universal-dev-standards 6.7.5 → 6.9.0

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 (213) hide show
  1. package/bin/uds.js +19 -2
  2. package/bundled/ai/standards/acceptance-criteria-traceability.ai.yaml +14 -2
  3. package/bundled/ai/standards/adr-standards.ai.yaml +14 -2
  4. package/bundled/ai/standards/ai-instruction-standards.ai.yaml +6 -6
  5. package/bundled/ai/standards/code-review.ai.yaml +13 -3
  6. package/bundled/ai/standards/commit-message.ai.yaml +8 -4
  7. package/bundled/ai/standards/deferred-item-exit.ai.yaml +225 -0
  8. package/bundled/ai/standards/feature-discovery-standards.ai.yaml +14 -2
  9. package/bundled/ai/standards/governance-layer.ai.yaml +128 -2
  10. package/bundled/ai/standards/logging.ai.yaml +2 -2
  11. package/bundled/ai/standards/retrospective-standards.ai.yaml +14 -2
  12. package/bundled/ai/standards/reverse-engineering-standards.ai.yaml +73 -2
  13. package/bundled/ai/standards/security-standards.ai.yaml +2 -2
  14. package/bundled/ai/standards/spec-driven-development.ai.yaml +14 -2
  15. package/bundled/ai/standards/tech-debt-standards.ai.yaml +87 -3
  16. package/bundled/ai/standards/turn-completion-integrity.ai.yaml +131 -0
  17. package/bundled/core/acceptance-criteria-traceability.md +5 -2
  18. package/bundled/core/adr-standards.md +26 -2
  19. package/bundled/core/ai-instruction-standards.md +9 -7
  20. package/bundled/core/code-review-checklist.md +5 -2
  21. package/bundled/core/context-aware-loading.md +1 -1
  22. package/bundled/core/deferred-item-exit.md +254 -0
  23. package/bundled/core/feature-discovery-standards.md +5 -1
  24. package/bundled/core/governance-layer.md +114 -2
  25. package/bundled/core/retrospective-standards.md +4 -2
  26. package/bundled/core/reverse-engineering-standards.md +81 -2
  27. package/bundled/core/spec-driven-development.md +8 -2
  28. package/bundled/core/tech-debt-standards.md +67 -8
  29. package/bundled/core/turn-completion-integrity.md +196 -0
  30. package/bundled/hooks/check-dangerous-cmd.mjs +60 -0
  31. package/bundled/hooks/check-logging-standard.mjs +59 -0
  32. package/bundled/hooks/check-turn-completion.mjs +233 -0
  33. package/bundled/hooks/inject-standards.mjs +183 -0
  34. package/bundled/hooks/telemetry-wrapper.mjs +77 -0
  35. package/bundled/hooks/turn-completion/detect.mjs +99 -0
  36. package/bundled/hooks/turn-completion/locales/en.mjs +159 -0
  37. package/bundled/hooks/turn-completion/locales/zh-TW.mjs +166 -0
  38. package/bundled/hooks/validate-commit-msg.mjs +104 -0
  39. package/bundled/locales/zh-CN/CHANGELOG.md +65 -3
  40. package/bundled/locales/zh-CN/CLAUDE.md +1 -1
  41. package/bundled/locales/zh-CN/README.md +7 -7
  42. package/bundled/locales/zh-CN/SECURITY.md +1 -1
  43. package/bundled/locales/zh-CN/core/adr-standards.md +1 -1
  44. package/bundled/locales/zh-CN/core/ai-instruction-standards.md +10 -8
  45. package/bundled/locales/zh-CN/core/governance-layer.md +118 -6
  46. package/bundled/locales/zh-CN/core/retrospective-standards.md +1 -1
  47. package/bundled/locales/zh-CN/core/tech-debt-standards.md +71 -4
  48. package/bundled/locales/zh-CN/core/turn-completion-integrity.md +190 -0
  49. package/bundled/locales/zh-CN/docs/CHEATSHEET.md +27 -6
  50. package/bundled/locales/zh-CN/docs/CLI-INIT-OPTIONS.md +29 -68
  51. package/bundled/locales/zh-CN/docs/FEATURE-REFERENCE.md +172 -24
  52. package/bundled/locales/zh-CN/docs/USAGE-MODES-COMPARISON.md +1 -2
  53. package/bundled/locales/zh-CN/integrations/google-antigravity/{INSTRUCTIONS.md → AGENTS.md} +1 -1
  54. package/bundled/locales/zh-CN/integrations/google-antigravity/README.md +3 -3
  55. package/bundled/locales/zh-CN/skills/agents/README.md +1 -1
  56. package/bundled/locales/zh-CN/skills/atdd-assistant/SKILL.md +2 -0
  57. package/bundled/locales/zh-CN/skills/bdd-assistant/SKILL.md +2 -0
  58. package/bundled/locales/zh-CN/skills/brainstorm-assistant/SKILL.md +22 -12
  59. package/bundled/locales/zh-CN/skills/brainstorm-assistant/guide.md +12 -9
  60. package/bundled/locales/zh-CN/skills/code-review-assistant/SKILL.md +1 -0
  61. package/bundled/locales/zh-CN/skills/commands/brainstorm.md +17 -13
  62. package/bundled/locales/zh-CN/skills/commands/config.md +0 -1
  63. package/bundled/locales/zh-CN/skills/commands/init.md +1 -2
  64. package/bundled/locales/zh-CN/skills/commit-standards/SKILL.md +2 -0
  65. package/bundled/locales/zh-CN/skills/contract-test-assistant/SKILL.md +1 -0
  66. package/bundled/locales/zh-CN/skills/dev-methodology/SKILL.md +2 -0
  67. package/bundled/locales/zh-CN/skills/observability-assistant/SKILL.md +1 -0
  68. package/bundled/locales/zh-CN/skills/project-structure-guide/SKILL.md +1 -0
  69. package/bundled/locales/zh-CN/skills/release-standards/SKILL.md +3 -0
  70. package/bundled/locales/zh-CN/skills/requirement-assistant/SKILL.md +2 -0
  71. package/bundled/locales/zh-CN/skills/reverse-engineer/SKILL.md +3 -0
  72. package/bundled/locales/zh-CN/skills/reverse-engineer/tdd-analysis.md +13 -23
  73. package/bundled/locales/zh-CN/skills/runbook-assistant/SKILL.md +1 -0
  74. package/bundled/locales/zh-CN/skills/slo-assistant/SKILL.md +1 -0
  75. package/bundled/locales/zh-CN/skills/tdd-assistant/SKILL.md +2 -0
  76. package/bundled/locales/zh-CN/skills/workflows/README.md +2 -11
  77. package/bundled/locales/zh-TW/CHANGELOG.md +65 -3
  78. package/bundled/locales/zh-TW/CLAUDE.md +1 -1
  79. package/bundled/locales/zh-TW/README.md +7 -7
  80. package/bundled/locales/zh-TW/SECURITY.md +1 -1
  81. package/bundled/locales/zh-TW/core/acceptance-criteria-traceability.md +2 -0
  82. package/bundled/locales/zh-TW/core/adr-standards.md +26 -5
  83. package/bundled/locales/zh-TW/core/ai-instruction-standards.md +10 -8
  84. package/bundled/locales/zh-TW/core/code-review-checklist.md +2 -0
  85. package/bundled/locales/zh-TW/core/container-image-standards.md +2 -2
  86. package/bundled/locales/zh-TW/core/contract-testing-standards.md +2 -2
  87. package/bundled/locales/zh-TW/core/cross-flow-regression.md +8 -7
  88. package/bundled/locales/zh-TW/core/data-contract.md +2 -2
  89. package/bundled/locales/zh-TW/core/data-migration-testing.md +2 -2
  90. package/bundled/locales/zh-TW/core/data-pipeline.md +2 -2
  91. package/bundled/locales/zh-TW/core/deferred-item-exit.md +251 -0
  92. package/bundled/locales/zh-TW/core/documentation-writing-standards.md +228 -3
  93. package/bundled/locales/zh-TW/core/full-coverage-testing.md +15 -2
  94. package/bundled/locales/zh-TW/core/governance-layer.md +118 -5
  95. package/bundled/locales/zh-TW/core/iac-design-principles.md +2 -2
  96. package/bundled/locales/zh-TW/core/incident-response.md +2 -2
  97. package/bundled/locales/zh-TW/core/model-provenance.md +4 -2
  98. package/bundled/locales/zh-TW/core/pii-classification.md +42 -6
  99. package/bundled/locales/zh-TW/core/prd-standards.md +4 -2
  100. package/bundled/locales/zh-TW/core/product-metrics-standards.md +4 -2
  101. package/bundled/locales/zh-TW/core/release-readiness-gate.md +2 -2
  102. package/bundled/locales/zh-TW/core/resource-cost-boundary.md +2 -2
