universal-dev-standards 5.5.0 → 5.7.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (123) hide show
  1. package/bundled/ai/options/testing/integration-testing.ai.yaml +2 -2
  2. package/bundled/ai/options/testing/unit-testing.ai.yaml +2 -2
  3. package/bundled/ai/standards/agent-communication-protocol.ai.yaml +8 -9
  4. package/bundled/ai/standards/agent-dispatch.ai.yaml +8 -9
  5. package/bundled/ai/standards/branch-completion.ai.yaml +8 -10
  6. package/bundled/ai/standards/browser-compatibility-standards.ai.yaml +63 -0
  7. package/bundled/ai/standards/capability-declaration.ai.yaml +4 -4
  8. package/bundled/ai/standards/change-batching-standards.ai.yaml +8 -10
  9. package/bundled/ai/standards/circuit-breaker.ai.yaml +7 -7
  10. package/bundled/ai/standards/contract-testing-standards.ai.yaml +62 -0
  11. package/bundled/ai/standards/cross-flow-regression.ai.yaml +61 -0
  12. package/bundled/ai/standards/disaster-recovery-drill.ai.yaml +1 -1
  13. package/bundled/ai/standards/dual-phase-output.ai.yaml +3 -3
  14. package/bundled/ai/standards/execution-history.ai.yaml +8 -10
  15. package/bundled/ai/standards/failure-source-taxonomy.ai.yaml +8 -10
  16. package/bundled/ai/standards/full-coverage-testing.ai.yaml +192 -0
  17. package/bundled/ai/standards/git-worktree.ai.yaml +1 -1
  18. package/bundled/ai/standards/governance-layer.ai.yaml +114 -0
  19. package/bundled/ai/standards/mock-boundary.ai.yaml +1 -1
  20. package/bundled/ai/standards/model-selection.ai.yaml +1 -1
  21. package/bundled/ai/standards/packaging-standards.ai.yaml +8 -8
  22. package/bundled/ai/standards/pipeline-integration-standards.ai.yaml +8 -9
  23. package/bundled/ai/standards/pipeline-security-gates.ai.yaml +4 -0
  24. package/bundled/ai/standards/recovery-recipe-registry.ai.yaml +6 -10
  25. package/bundled/ai/standards/release-readiness-gate.ai.yaml +77 -0
  26. package/bundled/ai/standards/security-decision.ai.yaml +3 -3
  27. package/bundled/ai/standards/server-ops-security.ai.yaml +1 -1
  28. package/bundled/ai/standards/standard-admission-criteria.ai.yaml +1 -1
  29. package/bundled/ai/standards/standard-lifecycle-management.ai.yaml +1 -1
  30. package/bundled/ai/standards/supply-chain-attestation.ai.yaml +1 -1
  31. package/bundled/ai/standards/testing.ai.yaml +20 -13
  32. package/bundled/ai/standards/token-budget.ai.yaml +3 -3
  33. package/bundled/ai/standards/workflow-enforcement.ai.yaml +8 -11
  34. package/bundled/ai/standards/workflow-state-protocol.ai.yaml +8 -10
  35. package/bundled/core/accessibility-standards.md +58 -0
  36. package/bundled/core/adversarial-test.md +1 -1
  37. package/bundled/core/agent-behavior-discipline.md +4 -4
  38. package/bundled/core/agent-communication-protocol.md +5 -5
  39. package/bundled/core/branch-completion.md +4 -0
  40. package/bundled/core/browser-compatibility-standards.md +220 -0
  41. package/bundled/core/checkin-standards.md +1 -0
  42. package/bundled/core/circuit-breaker.md +4 -4
  43. package/bundled/core/container-security.md +8 -8
  44. package/bundled/core/contract-testing-standards.md +182 -0
  45. package/bundled/core/cross-flow-regression.md +190 -0
  46. package/bundled/core/disaster-recovery-drill.md +3 -3
  47. package/bundled/core/dual-phase-output.md +1 -1
  48. package/bundled/core/failure-source-taxonomy.md +3 -3
  49. package/bundled/core/flow-based-testing.md +135 -2
  50. package/bundled/core/full-coverage-testing.md +183 -0
  51. package/bundled/core/git-worktree.md +1 -1
  52. package/bundled/core/governance-layer.md +151 -0
  53. package/bundled/core/llm-output-validation.md +2 -2
  54. package/bundled/core/mock-boundary.md +1 -1
  55. package/bundled/core/packaging-standards.md +14 -14
  56. package/bundled/core/performance-standards.md +65 -0
  57. package/bundled/core/policy-as-code-testing.md +9 -9
  58. package/bundled/core/recovery-recipe-registry.md +2 -2
  59. package/bundled/core/release-quality-manifest.md +58 -12
  60. package/bundled/core/release-readiness-gate.md +184 -0
  61. package/bundled/core/sast-advanced.md +5 -5
  62. package/bundled/core/secure-op.md +5 -5
  63. package/bundled/core/security-decision.md +1 -1
  64. package/bundled/core/server-ops-security.md +15 -15
  65. package/bundled/core/smoke-test.md +1 -1
  66. package/bundled/core/standard-admission-criteria.md +1 -1
  67. package/bundled/core/standard-lifecycle-management.md +1 -1
  68. package/bundled/core/supply-chain-attestation.md +4 -4
  69. package/bundled/core/token-budget.md +3 -3
  70. package/bundled/locales/zh-CN/CHANGELOG.md +51 -4
  71. package/bundled/locales/zh-CN/README.md +11 -27
  72. package/bundled/locales/zh-CN/core/agent-communication-protocol.md +5 -5
  73. package/bundled/locales/zh-CN/core/circuit-breaker.md +1 -1
  74. package/bundled/locales/zh-CN/core/git-worktree.md +1 -1
  75. package/bundled/locales/zh-CN/core/packaging-standards.md +14 -14
  76. package/bundled/locales/zh-CN/core/recovery-recipe-registry.md +6 -9
  77. package/bundled/locales/zh-CN/core/standard-admission-criteria.md +1 -1
  78. package/bundled/locales/zh-CN/core/standard-lifecycle-management.md +1 -1
  79. package/bundled/locales/zh-CN/core/token-budget.md +1 -1
  80. package/bundled/locales/zh-TW/CHANGELOG.md +51 -4
  81. package/bundled/locales/zh-TW/README.md +11 -27
  82. package/bundled/locales/zh-TW/core/agent-communication-protocol.md +5 -5
  83. package/bundled/locales/zh-TW/core/browser-compatibility-standards.md +11 -0
  84. package/bundled/locales/zh-TW/core/capability-declaration.md +4 -4
  85. package/bundled/locales/zh-TW/core/circuit-breaker.md +7 -7
  86. package/bundled/locales/zh-TW/core/contract-testing-standards.md +11 -0
  87. package/bundled/locales/zh-TW/core/cross-flow-regression.md +11 -0
