## References | 參考
 
 * [Brainstorm Assistant Skill](../brainstorm-assistant/SKILL.md)
+* [Brainstorm Assistant Guide](../brainstorm-assistant/guide.md)
 * [Requirement Assistant](../requirement-assistant/SKILL.md)
 * [Spec-Driven Development](../spec-driven-dev/SKILL.md)

package/bundled/skills/contract-test-assistant/SKILL.md

@@ -4,7 +4,7 @@ scope: universal
 description: |
   [UDS] Guide contract testing strategy for APIs and microservices.
   Use when: API contracts, microservices, consumer-driven testing, provider verification.
-  Keywords: contract test, Pact, OpenAPI, consumer-driven, provider, 合約測試, API 合約.
+  Keywords: contract test, Pact, OpenAPI, consumer-driven, provider.
 allowed-tools: Read, Write, Glob, Grep
 argument-hint: "[verify | consumer | provider | 策略選擇]"
 ---

package/bundled/skills/database-assistant/SKILL.md

@@ -4,7 +4,7 @@ scope: universal
 description: |
   Guide database design, migration, and query optimization.
   Use when: schema design, migration planning, query optimization, index strategy.
-  Keywords: database, schema, migration, SQL, index, query, 資料庫, 遷移, 查詢.
+  Keywords: database, schema, migration, SQL, index, query.
 allowed-tools: Read, Grep, Glob
 argument-hint: "[schema or migration to review | 要審查的 schema 或遷移]"
 ---

package/bundled/skills/deploy-assistant/SKILL.md

@@ -4,7 +4,7 @@ scope: universal
 description: |
   Guide reliable deployments without CI/CD platforms (GitHub Actions / GitLab CI).
   Use when: deploying to VPS, air-gapped servers, or environments without CI/CD infrastructure.
-  Keywords: deployment, no-cicd, shell script, blue-green, smoke test, rollback, 無CI/CD, 部署.
+  Keywords: deployment, no-cicd, shell script, blue-green, smoke test, rollback.
 allowed-tools: Read, Bash(cat VERSION:*), Bash(git describe:*), Bash(which nginx:*), Bash(which rsync:*)
 argument-hint: "[project type | 專案類型: node/python/docker/go]"
 ---

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

@@ -4,7 +4,7 @@ scope: universal
 description: |
   Guide documentation structure, content requirements, and project documentation best practices.
   Use when: creating README, documentation, docs folder, project setup, technical docs.
-  Keywords: README, docs, documentation, CONTRIBUTING, CHANGELOG, ARCHITECTURE, API docs, 文件, 說明文件, 技術文件.
+  Keywords: README, docs, documentation, CONTRIBUTING, CHANGELOG, ARCHITECTURE, API docs.
 ---
 
 # Documentation Guide

package/bundled/skills/error-code-guide/SKILL.md

@@ -4,7 +4,7 @@ scope: universal
 description: |
   Design consistent error codes following the PREFIX_CATEGORY_NUMBER format.
   Use when: defining error codes, creating error handling, designing APIs.
-  Keywords: error code, error handling, error format, API errors, 錯誤碼, 錯誤處理.
+  Keywords: error code, error handling, error format, API errors.
 ---
 
 # Error Code Guide

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

@@ -4,7 +4,7 @@ scope: universal
 description: |
   Guide Git branching strategies, branch naming, and merge operations.
   Use when: creating branches, merging, pull requests, Git workflow questions.
-  Keywords: branch, merge, PR, pull request, GitFlow, GitHub Flow, 分支, 合併, 工作流程.
+  Keywords: branch, merge, PR, pull request, GitFlow, GitHub Flow.
 ---
 