  103. package/bundled/locales/zh-TW/core/retrospective-standards.md +5 -3
  104. package/bundled/locales/zh-TW/core/reverse-engineering-standards.md +83 -5
  105. package/bundled/locales/zh-TW/core/runbook.md +2 -2
  106. package/bundled/locales/zh-TW/core/schema-evolution.md +2 -2
  107. package/bundled/locales/zh-TW/core/secret-management-standards.md +2 -2
  108. package/bundled/locales/zh-TW/core/slo-sli.md +2 -2
  109. package/bundled/locales/zh-TW/core/spec-driven-development.md +2 -0
  110. package/bundled/locales/zh-TW/core/tech-debt-standards.md +71 -4
  111. package/bundled/locales/zh-TW/core/turn-completion-integrity.md +190 -0
  112. package/bundled/locales/zh-TW/core/user-journey-testing.md +2 -2
  113. package/bundled/locales/zh-TW/core/user-story-mapping.md +2 -2
  114. package/bundled/locales/zh-TW/core/verification-oracle.md +2 -2
  115. package/bundled/locales/zh-TW/docs/CHEATSHEET.md +27 -6
  116. package/bundled/locales/zh-TW/docs/CLI-INIT-OPTIONS.md +29 -68
  117. package/bundled/locales/zh-TW/docs/FEATURE-REFERENCE.md +172 -24
  118. package/bundled/locales/zh-TW/docs/USAGE-MODES-COMPARISON.md +1 -2
  119. package/bundled/locales/zh-TW/integrations/google-antigravity/{INSTRUCTIONS.md → AGENTS.md} +1 -1
  120. package/bundled/locales/zh-TW/integrations/google-antigravity/README.md +3 -3
  121. package/bundled/locales/zh-TW/skills/adr-assistant/SKILL.md +1 -1
  122. package/bundled/locales/zh-TW/skills/agents/README.md +1 -1
  123. package/bundled/locales/zh-TW/skills/atdd-assistant/SKILL.md +2 -0
  124. package/bundled/locales/zh-TW/skills/bdd-assistant/SKILL.md +2 -0
  125. package/bundled/locales/zh-TW/skills/brainstorm-assistant/SKILL.md +22 -12
  126. package/bundled/locales/zh-TW/skills/brainstorm-assistant/guide.md +12 -9
  127. package/bundled/locales/zh-TW/skills/code-review-assistant/SKILL.md +1 -0
  128. package/bundled/locales/zh-TW/skills/commands/brainstorm.md +17 -13
  129. package/bundled/locales/zh-TW/skills/commands/config.md +0 -1
  130. package/bundled/locales/zh-TW/skills/commands/init.md +1 -2
  131. package/bundled/locales/zh-TW/skills/commit-standards/SKILL.md +2 -0
  132. package/bundled/locales/zh-TW/skills/contract-test-assistant/SKILL.md +2 -1
  133. package/bundled/locales/zh-TW/skills/dev-methodology/SKILL.md +2 -0
  134. package/bundled/locales/zh-TW/skills/dev-workflow-guide/SKILL.md +1 -1
  135. package/bundled/locales/zh-TW/skills/knowledge-graph/guide.md +2 -2
  136. package/bundled/locales/zh-TW/skills/migration-assistant/SKILL.md +1 -1
  137. package/bundled/locales/zh-TW/skills/observability-assistant/SKILL.md +1 -0
  138. package/bundled/locales/zh-TW/skills/project-discovery/SKILL.md +1 -0
  139. package/bundled/locales/zh-TW/skills/project-structure-guide/SKILL.md +1 -0
  140. package/bundled/locales/zh-TW/skills/release-standards/SKILL.md +3 -0
  141. package/bundled/locales/zh-TW/skills/requirement-assistant/SKILL.md +2 -0
  142. package/bundled/locales/zh-TW/skills/reverse-engineer/SKILL.md +3 -0
  143. package/bundled/locales/zh-TW/skills/reverse-engineer/tdd-analysis.md +13 -23
  144. package/bundled/locales/zh-TW/skills/runbook-assistant/SKILL.md +1 -0
  145. package/bundled/locales/zh-TW/skills/slo-assistant/SKILL.md +1 -0
  146. package/bundled/locales/zh-TW/skills/tdd-assistant/SKILL.md +2 -0
  147. package/bundled/locales/zh-TW/skills/workflows/README.md +2 -11
  148. package/bundled/skills/agents/README.md +1 -1
  149. package/bundled/skills/atdd-assistant/SKILL.md +2 -0
  150. package/bundled/skills/bdd-assistant/SKILL.md +2 -0
  151. package/bundled/skills/brainstorm-assistant/SKILL.md +31 -13
  152. package/bundled/skills/brainstorm-assistant/guide.md +9 -6
  153. package/bundled/skills/code-review-assistant/SKILL.md +1 -0
  154. package/bundled/skills/commands/brainstorm.md +12 -9
  155. package/bundled/skills/commands/config.md +0 -1
  156. package/bundled/skills/commands/init.md +2 -3
  157. package/bundled/skills/commit-standards/SKILL.md +2 -0
  158. package/bundled/skills/contract-test-assistant/SKILL.md +1 -0
  159. package/bundled/skills/dev-methodology/SKILL.md +4 -0
  160. package/bundled/skills/observability-assistant/SKILL.md +1 -0
  161. package/bundled/skills/project-discovery/SKILL.md +1 -0
  162. package/bundled/skills/project-structure-guide/SKILL.md +1 -0
  163. package/bundled/skills/release-standards/SKILL.md +3 -0
  164. package/bundled/skills/requirement-assistant/SKILL.md +2 -0
  165. package/bundled/skills/reverse-engineer/SKILL.md +3 -0
  166. package/bundled/skills/reverse-engineer/tdd-analysis.md +16 -23
  167. package/bundled/skills/runbook-assistant/SKILL.md +1 -0
  168. package/bundled/skills/slo-assistant/SKILL.md +1 -0
  169. package/bundled/skills/tdd-assistant/SKILL.md +2 -0
  170. package/bundled/skills/workflows/README.md +2 -11
  171. package/bundled/templates/.ai-context.yaml.template +194 -0
  172. package/bundled/templates/CLAUDE.md.template +145 -0
  173. package/bundled/templates/DESIGN.md +237 -0
  174. package/bundled/templates/SKILL-BRIEF-TEMPLATE.md +57 -0
  175. package/bundled/templates/SKILL-CANDIDATES.md +39 -0
  176. package/bundled/templates/gates/check-error-exit.mjs +309 -0
  177. package/bundled/templates/mcp-config.json +10 -0
  178. package/bundled/templates/methodology-template.yaml +209 -0
  179. package/bundled/templates/migration-template.md +408 -0
  180. package/bundled/templates/requirement-checklist.md +410 -0
  181. package/bundled/templates/requirement-document-template.md +591 -0
  182. package/bundled/templates/requirement-template.md +881 -0
  183. package/bundled/templates/reverse-spec-template.md +409 -0
  184. package/bundled/templates/test-case-template.md +74 -0
  185. package/bundled/templates/test-plan-template.md +74 -0
  186. package/package.json +9 -5
  187. package/src/commands/audit.js +82 -0
  188. package/src/commands/check.js +66 -10
  189. package/src/commands/init.js +161 -16
  190. package/src/commands/lint.js +96 -0
  191. package/src/commands/quickstart.js +16 -13
  192. package/src/commands/update.js +286 -14
  193. package/src/compilers/claude-code-compiler.js +4 -1
  194. package/src/config/ai-agent-paths.js +62 -17
  195. package/src/core/constants.js +42 -11
  196. package/src/core/manifest.js +201 -3
  197. package/src/core/paths.js +2 -2
  198. package/src/i18n/messages.js +9 -32
  199. package/src/installers/hooks-installer.js +167 -75
  200. package/src/installers/integration-installer.js +9 -5
  201. package/src/prompts/init.js +14 -14
  202. package/src/reconciler/actual-state-scanner.js +14 -3
  203. package/src/utils/detector.js +21 -1
  204. package/src/utils/effect-boundary.js +1093 -0
  205. package/src/utils/hasher.js +229 -9
  206. package/src/utils/hook-stats.js +1 -1
  207. package/src/utils/integration-generator.js +100 -4
  208. package/src/utils/reference-sync.js +4 -1
  209. package/src/utils/skills-installer.js +17 -3
  210. package/src/utils/spec-linter.js +35 -76
  211. package/src/utils/yaml-generator.js +51 -9
  212. package/standards-registry.json +31 -8
  213. package/src/commands/sync.js +0 -133
@@ -1,7 +1,7 @@
1
1
  # UDS 功能參考手冊
2
2
 