  88. package/bundled/locales/zh-TW/core/dual-phase-output.md +3 -3
  89. package/bundled/locales/zh-TW/core/failure-source-taxonomy.md +7 -9
  90. package/bundled/locales/zh-TW/core/governance-layer.md +159 -0
  91. package/bundled/locales/zh-TW/core/packaging-standards.md +14 -14
  92. package/bundled/locales/zh-TW/core/recovery-recipe-registry.md +6 -9
  93. package/bundled/locales/zh-TW/core/release-readiness-gate.md +11 -0
  94. package/bundled/locales/zh-TW/core/security-decision.md +3 -3
  95. package/bundled/locales/zh-TW/core/standard-admission-criteria.md +1 -1
  96. package/bundled/locales/zh-TW/core/standard-lifecycle-management.md +1 -1
  97. package/bundled/locales/zh-TW/core/token-budget.md +3 -3
  98. package/bundled/skills/README.md +23 -0
  99. package/bundled/skills/atdd-assistant/SKILL.md +4 -5
  100. package/bundled/skills/bdd-assistant/SKILL.md +4 -5
  101. package/bundled/skills/checkin-assistant/SKILL.md +4 -6
  102. package/bundled/skills/code-review-assistant/SKILL.md +4 -5
  103. package/bundled/skills/commands/observability.md +42 -0
  104. package/bundled/skills/commands/runbook.md +44 -0
  105. package/bundled/skills/commands/slo.md +45 -0
  106. package/bundled/skills/journey-test-assistant/SKILL.md +1 -1
  107. package/bundled/skills/orchestrate/SKILL.md +1 -1
  108. package/bundled/skills/plan/SKILL.md +1 -1
  109. package/bundled/skills/pr-automation-assistant/SKILL.md +4 -5
  110. package/bundled/skills/push/SKILL.md +1 -1
  111. package/bundled/skills/spec-driven-dev/SKILL.md +4 -5
  112. package/bundled/skills/sweep/SKILL.md +3 -3
  113. package/bundled/skills/tdd-assistant/SKILL.md +4 -5
  114. package/package.json +6 -6
  115. package/src/commands/check.js +43 -0
  116. package/src/commands/flow.js +7 -5
  117. package/src/commands/init.js +2 -1
  118. package/src/commands/start.js +7 -6
  119. package/src/commands/sweep.js +7 -6
  120. package/src/commands/update.js +10 -0
  121. package/src/commands/workflow.js +7 -6
  122. package/src/core/agent-communication-protocol.js +10 -3
  123. package/standards-registry.json +107 -51
@@ -0,0 +1,159 @@
1
+ ---
2
+ source: ../../../core/governance-layer.md
3
+ source_version: 1.0.0
4
+ translation_version: 1.0.0
5
+ last_synced: 2026-05-07
6
+ status: current
7
+ ---
8
+
9
+ # 治理層標準
10
+
11
+ > **語言**: [English](../../../core/governance-layer.md) | 繁體中文
12
+
13
+ **版本**: 1.0.0
14
+ **最後更新**: 2026-05-07
15
+ **適用範圍**: 所有具有多 Agent 或多角色 AI 工作流程的軟體專案
16
+ **範疇**: universal
17
+ **產業標準**: 無(UDS 原創)
18
+
19
+ ---
20
+
21
+ ## 目的
22
+
23
+ 治理層為專案中所有 Agent 與角色提供共同錨點:
24
+ Vision(方向)→ Mission(邊界 + 紅線)→ Goals(可量測的 KPI)。
25
+
26
+ 它是 **Standard #0**:在所有其他標準之前評估。當本標準與其他領域標準發生衝突時,本標準優先。
27
+
28
+ ---
29
+
30
+ ## 三層架構
31
+
32
+ ### Vision(願景)
33
+
34
+ | 欄位 | 要求 |
35
+ |------|------|
36
+ | 格式 | 單一句子,≤ 50 tokens |
37
+ | 內容 | 長期方向;永恆不變;不含量測指標 |
38
+ | 變更頻率 | 每年審查 |
39
+
40
+ **範例**:
41
+ > "成為全球軟體團隊最值得信賴的 AI 開發工作流程標準。"
42
+
43
+ ---
44
+
45
+ ### Mission(使命)
46
+
47
+ | 欄位 | 要求 |
48
+ |------|------|
49
+ | 格式 | 3–5 項承諾陳述 + 紅線清單(合計 ≤ 300 tokens) |
50
+ | 內容 | 我們做什麼 / 不做什麼;含觸發條件與處置動作的紅線 |
51
+ | 變更頻率 | 每季審查 |
52
+
53
+ **紅線必備欄位**:
54
+
55
+ | 欄位 | 型別 | 說明 |
56
+ |------|------|------|
57
+ | `id` | 字串 | 唯一識別碼(例如:R1、GUARD-001) |
58
+ | `category` | 字串 | 分類(quality / safety / compliance / ethics) |
59
+ | `clause` | 字串 | 人類可讀的禁止或要求陳述 |
60
+ | `action` | 列舉 | `block` \| `warn` \| `escalate_to_human` 之一 |
61
+
62
+ ---
63
+
64
+ ### Goals(目標)
65
+
66
+ | 欄位 | 要求 |
67
+ |------|------|
68
+ | 格式 | KPI 清單,≤ 500 tokens |
69
+ | 變更頻率 | 每個 Sprint 校準 |
70
+ | 可否證性 | 每個 KPI 必須可量測——禁止使用「改善」、「提升」等模糊詞彙 |
71
+
72
+ **KPI 必備欄位**:
73
+
74
+ | 欄位 | 型別 | 說明 |
75
+ |------|------|------|
76
+ | `id` | 字串 | 唯一識別碼(例如:KPI-01) |
77
+ | `metric_name` | 字串 | 追蹤的指標名稱 |
78
+ | `threshold` | 字串 | 量化目標(例如:≥ 95%、< 200 ms) |
79
+ | `measurement_method` | 字串 | 量測方式與時機 |
80
+
81
+ ---
82
+
83
+ ## 優先順序
84
+
85
+ 治理層對所有其他標準具有**更高優先權**。衝突時的解析順序:
86
+
87
+ 1. **治理層**(本標準)— 方向、紅線、KPI
88
+ 2. **領域標準**(測試、提交訊息、部署等)
89
+ 3. **專案特定覆寫**(本地 `.standards/` 客製化)
90
+
91
+ ---
92
+
93
+ ## 紅線格式
94
+
95
+ 每條紅線必須包含所有必備欄位。執行動作說明:
96
+
97
+ | 動作 | 行為 |
98
+ |------|------|
99
+ | `block` | 立即停止 pipeline;不繼續執行 |
100
+ | `warn` | 記錄違規並繼續;超過閾值時升級 |
101
+ | `escalate_to_human` | 暫停並要求人類決策後才繼續 |
102
+
103
+ 此外,每條紅線應包含 `mission_clause_ref` 欄位,參照其所強制執行的使命承諾。
104
+
105
+ ---
106
+
107
+ ## 評估器整合
108
+
109
+ 當專案使用 AI 評估器 Agent 時,治理層提供評分錨點:
110
+
111
+ | 評估軸 | 權重 | 否決閾值 |
112
+ |--------|------|----------|
113
+ | 正確性 | 0.4 | < 0.3 → 不通過 |
114
+ | 使命對齊度 | 0.3 | < 0.3 → 不通過 |
115
+ | 目標達成度 | 0.3 | < 0.3 → 不通過 |
116
+
117
+ - **mission_alignment_score**:輸出與使命承諾的對齊程度
118
+ - **goal_achievement_score**:輸出推進目標 KPI 的程度
119
+ - 任何單一評估軸低於 0.3 即觸發不通過,無論加權總分為何
120
+
121
+ ---
122
+
123
+ ## 風險接受(trace_only 模式)
124
+
125
+ 若專案放寬人工閘門(例如 `gate.mode = trace_only`),必須在 `mission.md` 中明確撰寫**風險接受條款**,包含:
126
+
127
+ | 必填欄位 | 說明 |
128
+ |----------|------|
129
+ | `date` | 接受風險的日期 |
130
+ | `signatory` | 接受風險的人員或角色 |
131
+ | `gates_bypassed` | 列舉所有繞過的人工閘門 |
132
+ | `risks_accepted` | 明確描述已接受的風險 |
133
+
134
+ 若無有效的風險接受條款,pipeline **必須拒絕啟動(fail-closed)**。
135
+
136
+ ---
137
+
138
+ ## 治理檔案結構
139
+
140
+ 採用本標準的專案應維護以下檔案:
141
+
142
+ ```
143
+ governance/
144
+ ├── vision.md # 單一句子願景陳述
145
+ ├── mission.md # 承諾 + 紅線清單
146
+ └── goals.md # KPI 清單(每個 Sprint 更新)
147
+ ```
148
+
149
+ ---
150
+
151
+ ## 合規檢查清單
152
+
153
+ - [ ] Vision 為單一句子且 ≤ 50 tokens,不含量測指標
154
+ - [ ] Mission 有 3–5 項承諾及含所有必備欄位的紅線清單
155
+ - [ ] 每條紅線均有:id、category、clause、action
156
+ - [ ] Goals 清單存在,每個 KPI 均含:id、metric_name、threshold、measurement_method
157
+ - [ ] 沒有任何 KPI 使用模糊詞彙(「改善」、「提升」、「更好」)
158
+ - [ ] 若 `gate.mode = trace_only`,`mission.md` 中存在風險接受條款
159
+ - [ ] 所有 AI 評估器以 0.4/0.3/0.3 權重評分,且任一軸 < 0.3 即不通過
@@ -12,19 +12,19 @@ status: current
12
12
 