 # Git Workflow Guide

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

@@ -4,7 +4,7 @@ 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.
+  Keywords: incident, outage, post-mortem, RCA, root cause.
 allowed-tools: Read, Write, Grep, Glob
 argument-hint: "[incident description or severity | 事故描述或嚴重程度]"
 ---

package/bundled/skills/journey-test-assistant/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: journey-test-assistant
 scope: partial
-description: "[UDS] 從專案描述生成連貫使用者旅程測試計畫（TESTPLAN）與 E2E 骨架"
+description: "[UDS] Generate coherent user journey test plans (TESTPLAN) and E2E skeletons from project description."
 allowed-tools: Read, Write, Grep, Glob
 argument-hint: "[project description | --analyze | --archetype A1|A2|A3]"
 status: stable

package/bundled/skills/knowledge-graph/SKILL.md

@@ -0,0 +1,58 @@
+---
+name: knowledge-graph
+scope: partial
+description: "[UDS] Trace spec/decision/code impact chains via a knowledge graph (engine or Markdown fallback)"
+allowed-tools: Read, Glob, Grep, Bash(curl:*)
+argument-hint: "[artifact id, e.g. XSPEC-205 | 產物 id]"
+---
+
+# Knowledge Graph | 知識圖
+
+> **Language**: English | [繁體中文](../../locales/zh-TW/skills/knowledge-graph/SKILL.md)
+
+Answer structural questions across specs, decisions, and code — *"what is the full impact chain of XSPEC-205?"* — using the [Knowledge Graph Memory](../../core/knowledge-graph-memory.md) relationship schema. Works with or without a graph engine.
+
+回答橫跨規格、決策與程式碼的結構性問題——*「XSPEC-205 的完整影響鏈是什麼？」*——依據[知識圖記憶標準](../../core/knowledge-graph-memory.md)的關係 schema。有無圖引擎皆可運作。
+
+> **Implements**: XSPEC-237 Phase 5 — knowledge-graph skill (EngramGraph opt-in)
+
+## Mode Selection | 模式選擇
+
+Detect which mode to use **before** answering:
+
+| Condition | Mode |
+|-----------|------|
+| `ENGRAM_URL` set, or a local graph engine responds on `/health` | Service mode (engine) |
+| Otherwise | Degraded mode (Markdown) |
+
+## Workflow | 工作流程
+
+1. **Resolve the target** — normalise the argument to a canonical id (`XSPEC-205`, `DEC-062`, a function name).
+2. **Choose mode** — probe for a graph engine (service) else fall back (degraded).
+3. **Service mode (AC-5b)** — issue a single multi-hop query and present the returned chain, including cross-domain links (code → spec → decision):
+   ```bash
+   curl -s -X POST "$ENGRAM_URL/graph/impact-analysis" \
+     -H 'content-type: application/json' \
+     -d '{"nodeId":"XSPEC-205","maxHops":3}'
+   ```
+4. **Degraded mode (AC-5a)** — with no engine, read the target document, follow its `impacts`/`impacted_by`/`supersedes`/`related` front-matter and inline `[[ref]]` links by reading the linked files, and assemble the chain manually (bounded by reading depth).
+5. **Present the chain** — list the connected Specs and Decisions, the edge type for each hop, and (if present) each node's `confidence`, highest first.
+6. **State the mode used** — always say whether the answer came from the engine or Markdown fallback, so completeness is clear.
+
+## Relationship Schema | 關係 schema
+
+See [knowledge-graph-memory](../../core/knowledge-graph-memory.md). Front-matter fields: `related`, `impacts`, `impacted_by`, `supersedes`, `implements`. Edge derivation: Decision `impacts` Spec → IMPACTS; Decision `supersedes` Decision → SUPERSEDES.
+
+關係欄位與邊推導見[知識圖記憶標準](../../core/knowledge-graph-memory.md)。
+
+## Next Steps Guidance | 下一步引導
+
+- If degraded mode hit a reading-depth limit, tell the user a graph engine (e.g. EngramGraph) would give a complete chain, and how to set `ENGRAM_URL`.
+- If a referenced id was not found, surface it as a dangling reference to fix.
+- Offer to add missing `impacts`/`impacted_by` front-matter to the documents you traversed.
+
+## Reference | 參考
+
+- Standard: [core/knowledge-graph-memory.md](../../core/knowledge-graph-memory.md)
+- Engine (opt-in): [EngramGraph](https://github.com/AsiaOstrich/EngramGraph) — `engramgraph`
+- Detailed guide: [guide.md](guide.md)