3
3
  > Universal Development Standards - 完整功能文件
4
- > Auto-generated | Last updated: 2026-08-17
4
+ > Auto-generated | Last updated: 2026-09-14
5
5
 
6
6
  **Language**: [English](../../../docs/reference/FEATURE-REFERENCE.md) | 繁體中文 | [简体中文](../../zh-CN/docs/FEATURE-REFERENCE.md)
7
7
 
@@ -9,15 +9,15 @@
9
9
 
10
10
  ## 目錄
11
11
 
12
- 1. [CLI 指令](#cli-commands) (9)
12
+ 1. [CLI 指令](#cli-commands) (23)
13
13
  2. [斜線命令](#slash-commands) (51)
14
14
  3. [技能](#skills) (55)
15
15
  4. [代理](#agents) (5)
16
16
  5. [工作流程](#workflows) (5)
17
- 6. [核心規範](#core-standards) (150)
18
- 7. [腳本](#scripts) (54)
17
+ 6. [核心規範](#core-standards) (152)
18
+ 7. [腳本](#scripts) (59)
19
19
 
20
- **Total Features: 329**
20
+ **Total Features: 350**
21
21
 
22
22
  ---
23
23
 
@@ -49,18 +49,31 @@
49
49
  | `--framework` | Framework extension (fat-free) |
50
50
  | `--locale` | Locale extension (zh-tw) |
51
51
  | `--skills-location` | Skills location (marketplace, user, project, none) [default: marketplace] |
52
- | `--content-mode` | Content mode for integration files (minimal, index, full) [default: index] |
52
+ | `--content-mode` | Content mode for integration files (minimal, index) [default: index]; full is retired and resolves to index |
53
53
  | `--agents-md` | Generate AGENTS.md universal summary |
54
54
  | `--no-agents-md` | Skip AGENTS.md generation |
55
- | `--with-hooks` | Install enforcement hooks (commit-msg, security, logging) |
55
+ | `--with-hooks` | Install enforcement hooks declared by the installed standards |
56
56
  | `--content-layout` | Content layout (flat, layered) [default: flat] |
57
57
  | `-y, --yes` | Use defaults, skip interactive prompts |
58
58
  | `-E, --experimental` | Enable experimental features (methodology) |
59
59
  | `--force` | Bypass UDS source-repo self-adoption guard (DEC-044 / XSPEC-071) |
60
60
 
61
+ ### `uds config`
62
+
63
+ **說明**: Manage UDS configuration and project settings
64
+
65
+ ### `uds hitl`
66
+
67
+ **說明**: Human-in-the-Loop controls
68
+
69
+ **選項**:
70
+ | Option | 說明 |
71
+ |--------|-------------|
72
+ | `--op` | Operation description |
73
+
61
74
  ### `uds configure`
62
75
 
63
- **說明**: Modify options for initialized project
76
+ **說明**: Alias for "uds config" — Modify project settings
64
77
 