13
13
  **版本**: 1.0.0
14
14
  **最後更新**: 2026-04-15
15
- **適用性**: 使用 UDS/DevAP 工具鏈的專案
15
+ **適用性**: 使用 UDS-aware 工具鏈的專案
16
16
  **範圍**: 通用 (Universal)
17
17
 
18
18
  ---
19
19
 
20
20
  ## 目的
21
21
 
22
- 本標準定義一套基於 Recipe 的打包框架,讓使用者專案可在 `.devap/packaging.yaml` 中宣告打包目標(target)。UDS 負責提供 Recipe 定義與內建 Recipe 函式庫;DevAP 則在 pipeline 中執行編排。
22
+ 本標準定義一套基於 Recipe 的打包框架,讓使用者專案可在 專案 packaging 配置(路徑由採用層決定) 中宣告打包目標(target)。UDS 負責提供 Recipe 定義與內建 Recipe 函式庫;採用層 runtime pipeline 中執行編排。
23
23
 
24
24
  框架的關注點分離如下:
25
25
  - **使用者專案**:宣告「打包什麼」(targets + 設定覆蓋)
26
26
  - **UDS**:定義「如何打包」(Recipe 結構 + 內建 Recipes)
27
- - **DevAP**:執行「何時打包」(在 Review 與 Deploy 之間的 pipeline 階段)
27
+ - **採用層 pipeline**:執行「何時打包」(在 Review 與 Deploy 之間的 pipeline 階段)
28
28
 