package/bundled/skills/knowledge-graph/guide.md

@@ -0,0 +1,69 @@
+# Knowledge Graph — Detailed Guide | 詳細指南
+
+Companion to [SKILL.md](SKILL.md). Worked examples of both operating modes and the engine API.
+
+[SKILL.md](SKILL.md) 的配套說明。兩種運作模式的範例與引擎 API。
+
+---
+
+## 1. Service Mode (graph engine) | 服務模式
+
+When an EngramGraph-compatible engine is reachable, a single query returns the full chain.
+
+### Impact analysis | 影響分析
+
+```bash
+curl -s -X POST "$ENGRAM_URL/graph/impact-analysis" \
+  -H 'content-type: application/json' \
+  -d '{"nodeId":"XSPEC-205","maxHops":3}'
+# => { "nodeId": "XSPEC-205",
+#      "decisions": [ {"id":"DEC-062","title":"...","via":"direct"},
+#                     {"id":"DEC-069","title":"...","via":"supersedes"} ] }
+```
+
+`via: "direct"` means the decision IMPACTS the spec directly; `via: "supersedes"` means it reaches the spec through a SUPERSEDES chain (≤ `maxHops`).
+
+### Confidence feedback (SAGE) | 信心回饋
+
+```bash
+curl -s -X POST "$ENGRAM_URL/graph/ingest" \
+  -H 'content-type: application/json' \
+  -d '{"type":"test_fail","functionId":"src/a.ts#execute"}'
+```
+
+Lowers the node's confidence; reads then surface higher-confidence nodes first.
+
+---
+
+## 2. Degraded Mode (Markdown only) | 降級模式
+
+No engine required. Reconstruct the chain by reading files:
+
+1. Read the target document (e.g. `XSPEC-205`).
+2. Collect ids from its front-matter (`impacts`, `impacted_by`, `supersedes`, `related`) and inline `[[ref]]` links.
+3. For each id, read that document and repeat up to the desired hop depth.
+4. Classify each id by prefix (`XSPEC-*`/`SPEC-*` → Spec; `DEC-*`/`ADR-*` → Decision) and report the edges.
+
+```bash
+# find the documents
+grep -rl "id: XSPEC-205" --include='*.md' .
+# discover outbound references
+grep -nE "(impacts|impacted_by|supersedes|related):|\[\[(XSPEC|DEC|ADR)-" path/to/XSPEC-205.md
+```
+
+Degraded mode is always correct but bounded by how many files you read; cross-domain code links (function → spec) are usually only available in service mode.
+
+---
+
+## 3. Equivalence | 等價性
+
+Both modes produce the **same answer shape** (a list of connected Specs/Decisions with edge types). Service mode is faster and more complete (it can include code→spec→decision hops); degraded mode is the universal fallback. Always tell the user which mode produced the answer.
+
+兩種模式產生**相同形狀的答案**。服務模式更快更完整；降級模式為通用後備。務必告知使用者答案來自哪種模式。
+
+---
+
+## Reference | 參考
+
+- [core/knowledge-graph-memory.md](../../core/knowledge-graph-memory.md)
+- [EngramGraph](https://github.com/AsiaOstrich/EngramGraph)

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

@@ -4,7 +4,7 @@ scope: universal
 description: |
   Implement structured logging with proper log levels and sensitive data handling.
   Use when: adding logging, debugging, setting up observability.
-  Keywords: logging, log level, structured logging, observability, 日誌, 記錄, 結構化日誌.
+  Keywords: logging, log level, structured logging, observability.
 ---
 
 # Logging Guide

package/bundled/skills/observability-assistant/SKILL.md

@@ -4,7 +4,7 @@ scope: universal
 description: |
   Guide observability setup, metrics design, and alerting configuration.
   Use when: new service instrumentation, SLO definition, alert design, maturity assessment.
-  Keywords: observability, metrics, traces, golden signals, alerting, SLO, 可觀測性, 告警.
+  Keywords: observability, metrics, traces, golden signals, alerting, SLO.
 allowed-tools: Read, Write, Grep, Glob
 argument-hint: "[service name or observability topic | 服務名稱或可觀測性主題]"
 ---