65
78
  **選項**:
66
79
  | Option | 說明 |
@@ -73,7 +86,7 @@
73
86
 
74
87
  ### `uds check`
75
88
 
76
- **說明**: Check adoption status of current project
89
+ **說明**: Check file integrity and adoption status (quick validation). For deep health diagnosis, use "uds audit"
77
90
 
78
91
  **選項**:
79
92
  | Option | 說明 |
@@ -91,6 +104,36 @@
91
104
  | `--force` | Bypass UDS source-repo self-adoption guard (DEC-044 / XSPEC-071) |
92
105
  | `--i18n` | Run i18n lint rules (XSPEC-239) across canonical + locale variants |
93
106
 
107
+ ### `uds lint`
108
+
109
+ **說明**: Check spec dependency validity and size against installed specs (specs/*.md)
110
+
111
+ **選項**:
112
+ | Option | 說明 |
113
+ |--------|-------------|
114
+ | `--json` | Output result in JSON format |
115
+
116
+ ### `uds simulate`
117
+
118
+ **說明**: Simulate a standard check with input (Predictive Validation)
119
+
120
+ **選項**:
121
+ | Option | 說明 |
122
+ |--------|-------------|
123
+ | `-s, --standard` | Standard to simulate against |
124
+ | `-i, --input` | Input string to test |
125
+ | `--json` | Output result in JSON format |
126
+
127
+ ### `uds fix`
128
+
129
+ **說明**: Auto-fix standard violations (Self-Healing)
130
+
131
+ **選項**:
132
+ | Option | 說明 |
133
+ |--------|-------------|
134
+ | `-s, --standard` | Standard to fix |
135
+ | `--json` | Output result in JSON format |
136
+
94
137
  ### `uds update`
95
138
 
96
139
  **說明**: Update standards to latest version
@@ -110,6 +153,7 @@
110
153
  | `--plan` | Show reconciliation plan without executing (like terraform plan); combines with --skills/--commands to plan just that scope, still writing nothing |
111
154
  | `--apply` | Apply exactly the plan --plan prints (plain `uds update` does not); with --skills/--commands it does the reconciliation AND that scope, not only the scope |
112
155
  | `--force` | Force update all files, ignoring hash comparison |
156
+ | `--prune` | Delete .standards/ files UDS wrote but no longer ships (listed without this flag; never touches files UDS did not write) |
113
157
  | `--rollback` | Rollback to the most recent backup |
114
158
  | `--locale` | Override locale for skills install (zh-tw, zh-cn, en); also reads .uds/install.yaml + UDS_LOCALE env |
115
159
 
@@ -117,9 +161,102 @@
117
161
 
118
162
  **說明**: List installed Claude Code skills
119
163
 
164
+ ### `uds audit`
165
+
166
+ **說明**: Deep health diagnosis with pattern detection and feedback (strategic). For quick file check, use "uds check"
167
+
168
+ **選項**:
169
+ | Option | 說明 |
170
+ |--------|-------------|
171
+ | `--health` | Health check only |
172
+ | `--patterns` | Pattern detection only |
173
+ | `--friction` | Friction detection only |
174
+ | `--report` | Interactive feedback submission |
175
+ | `--yes` | Submit all findings without interactive selection (CI / non-TTY) |
176
+ | `--dry-run` | Preview report without submitting |
177
+ | `--gh` | Force gh CLI for submission |
178
+ | `--format` | Output format (json) |
179
+ | `--quiet` | Summary only |
180
+ | `--score` | Run multi-dimensional health score analysis |
181
+ | `--self` | Self mode: analyze UDS repo itself (use with --score) |
182
+ | `--save` | Save score snapshot for trend tracking (use with --score) |
183
+ | `--trend` | Show historical score trend (use with --score) |
184
+ | `--ci` | CI mode: output score only, exit 1 if below threshold (use with --score) |
185
+ | `--threshold` | Score threshold for CI mode (default: 75) |
186
+ | `--effects` | Static effect boundary gate: do the implementations of each declared effect interface reach anything outside this process |
187
+ | `--effects-config` | Path to the effect-family config (default: .uds/effect-boundary.json) |
188
+
189
+ ### `uds deps`
190
+
191
+ **說明**: Compare the versions you test against the versions your declared ranges resolve to
192
+
193
+ **選項**:
194
+ | Option | 說明 |
195
+ |--------|-------------|
196
+ | `--path` | Directory containing package.json (default: cwd) |
197
+ | `--json` | Output raw JSON |
198
+ | `--concurrency` | Parallel registry lookups (default: 8) |
199
+
200
+ ### `uds uninstall`
201
+
202
+ **說明**: Remove UDS standards, integrations, skills, and hooks
203
+
204
+ **選項**:
205
+ | Option | 說明 |
206
+ |--------|-------------|
207
+ | `--all` | Remove everything including user-level installations |
208
+ | `--standards-only` | Remove only .standards/ directory |
209
+ | `--skills-only` | Remove only skills and commands |
210
+ | `--integrations-only` | Remove only UDS blocks from integration files |
211
+ | `--dry-run` | Preview mode, no files modified |
212
+ | `-y, --yes` | Skip confirmation prompts |
213
+
214
+ ### `uds compile`
215
+
216
+ **說明**: Compile enforcement standards into hook configurations
217
+
218
+ **選項**:
219
+ | Option | 說明 |
220
+ |--------|-------------|
221
+ | `--target` | Target platform (claude-code) |
222
+ | `--dry-run` | Preview output without writing files |
223
+
224
+ ### `uds report`
225
+
226
+ **說明**: Analyze hook telemetry and show adoption report
227
+
228
+ ### `uds release`
229
+
230
+ **說明**: Manage release process (promote, deploy, manifest, verify)
231
+
232
+ ### `uds spec`
233
+
234
+ **說明**: Manage lightweight micro-specs for vibe coding. For full spec lifecycle with review, use "/sdd"
235
+
236
+ **選項**:
237
+ | Option | 說明 |
238
+ |--------|-------------|
239
+ | `-s, --scope` | Scope (frontend, backend, fullstack) |
240
+ | `-o, --output` | Output directory (default: specs/) |
241
+ | `-y, --yes` | Auto-confirm without prompting |
242
+ | `--status` | Filter by status (draft, confirmed, archived) |
243
+ | `-o, --output` | Specs directory (default: specs/) |
244
+ | `-o, --output` | Specs directory (default: specs/) |
245
+ | `-o, --output` | Specs directory (default: specs/) |
246
+ | `-o, --output` | Specs directory (default: specs/) |
247
+ | `-y, --yes` | Skip confirmation |
248
+ | `-o, --output` | Specs directory (default: specs/) |
249
+ | `--archived` | Search only archived specs |
250
+ | `-o, --output` | Specs directory |
251
+ | `-o, --output` | Specs directory |
252
+
253
+ ### `uds quickstart`
254
+
255
+ **說明**: Interactive workflow guide — find the right commands quickly
256
+
120
257
  ### `uds agent`
121
258
 