29
29
  ---
30
30
 
@@ -33,9 +33,9 @@ status: current
33
33
  | 原則 | 說明 |
34
34
  |------|------|
35
35
  | **Recipe-based** | 每個打包目標都參照一個具名 Recipe;不在 pipeline YAML 中撰寫臨時腳本 |
36
- | **宣告式 targets** | 專案在 `.devap/packaging.yaml` 中宣告 targets;DevAP 負責解析與執行 |
36
+ | **宣告式 targets** | 專案在 專案 packaging 配置(路徑由採用層決定) 中宣告 targets;採用層 runtime 負責解析與執行 |
37
37
  | **可客製化** | 四個客製化層允許設定覆蓋、Hook 注入、自訂 Recipe 及 Escape Hatch |
38
- | **整合至 Pipeline** | 打包作為獨立階段運行於 VibeOps pipeline 的 Review 與 Deploy 之間 |
38
+ | **整合至 Pipeline** | 打包作為獨立階段運行於 採用層 pipeline 的 Review 與 Deploy 之間 |
39
39
 
40
40
  ---
41
41
 
@@ -119,15 +119,15 @@ UDS 隨附四個內建 Recipe,位於 `recipes/` 目錄:
119
119
 
120
120
  | 層級 | 機制 | 使用時機 |
121
121
  |------|------|----------|
122
- | **L1 — 設定覆蓋** | `.devap/packaging.yaml` 中的 `config:` 區塊 | 更改預設值(registry URL、tag、輸出目錄)|
123
- | **L2 — Hook 注入** | `.devap/packaging.yaml` 中的 `hooks:` 區塊 | 在建置或發佈前後執行額外指令 |
124
- | **L3 — 自訂 Recipe** | 專案 `.devap/recipes/` 中的新 `.yaml` 檔案 | 完全不同的建置流程;內建 Recipe 不適用 |
122
+ | **L1 — 設定覆蓋** | 專案 packaging 配置(路徑由採用層決定) 中的 `config:` 區塊 | 更改預設值(registry URL、tag、輸出目錄)|
123
+ | **L2 — Hook 注入** | 專案 packaging 配置(路徑由採用層決定) 中的 `hooks:` 區塊 | 在建置或發佈前後執行額外指令 |
124
+ | **L3 — 自訂 Recipe** | 專案 `.uds/recipes/` 中的新 `.yaml` 檔案 | 完全不同的建置流程;內建 Recipe 不適用 |
125
125
  | **L4 — Escape Hatch** | target 定義中以 `script:` 取代 `recipe:` | 原始 shell 腳本,無適合的 Recipe 抽象 |
126
126
 
127
127
  ### L1 範例 — 設定覆蓋
128
128
 
129
129
  ```yaml
130
- # .devap/packaging.yaml
130
+ # .uds/packaging.yaml
131
131
  targets:
132
132
  - name: publish-npm
133
133
  recipe: npm-library
@@ -140,7 +140,7 @@ targets:
140
140
  ### L2 範例 — Hook 注入
141
141
 
142
142
  ```yaml
143
- # .devap/packaging.yaml
143
+ # .uds/packaging.yaml
144
144
  targets:
145
145
  - name: docker-push
146
146
  recipe: docker-service
@@ -153,7 +153,7 @@ targets:
153
153
  ### L3 範例 — 自訂 Recipe
154
154
 
155
155
  ```yaml
156
- # .devap/recipes/electron-app.yaml
156
+ # .uds/recipes/electron-app.yaml
157
157
  name: electron-app
158
158
  description: 建置 Electron 桌面應用程式
159
159
  requires:
@@ -169,7 +169,7 @@ config:
169
169
  ### L4 範例 — Escape Hatch
170
170
 
171
171
  ```yaml
172
- # .devap/packaging.yaml
172
+ # .uds/packaging.yaml
173
173
  targets:
174
174
  - name: legacy-bundle
175
175
  script: |
@@ -187,9 +187,9 @@ targets:
187
187
  |------|------|------|
188
188
  | 所有 `requires` 檔案存在 | 100% | 在任何步驟執行前檢查 |
189
189
  | 所有步驟以 exit code 0 結束 | 100% | 任何非零 exit 使執行失敗 |
190
- | `postBuild` 產出物存在 | 存在於預期路徑 | 建置步驟後由 DevAP 驗證 |
190
+ | `postBuild` 產出物存在 | 存在於預期路徑 | 建置步驟後由採用層 runtime 驗證 |
191
191
  | Hook 指令以 exit code 0 結束 | 100% | Hook 失敗會傳播為步驟失敗 |
192
- | 已發佈產出物可被取回 | HTTP 200 / registry 查詢成功 | DevAP 在發佈後進行 smoke check |
192
+ | 已發佈產出物可被取回 | HTTP 200 / registry 查詢成功 | 由採用層 runtime 在發佈後進行 smoke check |
193
193
 
194
194
  ### 失敗處理
195
195
 
@@ -133,14 +133,11 @@ fix_loop | circuit_breaker | rebase_and_retry | model_switch | degraded_mode | h
133
133
 
134
134
  ## 整合點
135
135
 
136
- ### DevAP
136
+ > 整合指引(informative;具體檔案路徑屬於採用層自訂範圍)。
137
137
 
138
- - `packages/core/src/types.ts` — `RecoveryRecipe` / `RecoveryStrategy` type
139
- - `packages/core/src/recovery-registry.ts` — Registry 實作與預設 recipe
140
- - `packages/core/src/orchestrator.ts` — fix loop 前查詢 Registry
138
+ ### 預期呼叫點
141
139
 