package/bundled/skills/orchestrate/SKILL.md

@@ -5,7 +5,7 @@ scope: universal
 description: |
   Orchestrate multi-task execution plans using Claude's native Agent tool (DAG-based, no external engine).
   Use when: executing a plan.json file with parallel/sequential task dependencies.
-  Keywords: orchestrate, plan, execute, DAG, task plan, 編排, 執行計畫, 並行.
+  Keywords: orchestrate, plan, execute, DAG, task plan.
 argument-hint: "<plan.json> [--dry-run]"
 ---
 

package/bundled/skills/plan/SKILL.md

@@ -5,7 +5,7 @@ scope: universal
 description: |
   Generate plan.json from Spec documents, OpenSpec changes, or free-text requirements.
   Use when: converting specifications into executable task plans for /orchestrate.
-  Keywords: plan, spec, task plan, 計畫, 規格, 任務, plan.json, DAG.
+  Keywords: plan, spec, task plan, plan.json, DAG.
 argument-hint: "[spec-file.md | openspec-dir/ | \"requirement text\" | (interactive)]"
 ---
 

package/bundled/skills/pr-automation-assistant/SKILL.md

@@ -4,7 +4,7 @@ scope: universal
 description: |
   Guide pull request creation, review automation, and merge strategies.
   Use when: creating PRs, automating reviews, configuring merge policies.
-  Keywords: pull request, PR, merge, review, GitHub, GitLab, 合併請求, 審查.
+  Keywords: pull request, PR, merge, review, GitHub, GitLab.
 allowed-tools: Read, Grep, Glob, Bash(git:*, gh:*)
 argument-hint: "[branch name or PR number | 分支名稱或 PR 編號]"
 ---

package/bundled/skills/project-structure-guide/SKILL.md

@@ -4,7 +4,7 @@ scope: universal
 description: |
   Guide for organizing project directories following language-specific best practices.
   Use when: creating projects, reorganizing structure, adding modules, setting up builds, deciding file placement.
-  Keywords: project, structure, directory, layout, gitignore, scaffold, 專案結構, 目錄, file placement, utils, helpers, shared, where to put, 檔案歸檔.
+  Keywords: project, structure, directory, layout, gitignore, scaffold, file placement, utils, helpers, shared, where to put.
 ---
 
 # Project Structure Guide

package/bundled/skills/push/SKILL.md

@@ -4,7 +4,7 @@ scope: universal
 description: |
   AI-assisted safety layer for git push operations with quality gates and collaboration guardrails.
   Use when: pushing commits, force pushing, pushing to protected branches, pushing feature branches.
-  Keywords: git push, force push, protected branch, quality gate, push receipt, PR automation, 推送, 保護分支, 品質閘門.
+  Keywords: git push, force push, protected branch, quality gate, push receipt, PR automation.
 allowed-tools: Read, Bash(git:*), Bash(npm:*), Bash(pnpm:*), Bash(yarn:*), Bash(bun:*)
 argument-hint: "[--force] [--target <branch>] [--skip-gates] [--no-pr]"
 ---

package/bundled/skills/retrospective-assistant/SKILL.md

@@ -4,7 +4,7 @@ scope: universal
 description: |
   [UDS] Guide structured team retrospectives for Sprint and Release cycles.
   Use when: sprint end, release post-mortem, iteration review, process improvement.
-  Keywords: retrospective, retro, sprint review, lessons learned, action items, 回顧, 檢討, 持續改善.
+  Keywords: retrospective, retro, sprint review, lessons learned, action items.
 allowed-tools: Read, Write, Glob, Grep
 argument-hint: "[sprint | release | actions | --technique starfish]"
 ---

package/bundled/skills/reverse-engineer/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: reverse
 scope: partial
-description: "[UDS] System archeology — reverse engineer code across Logic, Data, and Runtime dimensions"
+description: "[UDS] System archeology - reverse engineer code across Logic, Data, and Runtime dimensions"
 allowed-tools: Read, Grep, Glob, Bash(pg_dump:*), Bash(mysql:*), Bash(sqlite3:*), Bash(npm run:*), Bash(cat:*), Bash(docker:*)
 argument-hint: "[spec|data|runtime|bdd|tdd] <input>"
 disable-model-invocation: true