122
- **說明**: Manage UDS agents (list, install, info)
259
+ **說明**: Manage UDS agents for AI tools
123
260
 
124
261
  **選項**:
125
262
  | Option | 說明 |
@@ -129,13 +266,17 @@
129
266
  | `-g, --global` | Install to user level instead of project level |
130
267
  | `-y, --yes` | Skip confirmation prompts |
131
268
 
132
- ### `uds workflow`
269
+ ### `uds ai-context`
133
270
 
134
- **說明**: Manage UDS workflows (list, install, info, execute, status)
271
+ **說明**: Manage .ai-context.yaml configuration for AI-friendly architecture
135
272
 
136
- ### `uds ai-context`
273
+ ### `uds mcp`
274
+
275
+ **說明**: MCP server commands for AI tool integration
276
+
277
+ ### `uds run`
137
278
 
138
- **說明**: Manage AI context configuration (init, validate, graph)
279
+ **說明**: Run a project command by intent (test/lint/build/security) via uds.project.yaml
139
280
 
140
281
  ---
141
282
 
@@ -287,10 +428,10 @@
287
428
 
288
429
  | Standard | 版本 | 說明 |
289
430
  |----------|---------|-------------|
290
- | `acceptance-criteria-traceability` | 1.1.0 | |
431
+ | `acceptance-criteria-traceability` | 1.2.0 | |
291
432
  | `acceptance-test-driven-development` | 1.1.0 | |
292
433
  | `accessibility-standards` | 1.1.0 | This standard defines comprehensive guidelines for creating accessible software |
293
- | `adr-standards` | 1.0.0 | Architecture Decision Records capture the context, options, and rationale behind |
434
+ | `adr-standards` | 1.1.0 | Architecture Decision Records capture the context, options, and rationale behind |
294
435
  | `adversarial-test` | - | |
295
436
  | `agent-behavior-discipline` | 1.0.0 | This standard defines four behavioral disciplines for AI agents that elevate per |
296
437
  | `agent-communication-protocol` | 1.0.0 | Define a unified communication protocol for AI agents across the AsiaOstrich pro |
@@ -298,7 +439,7 @@
298
439
  | `ai-agreement-standards` | 1.0.0 | This standard formalizes the interaction between Human (Acquirer) and AI (Suppli |
299
440
  | `ai-command-behavior` | 1.0.0 | This standard defines a structure for specifying AI Agent runtime behavior in co |
300
441
  | `ai-friendly-architecture` | 1.0.0 | This standard defines architecture and documentation practices that maximize the |
301
- | `ai-instruction-standards` | 1.1.0 | This standard defines best practices for creating and maintaining AI instruction |
442
+ | `ai-instruction-standards` | 1.1.1 | This standard defines best practices for creating and maintaining AI instruction |
302
443
  | `ai-response-navigation` | 1.3.0 | This standard defines navigation behavior for AI responses: every substantive AI |
303
444
  | `alerting-standards` | 1.0.0 | |
304
445
  | `anti-hallucination` | 1.5.1 | This standard defines strict guidelines for AI assistants to prevent hallucinati |
@@ -318,7 +459,7 @@
318
459
  | `checkin-standards` | 1.8.0 | This standard defines quality gates that MUST be passed before committing code t |
319
460
  | `circuit-breaker` | - | |
320
461
  | `class-level-fix` | 1.1.0 | A defect is almost never alone. It is one member of a set — one flag in a dispat |
321
- | `code-review-checklist` | 1.4.0 | This standard provides a comprehensive checklist for reviewing code changes, ens |
462
+ | `code-review-checklist` | 1.5.0 | This standard provides a comprehensive checklist for reviewing code changes, ens |
322
463
  | `commit-message-guide` | 1.3.0 | Standardized commit messages improve code review efficiency, facilitate automate |
323
464
  | `container-image-standards` | 1.0.0 | **Status**: Active | **Updated**: 2026-06-17 | |
324
465
  | `container-security` | - | |
@@ -331,6 +472,7 @@
331
472
  | `data-migration-testing` | - | |
332
473
  | `data-pipeline` | 1.0.0 | **Status**: Active | **Updated**: 2026-06-17 | |
333
474
  | `database-standards` | 1.0.0 | This standard defines guidelines for database design, querying, migration, and o |
475
+ | `deferred-item-exit` | 1.0.0 | Several standards require documents that **produce deferred items** — an ADR's a |
334
476
  | `deployment-standards` | 1.1.0 | This standard defines guidelines for safely deploying software to production, co |
335
477
  | `deprecation-standards` | 1.1.0 | |
336
478
  | `design-document-standards` | 1.0.0 | |
@@ -345,7 +487,7 @@
345
487
  | `estimation-standards` | 1.0.0 | |
346
488
  | `execution-history` | 1.0.0 | |
347
489
  | `failure-source-taxonomy` | - | |
348
- | `feature-discovery-standards` | 1.0.0 | **Status**: Active | **Updated**: 2026-05-13 | |
490
+ | `feature-discovery-standards` | 1.1.0 | **Status**: Active | **Updated**: 2026-08-24 | |
349
491
  | `feature-flag-standards` | 1.0.0 | |
350
492
  | `feature-manifest-standard` | - | |
351
493
  | `flaky-test-management` | - | |
@@ -355,7 +497,7 @@
355
497
  | `full-coverage-testing` | - | |
356
498
  | `git-workflow` | 1.4.0 | This standard defines Git branching strategies and workflows to ensure consisten |
357
499
  | `git-worktree` | 1.1.0 | Define a lifecycle for using Git worktrees to isolate development work, ensuring |
358
- | `governance-layer` | 1.0.0 | A governance layer provides a shared anchor for all agents and roles in a projec |
500
+ | `governance-layer` | 1.1.0 | A governance layer provides a shared anchor for all agents and roles in a projec |
359
501
  | `health-check-standards` | - | |
360
502
  | `iac-design-principles` | 1.0.0 | **Status**: Active | **Updated**: 2026-06-17 | |
361
503
  | `immutability-first` | - | |
@@ -394,9 +536,9 @@
394
536
  | `replay-test` | - | |
395
537
  | `requirement-engineering` | 1.1.0 | |
396
538
  | `resource-cost-boundary` | 1.0.0 | **Status**: Active | **Updated**: 2026-06-17 | |
397
- | `retrospective-standards` | 1.0.0 | Retrospectives are structured team reflections that identify what worked well, w |
539
+ | `retrospective-standards` | 1.1.0 | Retrospectives are structured team reflections that identify what worked well, w |
398
540
  | `retry-standards` | - | |
399
- | `reverse-engineering-standards` | 1.2.0 | This standard defines the principles, workflows, and best practices for reverse |
541
+ | `reverse-engineering-standards` | 1.3.0 | This standard defines the principles, workflows, and best practices for reverse |
400
542
  | `rollback-standards` | - | |
401
543
  | `runbook-standards` | 1.0.0 | |
402
544
  | `runbook` | 1.0.0 | **Status**: Active | **Updated**: 2026-06-17 | |
@@ -413,14 +555,14 @@
413
555
  | `slo-sli` | 1.0.0 | **Status**: Active | **Updated**: 2026-06-17 | |
414
556
  | `slo-standards` | 1.0.0 | |
415
557
  | `smoke-test` | - | |
416
- | `spec-driven-development` | 2.4.0 | |
558
+ | `spec-driven-development` | 2.5.0 | |
417
559
  | `standard-admission-criteria` | - | |
418
560
  | `standard-lifecycle-management` | - | |
419
561
  | `structured-task-definition` | 1.0.0 | |
420
562
  | `supply-chain-attestation` | - | |
421
563
  | `supply-chain-security-standards` | 1.1.0 | |
422
564
  | `systematic-debugging` | 1.0.0 | Define a structured, four-phase debugging workflow that prevents the common anti |
423
- | `tech-debt-standards` | 1.0.0 | |
565
+ | `tech-debt-standards` | 1.1.0 | |
424
566
  | `test-completeness-dimensions` | 1.1.0 | This document defines a systematic framework for evaluating test completeness. I |
425
567
  | `test-data-standards` | 1.0.0 | |
426
568
  | `test-driven-development` | 1.2.0 | |
@@ -429,6 +571,7 @@
429
571
  | `timeout-standards` | - | |
430
572
  | `token-budget` | - | |
431
573
  | `translation-lifecycle-standards` | 1.0.1 | Translation lifecycle standards: MISSING vs OUTDATED distinction, semver-aware s |
574
+ | `turn-completion-integrity` | 1.3.0 | An agent writes *"I'll do X next"* and then ends the turn without doing X. |
432
575
  | `user-journey-testing` | - | |
433
576
  | `user-story-mapping` | 1.0.0 | **Status**: Active | **Updated**: 2026-06-17 | |
434
577
  | `verification-evidence` | 1.3.0 | Establish an "Iron Law" that no task can be claimed as complete without verifica |
@@ -452,6 +595,7 @@
452
595
  | `check-ai-agent-sync.ps1` | Check Ai Agent Sync |
453
596
  | `check-ai-agent-sync.sh` | AI Agent Sync Checker |
454
597
  | `check-ai-yaml-parses.mjs` | Every shipped .ai.yaml must parse, and must parse into what it says. |
598
+ | `check-bump-sync-roundtrip.mjs` | check-bump-sync-roundtrip — 測「跑完 bump 之後 check 必須通過」這個不變量。 |
455
599
  | `check-cli-docs-sync.ps1` | Check Cli Docs Sync |
456
600
  | `check-cli-docs-sync.sh` | CLI-to-Documentation Sync Checker |
457
601
  | `check-commands-sync.ps1` | Check Commands Sync |
@@ -461,6 +605,7 @@
461
605
  | `check-docs-integrity.sh` | Documentation Integrity Checker |
462
606
  | `check-docs-sync.ps1` | Check Docs Sync |
463
607
  | `check-docs-sync.sh` | Documentation Sync Checker |
608
+ | `check-error-exit.mjs` | 🔴 沒填就是沒設定,而沒設定會 exit 2, |
464
609
  | `check-external-references.mjs` | External Reference Checker (SPEC-SELFDIAG-001 REQ-5, AC-7) |
465
610
  | `check-orphan-specs.ps1` | Check Orphan Specs |
466
611
  | `check-orphan-specs.sh` | Orphan Spec Detection Script |
@@ -474,6 +619,7 @@
474
619
  | `check-standards-reference-sync.sh` | check-standards-reference-sync.sh |
475
620
  | `check-standards-sync.ps1` | Check Standards Sync |
476
621
  | `check-standards-sync.sh` | Standards Consistency Checker |
622
+ | `check-translation-hash-ratchet.sh` | XSPEC-392 R6 棘輪:新的翻譯必須帶 source_hash,既有的欠債冷凍為基線。 |
477
623
  | `check-translation-sync.ps1` | Check Translation Sync |
478
624
  | `check-translation-sync.sh` | Translation Sync Checker |
479
625
  | `check-usage-docs-sync.ps1` | Check if usage documentation needs to be regenerated |
@@ -485,7 +631,9 @@
485
631
  | `convert-md-to-yaml.mjs` | Markdown to AI-YAML Conversion Script |
486
632
  | `fix-manifest-paths.ps1` | Fix Manifest Paths |
487
633
  | `fix-manifest-paths.sh` | Manifest Path Fixer |
634
+ | `generate-adoption-skills.mjs` | Self-Adoption Skill Copy Generator and Drift Gate — XSPEC-385 |
488
635
  | `generate-docs.mjs` | Look up the release date for `version` from CHANGELOG.md's own |
636
+ | `generate-llms-txt.mjs` | llms.txt Generator and Drift Gate — XSPEC-385 |
489
637
  | `generate-locale-coverage.mjs` | Locale Coverage Generator |
490
638
  | `generate-version-manifest.mjs` | Generate Version Manifest (SPEC-SELFDIAG-001 REQ-9, AC-14) |
491
639
  | `install-hooks.mjs` | Install Hooks |
@@ -58,7 +58,6 @@ status: current
58
58
 