142
- ### VibeOps
143
-
144
- - `src/types/index.ts`獨立定義 `RecoveryRecipe`(AGPL 隔離)
145
- - `src/runner/recovery-registry.ts`獨立實作
146
- - `recovery-recipes.yaml` — 預設 recipe 配置
140
+ - 核心型別模組 — `RecoveryRecipe` / `RecoveryStrategy` type
141
+ - recovery-registry 模組 — Registry 實作與預設 recipe
142
+ - orchestrator 模組 fix loop 前查詢 Registry
143
+ - recovery-recipes 配置檔 預設 recipe 配置(檔名由採用層決定)
@@ -0,0 +1,11 @@
1
+ ---
2
+ source: ../../../core/release-readiness-gate.md
3
+ source_version: 1.0.0
4
+ translation_version: 0.0.0
5
+ last_synced: 2026-05-05
6
+ ---
7
+
8
+ <!-- TODO: 待完整繁體中文翻譯 — Translation pending -->
9
+ <!-- See source: core/release-readiness-gate.md -->
10
+
11
+ > 此標準尚未完整翻譯。請參閱英文原文:[English](../../../core/release-readiness-gate.md)
@@ -104,9 +104,9 @@ deny | ask | allow
104
104
 
105
105
  ## 適用組件
106
106
 
107
- - DevAP Safety Hook
108
- - VibeOps CommandPolicy
109
- - VibeOps Governance Framework(SPEC-049)
107
+ - Safety Hook(採用層)
108
+ - CommandPolicy(採用層)
109
+ - Governance Framework(採用層;OPA / Cedar / 自訂 policy engine 皆可)
110
110
  - 任何多來源規則合併的安全仲裁場景
111
111
 
112
112
  ---
@@ -66,7 +66,7 @@ status: current
66
66
 
67
67
  ### 4. AI-executable(AI 可消費)
68
68
 
69
- 至少一個 DevAP QualityGate / VibeOps Agent prompt / Skill 能消費:
69
+ 至少一個採用層元件(Quality Gate / Agent prompt / Skill / IDE rule)能消費:
70
70
 
71
71
  - 定義清楚的 guidelines(每條可驗證)
72
72
  - 至少 2 個 Given-When-Then scenarios
@@ -85,7 +85,7 @@ Deprecated ──(遷移完成)────────→ Archived
85
85
 
86
86
  ## 情境範例
87
87
 
88
- - **情境 1 — Trial → Active**:`retry-standards` 處於 trial。2026-08-01 審視發現 DevAP Fix Loop VibeOps Builder 均採用且無重大缺陷 → 轉 Active,`since=2026-08-01`,移除 `expires`
88
+ - **情境 1 — Trial → Active**:`retry-standards` 處於 trial。2026-08-01 審視發現多個採用層(Fix Loop / Builder Agent 等)均採用且無重大缺陷 → 轉 Active,`since=2026-08-01`,移除 `expires`
89
89
  - **情境 2 — Trial 逾期自動 Archived**:某標準 trial 期限 2026-10-17 到期未通過驗證 → 狀態轉 Archived,記錄原因
90
90
  - **情境 3 — Deprecated 帶遷移**:`legacy-retry-logic` 被 `retry-standards` 取代 → `status=deprecated, supersedes=retry-standards, migration_guide=docs/migrations/retry-v1-to-v2.md`;Skill 使用時顯示警告
91
91
 
@@ -127,9 +127,9 @@ safe | warning | danger | blocking
127
127
 
128
128
  ## 適用場景
129
129
 
130
- - DevAP 任務執行(Task token 預算監控)
131
- - VibeOps 9-Agent Pipeline(跨 Agent 累積上下文監控)
132
- - VibeOps PipelineMemory Snip 觸發條件
130
+ - Task 執行(Token 預算監控;採用層)
131
+ - Agent Pipeline(跨 Agent 累積上下文監控;採用層)
132
+ - PipelineMemory Snip 觸發條件(採用層)
133
133
  - 任何有 `maxTotalTokens` 限制的 Agent 執行環境
134
134
 
135
135
  ---
@@ -67,6 +67,29 @@ These skills provide standard guidance and workflows. They can be accessed via s
67
67
 
68
68
  > **Note**: For reference guides (e.g., Git Workflow, Logging, Error Codes), use the `/guide` command.
69
69
 
70
+ ## Skill Tiers (Listing Budget Optimization)
71
+
72
+ > Background: Claude Code reserves a fraction of context (default 1%) for skill listings via `skillListingBudgetFraction`. With 40+ UDS skills and adopter-installed plugins, descriptions can be truncated. UDS organizes skills into three tiers so adopters can optionally suppress less-used descriptions while keeping skills callable via `/<name>`.
73
+ >
74
+ > See [DEC-061](https://github.com/AsiaOstrich/dev-platform/blob/main/cross-project/decisions/DEC-061-uds-skill-listing-budget.md) for the decision and tradeoffs. Reference settings live in [`examples/skill-overrides-recommended.json`](../examples/skill-overrides-recommended.json). Detailed tuning: [`docs/skill-budget-tuning.md`](../docs/skill-budget-tuning.md).
75
+
76
+ ### Tier 1 — Core (daily use)
77
+ **Listing default**: `"on"` (full description shown). Always auto-discoverable.
78
+
79
+ `commit-standards`, `push`, `git-workflow-guide`, `tdd-assistant`, `bdd-assistant`, `testing-guide`, `code-review-assistant`, `refactoring-assistant`, `requirement-assistant`, `spec-driven-dev`, `adr-assistant`, `dev-workflow-guide`, `checkin-assistant`
80
+
81
+ ### Tier 2 — Advanced (weekly use)
82
+ **Listing default**: `"on"` (full description shown).
83
+
84
+ `atdd-assistant`, `e2e-assistant`, `journey-test-assistant`, `contract-test-assistant`, `security-assistant`, `deploy-assistant`, `ci-cd-assistant`, `error-code-guide`, `logging-guide`, `documentation-guide`, `api-design-assistant`, `database-assistant`, `project-structure-guide`, `ai-instruction-standards`, `release-standards`, `changelog-guide`, `test-coverage-assistant`, `pr-automation-assistant`, `spec-derivation`, `reverse-engineer`, `project-discovery`, `dev-methodology`, `audit-assistant`, `docs-generator`
85
+
86
+ ### Tier 3 — Specialist (monthly or event-driven)
87
+ **Listing default**: `"name-only"` in reference overrides — saves tokens; **still callable via `/<name>`**.
88
+
89
+ `incident-response-assistant`, `observability-assistant`, `slo-assistant`, `runbook-assistant`, `retrospective-assistant`, `durable-execution-assistant`, `metrics-dashboard-assistant`, `migration-assistant`, `security-scan-assistant`, `brainstorm-assistant`, `skill-builder`
90
+
91
+ > Tier rationale & criteria: [`flows/skill-tiering-rationale.md`](../flows/skill-tiering-rationale.md). Adopters may freely override the reference (promote a Tier 3 skill to `"on"` if they use it daily, or demote any to `"name-only"`).
92
+
70
93
  ## Tool Adapters
71
94
 