package/bundled/skills/runbook-assistant/SKILL.md

@@ -4,7 +4,7 @@ scope: universal
 description: |
   Guide runbook creation, maintenance, and drill exercises.
   Use when: writing runbooks, planning drills, auditing runbook coverage, post-incident runbook updates.
-  Keywords: runbook, operations, drill, on-call, procedure, 操作手冊, 演練.
+  Keywords: runbook, operations, drill, on-call, procedure.
 allowed-tools: Read, Write, Grep, Glob
 argument-hint: "[create|drill|coverage] [alert name or type | 告警名稱或類型]"
 ---

package/bundled/skills/security-assistant/SKILL.md

@@ -4,7 +4,7 @@ scope: universal
 description: |
   Guide security review and vulnerability assessment following OWASP standards.
   Use when: security audit, vulnerability check, secure coding review, threat modeling.
-  Keywords: security, OWASP, vulnerability, authentication, authorization, 安全, 漏洞, 認證.
+  Keywords: security, OWASP, vulnerability, authentication, authorization.
 allowed-tools: Read, Grep, Glob
 argument-hint: "[module or file to audit | 要審計的模組或檔案]"
 ---

package/bundled/skills/security-scan-assistant/SKILL.md

@@ -4,7 +4,7 @@ scope: universal
 description: |
   Guide automated security scanning, dependency auditing, and secret detection.
   Use when: dependency audit, CVE scanning, secret detection, license compliance.
-  Keywords: scan, audit, CVE, dependency, secret, SBOM, vulnerability, 掃描, 漏洞.
+  Keywords: scan, audit, CVE, dependency, secret, SBOM, vulnerability.
 allowed-tools: Read, Grep, Glob, Bash(npm:audit, npx:*)
 argument-hint: "[scan type or target | 掃描類型或目標]"
 ---

package/bundled/skills/slo-assistant/SKILL.md

@@ -4,7 +4,7 @@ scope: universal
 description: |
   Guide SLI selection, SLO setting, and Error Budget management.
   Use when: defining service quality targets, setting up SLO-based alerting, Error Budget policy.
-  Keywords: SLI, SLO, SLA, Error Budget, burn rate, service level, 服務等級.
+  Keywords: SLI, SLO, SLA, Error Budget, burn rate, service level.
 allowed-tools: Read, Write, Grep, Glob
 argument-hint: "[create|review|budget] [service name | 服務名稱]"
 ---

package/bundled/skills/sweep/SKILL.md

@@ -4,7 +4,7 @@ scope: universal
 description: |
   Scan codebase for debug artifacts and code quality issues; optionally auto-fix safe patterns.
   Use when: before committing, during PR review, or periodic codebase cleanup.
-  Keywords: sweep, debug cleanup, console.log, debugger, TODO, ts-any, code quality, 掃描, 清理.
+  Keywords: sweep, debug cleanup, console.log, debugger, TODO, ts-any, code quality.
 allowed-tools: Read, Grep, Glob, Bash(find:*), Edit, Write
 argument-hint: "[--fix] [--report] [--path <dir>] [--exclude <pattern>]"
 ---

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

@@ -5,7 +5,7 @@ description: |
   Testing pyramid and test writing standards for UT/IT/ST/E2E.
   Supports ISTQB and Industry Pyramid frameworks.
   Use when: writing tests, discussing test coverage, test strategy, or test naming.
-  Keywords: test, unit, integration, e2e, coverage, mock, ISTQB, SIT, 測試, 單元, 整合, 端對端.
+  Keywords: test, unit, integration, e2e, coverage, mock, ISTQB, SIT.
 ---
 