59
59
  **配置方式**:
60
60
  - 安裝時選擇 `standardsScope: full` + Skills 安裝
61
- - 或透過 `contentMode: full` 獲得完整規範
62
61
 
63
62
  **包含內容**:
64
63
  - 16 個 Claude Code Skills
@@ -212,7 +211,7 @@ uds init -y --skills-location marketplace --content-mode index
212
211
 
213
212
  **配置方式**:
214
213
  ```bash
215
- uds init -y --skills-location none --content-mode full
214
+ uds init -y --skills-location none --content-mode index
216
215
  ```
217
216
 
218
217
  ### 場景 4:學習 UDS 標準體系
@@ -1,5 +1,5 @@
1
1
  ---
2
- source: ../../../../integrations/google-antigravity/INSTRUCTIONS.md
2
+ source: ../../../../integrations/google-antigravity/AGENTS.md
3
3
  source_version: 1.0.0
4
4
  translation_version: 1.0.0
5
5
  last_synced: 2026-01-13
@@ -19,7 +19,7 @@ Google Antigravity 是一個先進的代理程式碼開發助理。此整合協
19
19
  - **[.antigravity/rules.md](../../../../integrations/google-antigravity/.antigravity/rules.md)**(推薦):
20
20
  專案級規則檔,Antigravity 會自動載入。
21
21
 
22
- - **[INSTRUCTIONS.md](./INSTRUCTIONS.md)**:
22
+ - **[AGENTS.md](./AGENTS.md)**:
23
23
  用於手動配置的系統提示詞片段。
24
24
 