72
95
  Specific configurations for various AI tools are located in `skills/tools/`.
@@ -7,11 +7,10 @@ argument-hint: "[feature or spec | 功能或規格]"
7
7
  ---
8
8
  <!-- DEPRECATION NOTICE (XSPEC-086 Phase 4, 2026-04-28):
9
9
  ATDD lifecycle orchestration (5-phase: WORKSHOP→DISTILLATION→DEVELOPMENT→DEMO→DONE,
10
- INVEST validation, AC→Gherkin conversion, RED/GREEN execution, PO sign-off gates) extracted to:
11
- - DevAP flow: dev-autopilot/.devap/flows/atdd.flow.yaml
12
- - DevAP CLI: devap atdd (packages/cli/src/commands/atdd.ts)
13
- This Skill retains: INVEST criteria table, ATDD cycle diagram, Gherkin AC format, Three Amigos structure.
14
- Use `devap atdd` for enforced lifecycle; this Skill for format and principle reference.
10
+ INVEST validation, AC→Gherkin conversion, RED/GREEN execution, PO sign-off gates) relocated to
11
+ adoption layer (XSPEC-095, 2026-04-28). This Skill retains: INVEST criteria table, ATDD cycle
12
+ diagram, Gherkin AC format, Three Amigos structure.
13
+ For enforced lifecycle execution, use your adoption layer's toolchain.
15
14
  -->
16
15
 
17
16
  # ATDD Assistant | ATDD 助手
@@ -6,11 +6,10 @@ allowed-tools: Read, Write, Grep, Glob
6
6
  argument-hint: "[feature or spec | 功能或規格]"
7
7
  ---
8
8
  <!-- DEPRECATION NOTICE (XSPEC-086 Phase 4, 2026-04-28):
9
- BDD lifecycle orchestration (4-phase cycle, Gherkin scaffolding, RED/GREEN execution) extracted to:
10
- - DevAP flow: dev-autopilot/.devap/flows/bdd.flow.yaml
11
- - DevAP CLI: devap bdd (packages/cli/src/commands/bdd.ts)
12
- This Skill retains: Gherkin format definition, Three Amigos structure, BDD cycle diagram.
13
- Use `devap bdd` for enforced cycle; this Skill for format and principle reference.
9
+ BDD lifecycle orchestration (4-phase cycle, Gherkin scaffolding, RED/GREEN execution) relocated to
10
+ adoption layer (XSPEC-095, 2026-04-28). This Skill retains: Gherkin format definition, Three
11
+ Amigos structure, BDD cycle diagram.
12
+ For enforced lifecycle execution, use your adoption layer's toolchain.
14
13
  -->
15
14
 
16
15
  # BDD Assistant | BDD 助手
@@ -6,12 +6,10 @@ allowed-tools: Read, Grep, Glob, Bash(git diff:*), Bash(git status:*), Bash(npm
6
6
  disable-model-invocation: true
7
7
  ---
8
8
  <!-- DEPRECATION NOTICE (XSPEC-086 Phase 4, 2026-04-28):
9
- Checkin workflow orchestration (gate execution sequence, abort logic) extracted to:
10
- - DevAP flow: dev-autopilot/.devap/flows/checkin.flow.yaml
11
- - DevAP CLI: devap checkin (packages/cli/src/commands/checkin.ts)
12
- - Flow spec: dev-autopilot/standards/flow/checkin-gate-sequence.ai.yaml
13
- This Skill retains: quality gate definitions, checklist items, never-commit rules.
14
- Use `devap checkin` for enforced execution; this Skill for activity reference.
9
+ Checkin workflow orchestration (gate execution sequence, abort logic) relocated to adoption layer
10
+ (XSPEC-095, 2026-04-28). This Skill retains: quality gate definitions, checklist items,
11
+ never-commit rules.
12
+ For enforced execution, use your adoption layer's toolchain.
15
13
  -->
16
14
 
17
15
  # Check-in Assistant | 簽入助手
@@ -7,11 +7,10 @@ argument-hint: "[file path or branch | 檔案路徑或分支名稱]"
7
7
  disable-model-invocation: true
8
8
  ---
9
9
  <!-- DEPRECATION NOTICE (XSPEC-086 Phase 4, 2026-04-28):
10
- Code review workflow orchestration (4-step sequence, outcome gating) extracted to:
11
- - DevAP flow: dev-autopilot/.devap/flows/review.flow.yaml
12
- - DevAP CLI: devap review (packages/cli/src/commands/review.ts)
13
- This Skill retains: 8 review category definitions, BLOCKING/IMPORTANT/SUGGESTION/QUESTION/NOTE prefix semantics.
14
- Use `devap review` for enforced execution; this Skill for category and prefix reference.
10
+ Code review workflow orchestration (4-step sequence, outcome gating) relocated to adoption layer
11
+ (XSPEC-095, 2026-04-28). This Skill retains: 8 review category definitions,
12
+ BLOCKING/IMPORTANT/SUGGESTION/QUESTION/NOTE prefix semantics.
13
+ For enforced execution, use your adoption layer's toolchain.
15
14
  -->
16
15
 
17
16
  # Code Review Assistant | 程式碼審查助手
@@ -9,3 +9,45 @@ argument-hint: "[--checklist | --maturity | --alerting | service name | 服務
9
9
  See [SKILL.md](../observability-assistant/SKILL.md) for full documentation.
10
10
 