 # Testing Guide

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "universal-dev-standards",
-  "version": "5.14.0",
+  "version": "5.16.0",
   "description": "CLI tool for adopting Universal Development Standards",
   "keywords": [
     "documentation",
@@ -70,7 +70,7 @@
     "@vitest/coverage-v8": "^4.1.5",
     "ajv": "^8.20.0",
     "ajv-formats": "^3.0.1",
-    "eslint": "10.4.0",
+    "eslint": "10.4.1",
     "glob": "^13.0.1",
     "globals": "17.6.0",
     "husky": "^9.1.7",

package/src/commands/check.js

@@ -38,6 +38,7 @@ import { StandardValidator } from '../utils/standard-validator.js';
 import { WorkflowGate } from '../utils/workflow-gate.js';
 import { t, setLanguage, isLanguageExplicitlySet } from '../i18n/messages.js';
 import { guardAgainstSelfAdoption } from '../utils/detect-self-adoption.js';
+import { lintAll as lintI18nAll, partitionFindings as partitionI18nFindings } from '../lint/i18n.js';
 
 /**
  * Display the summary of file integrity status
@@ -243,6 +244,15 @@ function displayAdoptionStatus(manifest, msg, common, repoInfo) {
 export async function checkCommand(options = {}) {
   const projectPath = process.cwd();
 
+  // Handle --i18n option early — i18n lint is meant to be runnable both
+  // inside UDS source (lint canonical + locale variants) and inside
+  // adopter projects (lint installed locale variants). It does not require
+  // adoption-drift checks, so we short-circuit before guardAgainstSelfAdoption.
+  if (options.i18n) {
+    await runI18nLint(projectPath, options);
+    return;
+  }
+
   // Refuse to run inside the UDS source repo itself.
   // See DEC-044 / XSPEC-071 — adoption-drift check makes no sense for the
   // source repo. `--force` bypasses (e.g. private forks of UDS).
@@ -1837,3 +1847,73 @@ function displayWorkflowStatus(projectPath) {
     // Silently skip if workflow gate not available
   }
 }
+
+// ============================================================
+// i18n Lint (XSPEC-239 — P1-CLI-5)
+// ============================================================
+
+/**
+ * Run i18n lint across canonical + locale variants and print findings.
+ * Exits 1 if any error-level findings are detected.
+ *
+ * @param {string} projectPath
+ * @param {object} options - CLI options (currently honors options.json)
+ */
+async function runI18nLint(projectPath, options = {}) {
+  const findings = lintI18nAll({ projectPath });
+  const { errors, warnings, infos } = partitionI18nFindings(findings);
+
+  if (options.json) {
+    console.log(JSON.stringify({
+      summary: {
+        errors: errors.length,
+        warnings: warnings.length,
+        infos: infos.length,
+      },
+      findings,
+    }, null, 2));
+    if (errors.length > 0) process.exitCode = 1;
+    return;
+  }
+
+  console.log();
+  console.log(chalk.bold('UDS i18n Lint (XSPEC-239)'));
+  console.log(chalk.gray('─'.repeat(50)));
+  console.log();
+
+  if (findings.length === 0) {
+    console.log(chalk.green('  ✓ No i18n violations found.'));
+    console.log();
+    return;
+  }
+
+  // Display errors first
+  for (const f of errors) {
+    console.log(chalk.red(`  ✗ [${f.rule}]`));
+    console.log(chalk.red(`    ${f.file}:${f.line}`));
+    console.log(chalk.gray(`    ${f.message}`));
+    console.log();
+  }
+  for (const f of warnings) {
+    console.log(chalk.yellow(`  ⚠ [${f.rule}]`));
+    console.log(chalk.yellow(`    ${f.file}:${f.line}`));
+    console.log(chalk.gray(`    ${f.message}`));
+    console.log();
+  }
+
+  // Info findings are collapsed to a summary line to avoid flooding output
+  // (e.g. many locale files still lack source_hash). They never fail the gate.
+  if (infos.length > 0) {
+    console.log(chalk.cyan(`  ℹ ${infos.length} locale file(s) lack source_hash — silent content drift cannot be detected for them.`));
+    console.log(chalk.gray('    Stamp source_hash (sha256[:12] of canonical) when a locale is verified in sync to enable detection.'));
+    console.log();
+  }
+
+  console.log(chalk.gray('─'.repeat(50)));
+  console.log(`  ${chalk.red('Errors:')} ${errors.length}    ${chalk.yellow('Warnings:')} ${warnings.length}    ${chalk.cyan('Info:')} ${infos.length}`);
+  console.log();
+
+  if (errors.length > 0) {
+    process.exitCode = 1;
+  }
+}