25
25
  ## 規則配置
@@ -53,7 +53,7 @@ curl -o .antigravity/rules.md https://raw.githubusercontent.com/AsiaOstrich/univ
53
53
  確保 `core/` 規範已複製到您的專案(例如 `.standards/`)。
54
54
 
55
55
  2. **配置代理**:
56
- 將 `INSTRUCTIONS.md` 的內容複製到您的 Antigravity「使用者規則」或特定任務指令中。
56
+ 將 `AGENTS.md` 的內容複製到您的 Antigravity「使用者規則」或特定任務指令中。
57
57
 
58
58
  ### 驗證合規性
59
59
 
@@ -65,7 +65,7 @@ curl -o .antigravity/rules.md https://raw.githubusercontent.com/AsiaOstrich/univ
65
65
 
66
66
  - [防幻覺標準](../../core/anti-hallucination.md)
67
67
  - [Commit 訊息指南](../../core/commit-message-guide.md)
68
- - [INSTRUCTIONS.md](./INSTRUCTIONS.md)
68
+ - [AGENTS.md](./AGENTS.md)
69
69
 
70
70
  ---
71
71
 
@@ -2,7 +2,7 @@
2
2
  name: adr-assistant
3
3
  source: ../../../../skills/adr-assistant/SKILL.md
4
4
  source_version: 1.0.0
5
- source_hash: 7d8bf5944cf4
5
+ source_hash: a5c79c6a04fe
6
6
  translation_version: 1.1.0
7
7
  last_synced: 2026-08-17
8
8
  status: current
@@ -153,7 +153,7 @@ uds agent list
153
153
  uds agent install code-architect
154
154
 
155
155
  # 安裝所有代理
156
- uds agent install --all
156
+ uds agent install all
157
157
 
158
158
  # 安裝到使用者目錄(全域)
159
159
  uds agent install code-architect --global
@@ -80,5 +80,7 @@ So that [benefit].
80
80
 
81
81
  ## 參考
82
82
 
83
+ - [驗收標準撰寫指南](./acceptance-criteria-guide.md) — 要撰寫或審查驗收標準時讀它。
84
+ - [ATDD 工作流程指南](./atdd-workflow.md) — 要完整跑一輪 ATDD 循環時讀它。
83
85
  - 詳細指南:[guide.md](./guide.md)
84
86
  - 核心規範:[acceptance-test-driven-development.md](../../../../core/acceptance-test-driven-development.md)
@@ -77,5 +77,7 @@ Feature: User Login
77
77
 
78
78
  ## 參考
79
79
 
80
+ - [BDD 工作流程指南](./bdd-workflow.md) — 要把探索、制定、自動化當一個循環跑時讀它。
81
+ - [Gherkin 快速參考指南](./gherkin-guide.md) — 要寫 Given/When/Then 而需要確切語法時讀它。
80
82
  - 詳細指南:[guide.md](./guide.md)
81
83
  - 核心規範:[behavior-driven-development.md](../../../../core/behavior-driven-development.md)
@@ -1,10 +1,10 @@
1
1
  ---
2
2
  name: brainstorm-assistant
3
3
  source: ../../../../skills/brainstorm-assistant/SKILL.md
4
- source_version: 4.1.0
5
- source_hash: 711404f2c4af
6
- translation_version: 4.2.0
7
- last_synced: 2026-08-17
4
+ source_version: 4.2.0
5
+ source_hash: 02e63146c84e
6
+ translation_version: 4.3.0
7
+ last_synced: 2026-08-24
8
8
  status: current
9
9
  description: |
10
10
  [UDS] 在規格出現之前執行的結構化多角色腦力激盪,並附帶評分品質關卡。
@@ -26,6 +26,10 @@ description: |
26
26
 
27
27
  **v4 的核心改動:** v3 提供了強健的*機制*,卻沒有可判定 pass/fail 的品質閘。v4 在其上疊加一道**時序化品質契約**——**腦力激盪品質標準(BQS v1)**——且不移除任何 v3 行為。BQS 是**四層 × 時間軸**結構:第 0 層宣告 explore/exploit 意圖;第 1 層(過程、leading、發散期全程可見)跑維度 **D1–D4**;第 2 層(產物、leading、收斂後僅施於推薦集,即 Agg. Score ≥ 3.5、不限筆數的想法)跑 **D5–D8** 加 Seeds 欄與爭議區;第 3 層是不受治理的 **Judgment Override**。第一原理:**決策用 leading 訊號、校準用 lagging 訊號——兩者是時間前後,而非對錯取捨。** 硬序列閘禁止 D5–D8 在發散期被揭示或評分。詳見下方「BQS v1 — 品質契約」。
28
28
 
29
+ **v4.2 的核心改動(XSPEC-388):** D4 原本只釘住判官坐在哪裡,一個字都沒說它得想得動。一個獨立 context 跑字面遵循型模型會逐字滿足舊條文,然後照 D5–D8 逐條打勾放行——與一場真的有人反對過的評審在報告上無從分辨。v4.2 給 D4 加上**第二個軸**:評審還必須宣告其**模型層級**要求(見下方術語說明)。CONVERGE 的提示改為**目標+約束**形狀——D5–D8 是判斷必須滿足的判準,不是按順序執行的步驟;既有固定句型與逐準則分數指南保留為參考格式。發散側引用 [core/model-selection.md](../../../../core/model-selection.md)(Standard 或更高)而不另立規則。不移除任何 v3 機制。
30
+
31
+ > **術語——「模型層級」,不用「tier」:** 在本 skill 內,`tier` 已被佔用兩次——BQS 分級表(套用哪些維度)與 Enhanced Tier。[core/model-selection.md](../../../../core/model-selection.md) 定義的模型能力軸(該標準稱 *model tier*)在本 skill 一律寫作**模型層級(model level)**。模型層級是該標準的**廠商中立標籤**;本 skill 絕不指名具體廠商模型(見 D4)。
32
+
29
33
  ## 使用前先選模式
30
34
 
31
35
  使用前套用以下**客觀觸發條件**。預設為完整 v3,路由規則是跳過階段的快捷鍵,而非額外障礙。
@@ -68,7 +72,7 @@ BQS 是**四層 × 時間軸**契約。它是 v3 的**疊加**——所有 v3
68
72
  | **D1 框架純度** | 問題內嵌特定方案或「像 X 給 Y」→fail;須 5-Whys 到根因 |
69
73
  | **D2 發散覆蓋** | 存活想法跨 <3 獨立 persona/透鏡→fail(受第 0 層權重調節);連一輪零新增才算飽和 |
70
74
  | **D3 跨會話多樣性** | 種子是競品類比→fail;Top 全來自單一 lens→fail |
71
- | **D4 評估去偏** | 須 ≥3 評審 + 硬角色 Devil's Advocate + Steelman;**pass 須在獨立 context 執行**,否則標 `[degraded]` 不得標 pass |
75
+ | **D4 評估去偏** | 須 ≥3 評審 + 硬角色 Devil's Advocate + Steelman;**pass 須同時滿足兩軸**:(1) 獨立 context,**且** (2) 以 [model-selection](../../../../core/model-selection.md) 的廠商中立標籤宣告**模型層級**要求——指名具體廠商模型即違規。缺任一軸→標 `[degraded]` 不得標 pass |
72
76
 