11
11
  詳見 [SKILL.md](../observability-assistant/SKILL.md)。
12
+
13
+ ## AI Agent Behavior | AI 代理行為
14
+
15
+ > Follows [AI Command Behavior Standards](../../core/ai-command-behavior.md)
16
+
17
+ ### Entry Router | 進入路由
18
+
19
+ | Input | AI Action |
20
+ |-------|-----------|
21
+ | `/observability` | 詢問目標服務,進行整體可觀測性評估 |
22
+ | `/observability --checklist` | 直接執行可觀測性檢查清單 |
23
+ | `/observability --maturity` | 執行成熟度評估並給出改善建議 |
24
+ | `/observability --alerting` | 進入告警規則設計與審查流程 |
25
+ | `/observability <service>` | 針對指定服務進行可觀測性分析 |
26
+
27
+ ### Interaction Script | 互動腳本
28
+
29
+ 1. 確認目標服務與現有可觀測性工具(Prometheus、Grafana、Datadog 等)
30
+ 2. 依選定模式執行評估或設計流程
31
+ 3. 展示現況分析與缺口報告
32
+
33
+ **Decision: 可觀測性缺口**
34
+ - IF 缺少 Metrics → 建議關鍵指標清單(RED/USE method)
35
+ - IF 缺少 Tracing → 建議分散式追蹤導入步驟
36
+ - IF 缺少 Logging → 建議結構化日誌規範
37
+ - IF 告警規則不完整 → 建議補齊 SLO-based alerting
38
+
39
+ 🛑 **STOP**: 缺口分析完成後等待使用者確認優先補齊項目
40
+
41
+ ### Stop Points | 停止點
42
+
43
+ | Stop Point | 等待內容 |
44
+ |-----------|---------|
45
+ | 現況評估報告後 | 使用者確認分析正確性 |
46
+ | 改善建議展示後 | 使用者決定優先實施項目 |
47
+
48
+ ### Error Handling | 錯誤處理
49
+
50
+ | Error Condition | AI Action |
51
+ |-----------------|-----------|
52
+ | 無法識別監控工具 | 詢問工具名稱或改以通用建議進行 |
53
+ | 服務不存在或名稱不明 | 請使用者確認服務名稱或列出已知服務 |
@@ -9,3 +9,47 @@ argument-hint: "[create | drill | coverage] [alert name | 告警名稱]"
9
9
  See [SKILL.md](../runbook-assistant/SKILL.md) for full documentation.
10
10
 
11
11
  詳見 [SKILL.md](../runbook-assistant/SKILL.md)。
12
+
13
+ ## AI Agent Behavior | AI 代理行為
14
+
15
+ > Follows [AI Command Behavior Standards](../../core/ai-command-behavior.md)
16
+
17
+ ### Entry Router | 進入路由
18
+
19
+ | Input | AI Action |
20
+ |-------|-----------|
21
+ | `/runbook` | 詢問目標告警或服務,進入 runbook 導覽選單 |
22
+ | `/runbook create` | 啟動 runbook 建立流程 |
23
+ | `/runbook create <alert>` | 針對指定告警直接建立 runbook |
24
+ | `/runbook drill` | 啟動 runbook 演練模擬流程 |
25
+ | `/runbook coverage` | 產生 runbook 覆蓋率報告 |
26
+
27
+ ### Interaction Script | 互動腳本
28
+
29
+ 1. 確認操作模式(建立 / 演練 / 覆蓋率)
30
+ 2. 依模式執行對應流程,收集必要資訊
31
+ 3. 輸出 runbook 草稿或報告
32
+
33
+ **Decision: 建立模式**
34
+ - IF 告警名稱已提供 → 直接填入模板並產生草稿
35
+ - IF 告警名稱未提供 → 詢問告警名稱、嚴重程度、負責團隊
36
+
37
+ **Decision: 演練模式**
38
+ - 逐步模擬告警觸發情境,確認執行步驟可行性
39
+ - IF 步驟有疑義 → 停止並請使用者確認或修正
40
+
41
+ 🛑 **STOP**: runbook 草稿產生後等待使用者審查與修正
42
+
43
+ ### Stop Points | 停止點
44
+
45
+ | Stop Point | 等待內容 |
46
+ |-----------|---------|
47
+ | 草稿產生後 | 使用者審查並確認內容正確 |
48
+ | 演練每個關鍵步驟後 | 使用者確認步驟可執行 |
49
+
50
+ ### Error Handling | 錯誤處理
51
+
52
+ | Error Condition | AI Action |
53
+ |-----------------|-----------|
54
+ | 告警名稱不明確 | 請使用者提供告警名稱或描述觸發條件 |
55
+ | 無現有 runbook 可演練 | 提示先執行 `create` 建立 runbook |
@@ -9,3 +9,48 @@ argument-hint: "[create | review | budget] [service name | 服務名稱]"
9
9
  See [SKILL.md](../slo-assistant/SKILL.md) for full documentation.
10
10
 
11
11
  詳見 [SKILL.md](../slo-assistant/SKILL.md)。
12
+
13
+ ## AI Agent Behavior | AI 代理行為
14
+
15
+ > Follows [AI Command Behavior Standards](../../core/ai-command-behavior.md)
16
+
17
+ ### Entry Router | 進入路由
18
+
19
+ | Input | AI Action |
20
+ |-------|-----------|
21
+ | `/slo` | 詢問目標服務,進入 SLO 設計導覽 |
22
+ | `/slo create` | 啟動新 SLO 建立流程 |
23
+ | `/slo create <service>` | 針對指定服務直接啟動 SLO 建立 |
24
+ | `/slo review` | 審查現有 SLO 設定合理性 |
25
+ | `/slo budget` | 查看 Error Budget 消耗狀況與建議 |
26
+
27
+ ### Interaction Script | 互動腳本
28
+
29
+ 1. 確認操作模式(建立 / 審查 / Error Budget)
30
+ 2. 依模式引導使用者完成 SLI 選擇、目標設定或現況分析
31
+ 3. 輸出 SLO 定義草稿或 Error Budget 報告
32
+
33
+ **Decision: 建立模式**
34
+ - 引導選擇 SLI 類型(Availability / Latency / Quality)
35
+ - 詢問目標值(如 99.9%)與測量窗口(rolling 28d)
36
+ - IF 目標值過高(>99.99%)→ 警告工程成本,建議先設較保守目標
37
+
38
+ **Decision: Error Budget 模式**
39
+ - IF budget 剩餘 < 10% → 建議暫停非必要發布
40
+ - IF budget 已燒盡 → 提示凍結發布,優先處理可靠性
41
+
42
+ 🛑 **STOP**: SLO 草稿完成後等待使用者確認目標值與告警閾值
43
+
44
+ ### Stop Points | 停止點
45
+
46
+ | Stop Point | 等待內容 |
47
+ |-----------|---------|
48
+ | SLI 選擇完成後 | 使用者確認選定的可靠性指標 |
49
+ | SLO 草稿產生後 | 使用者審查目標值與告警設定 |
50
+
51
+ ### Error Handling | 錯誤處理
52
+
53
+ | Error Condition | AI Action |
54
+ |-----------------|-----------|
55
+ | 服務無監控資料 | 建議先導入基礎 metrics,再設定 SLO |
56
+ | 目標值格式錯誤 | 提示正確格式(如 `99.9%` 或 `0.999`) |
@@ -199,5 +199,5 @@ describe.skipIf(!BASE_URL)("Platform Admin Journey — T-001 → T-010", () => {
199
199
  ## 參考
200
200
 
201
201
  - 標準:[user-journey-testing.ai.yaml](../../.standards/user-journey-testing.ai.yaml)
202
- - 相關 XSPEC:XSPEC-128(UDS 標準定義)、XSPEC-129(VibeOps 實作範例)
202
+ - 相關 XSPEC:XSPEC-128(UDS 標準定義)
203
203
  - 相關 Skill:`/e2e`(AC 層測試)、`/atdd`(驗收條件定義)
@@ -164,4 +164,4 @@ After completing the task, run: {task.verify_command}
164
164
  | 版本 | 日期 | 變更 |
165
165
  |------|------|------|
166
166
  | 2.0.0 | 2026-04-28 | 升格為 UDS 正式 Skill;Step 1 改為 Claude-native 解析(移除 plan-resolver-cli.js 依賴);新增 Quality Gate / Fix Loop 章節(XSPEC-097 Phase 3) |
167
- | 1.0.0 | 2026-04-09 | 初始發布(DevAP packages/cli/skills/) |
167
+ | 1.0.0 | 2026-04-09 | 初始發布(從上游遷移) |
@@ -231,4 +231,4 @@ Claude 對 plan.json 執行以下驗證(無需外部引擎):
231
231
  | 版本 | 日期 | 變更 |
232
232
  |------|------|------|
233
233
  | 2.0.0 | 2026-04-28 | 升格為 UDS 正式 Skill;移除 [DEVAP] 標記;Step 9 改為 Claude-native 驗證(XSPEC-097 Phase 3) |
234
- | 1.0.0 | 2026-04-09 | 初始發布(DevAP packages/cli/skills/) |
234
+ | 1.0.0 | 2026-04-09 | 初始發布(從上游遷移) |
@@ -10,11 +10,10 @@ argument-hint: "[branch name or PR number | 分支名稱或 PR 編號]"
10
10
  ---
11
11
  <!-- DEPRECATION NOTICE (XSPEC-086 Phase 4, 2026-04-28):
12
12
  PR lifecycle orchestration (5-step: CREATE→REVIEW→APPROVE→MERGE→CLEANUP,
13
- size gate >400 lines block, CI gate, squash/merge strategy, gh CLI integration) extracted to:
14
- - DevAP flow: dev-autopilot/.devap/flows/pr.flow.yaml
15
- - DevAP CLI: devap pr (packages/cli/src/commands/pr.ts)
16
- This Skill retains: PR description template, merge strategy decision matrix, auto-review trigger rules.
17
- Use `devap pr` for enforced lifecycle; this Skill for template and rule reference.
13
+ size gate >400 lines block, CI gate, squash/merge strategy, gh CLI integration) relocated to
14
+ adoption layer (XSPEC-095, 2026-04-28). This Skill retains: PR description template,
15
+ merge strategy decision matrix, auto-review trigger rules.
16
+ For enforced lifecycle execution, use your adoption layer's toolchain.
18
17
  -->
19
18
 
20
19
  # PR Automation Assistant | PR 自動化助手
@@ -238,7 +238,7 @@ After `/push` completes, the AI assistant should suggest:
238
238
 
239
239
  | Version | Date | Changes |
240
240
  |---------|------|---------|
241
- | 2.0.0 | 2026-04-28 | Restore workflow execution steps (DevAP decomposition XSPEC-097); remove deprecation notice |
241
+ | 2.0.0 | 2026-04-28 | Restore workflow execution steps (XSPEC-097 採用層解耦); remove deprecation notice |
242
242
  | 1.0.0 | 2026-04-23 | Initial release — XSPEC-081 Phase 1 |
243
243
 
244
244
  ---
@@ -6,11 +6,10 @@ allowed-tools: Read, Write, Grep, Glob, Bash(git:*)
6
6
  argument-hint: "[spec name or feature | 規格名稱或功能]"
7
7
  ---
8
8
  <!-- DEPRECATION NOTICE (XSPEC-086 Phase 4, 2026-04-28):
9
- SDD lifecycle orchestration (7-phase state machine, phase transitions, gate checks) extracted to:
10
- - DevAP flow: dev-autopilot/.devap/flows/sdd.flow.yaml
11
- - DevAP CLI: devap sdd (packages/cli/src/commands/sdd.ts) with --phase jump support
12
- This Skill retains: spec format definition, state descriptions, delta operations, decision tree.
13
- Use `devap sdd` for enforced lifecycle; this Skill for spec structure reference.
9
+ SDD lifecycle orchestration (7-phase state machine, phase transitions, gate checks) relocated to
10
+ adoption layer (XSPEC-095, 2026-04-28). This Skill retains: spec format definition, state
11
+ descriptions, delta operations, decision tree.
12
+ For enforced lifecycle execution, use your adoption layer's toolchain.
14
13
  -->
15
14
 
16
15
  # Spec-Driven Development Assistant | 規格驅動開發助手