73
77
  > **硬序列閘:** D5–D8 禁止在發散期揭示或評分;CONVERGE 的 critic 不得在**最後一個 persona** 產完前被呼叫。
74
78
 
@@ -92,7 +96,7 @@ BQS 是**四層 × 時間軸**契約。它是 v3 的**疊加**——所有 v3
92
96
  ### 結構規則
93
97
 
94
98
  1. **Meta 停止規則:** 該層維度全綠 **且** 再跑一輪後 **推薦集成員不變**(看集合成員、不看內部排序)→停。**硬上限 2 輪**。取代模糊的「不翻決策」。
95
- 2. **判官≠產生者:** D2/D4/D5/D7 判定須獨立視角;單 context 自評只能 `[degraded]`,不得 pass。
99
+ 2. **判官≠產生者:** D2/D4/D5/D7 判定須獨立視角;單 context 自評只能 `[degraded]`,不得 pass。D4 另需宣告模型層級——獨立性只是它兩軸之一(見 D4)。
96
100
  3. **校準回路(吃 lagging):** v3 的三個工作階段自評指標收編為此回路 **lagging** 端——**Adoption Rate=D6 滯後驗證、Diversity=D2/D3 滯後觀測、Cognitive Load=成本約束**;**禁兩套平行評估**。
97
101
  4. **BQS 自我演化(輕量):** 版本化 + 證據清單 last-reviewed 逾期 flag;「定期對 BQS 自身 brainstorm」列可選。
98
102
  5. **最小充分原則:** 套用該 tier 所需的最少維度 + 把第 2 層限縮在推薦集(Agg. Score ≥ 3.5),而非全部發散想法——認知經濟性的守門,不另設成本維度。
@@ -149,6 +153,8 @@ BQS 是**四層 × 時間軸**契約。它是 v3 的**疊加**——所有 v3
149
153
 
150
154
  > **v3 核心機制:** **persona 集成**——每個 persona 以**思維鏈**在**隔離**狀態下推理——再乘上**多樣性透鏡**。Meincke、Mollick、Terwiesch(2024)發現「思維鏈 + persona」的想法多樣性高於所有受測提示策略,接近人類團體。光衝數量是弱代理;結構性逼出不同視角才是真正槓桿。
151
155
 
156
+ > **模型層級(發散側):** 發散提示只給目標與約束——正是 core/model-selection.md 的 [MS-004](../../../../core/model-selection.md#rules)/[Criterion 2](../../../../core/model-selection.md#criterion-2--specification-definiteness規格明確度) 的觸發條件:發散以 **Standard 或更高**層級執行。不是「最高層級」——那會同時超出 MS-004 所說的與我們的證據。lagging 登記:此選擇由校準回路既有的 **Diversity(D2/D3 滯後觀測)** 欄驗證,不另開第二套登記。
157
+
152
158
  #### Step 2a — persona 集成
153
159
 
154
160
  透過預設 persona 組生成想法。每個 persona **逐步推理(思維鏈)**,**只從自己的視角**產出 2–4 個想法。使用者可用 `--personas` 增減或改名。
@@ -195,9 +201,11 @@ BQS 是**四層 × 時間軸**契約。它是 v3 的**疊加**——所有 v3
195
201
 
196
202
  > **v3 核心機制:** **多評審面板**取代單一加權評分者。單一 LLM 是弱且有偏的評估者(Li 等,2025:LLM 強於生成/精煉、弱於評估——人類保留最終裁決權)。三個獨立評審透鏡各自評分後聚合。
197
203
 
204
+ > **評審提示形狀——目標+約束(v4.2):** 對面板、Devil's Advocate、Steelman 派工時——尤其派入獨立 context(`--enhanced`)——提示**必須**以**目標+其判斷必須滿足的約束**表達,不得寫成按順序執行的步驟清單。D5–D8 與下方的具體性要求是**判準**(「你的判斷必須滿足這些」),不是**步驟**(「照這個順序做這些事」)。既有固定句型、逐準則 1–5 指南與評審權重公式**保留為參考格式**,皆非必經步驟。理由:core/model-selection.md 的 [MS-009](../../../../core/model-selection.md#rules)。
205
+
198
206
  #### Step 3a: 多評審面板
199
207
 
200
- 跑**三個獨立評審**,各自以自己的透鏡對每個想法打 1–5 分;取平均聚合以降低單評審偏誤。每位評審皆套用下方加權公式。
208
+ 跑**三個獨立評審**,各自以自己的透鏡對每個想法打 1–5 分;取平均聚合以降低單評審偏誤。下方加權準則定義預設透鏡——是參考格式,不是評審必須逐步照走的腳本。
201
209
 
202
210
  | 評審透鏡 | 它所負責的加權準則 |
203
211
  |---------|-------------------|
@@ -205,7 +213,7 @@ BQS 是**四層 × 時間軸**契約。它是 v3 的**疊加**——所有 v3
205
213
  | **User impact(使用者影響)** | Impact 70% · Alignment 30% |
206
214
  | **Strategic alignment(策略一致性)** | Alignment 60% · Impact 40% |
207
215
 
208
- 各準則評分指南(1–5):Feasibility(5=輕而易舉 … 1=幾乎不可能);Impact(5=變革性 … 1=可忽略);Effort(5=數小時 … 1=數季,反向計分,工作量越低分越高);Alignment(5=核心使命 … 1=偏離使命)。
216
+ 各準則評分指南(1–5,參考格式):Feasibility(5=輕而易舉 … 1=幾乎不可能);Impact(5=變革性 … 1=可忽略);Effort(5=數小時 … 1=數季,反向計分,工作量越低分越高);Alignment(5=核心使命 … 1=偏離使命)。
209
217
 
210
218
  > **可選——RICE / ICE(產品功能):** 排序可出貨功能時用 `RICE =(Reach × Impact × Confidence)/ Effort` 或較輕的 `ICE = Impact × Confidence × Ease`。Effort 交由工程師估、不要讓 LLM 估(它無程式庫知識)。RICE 偏好漸進式勝利,別單獨用於策略性押注。
211
219
 
@@ -213,7 +221,7 @@ BQS 是**四層 × 時間軸**契約。它是 v3 的**疊加**——所有 v3
213
221
 
214
222
  軟性「請批評一下」只會得到附和(諂媚)。v3 指派**硬角色**:對**推薦集**(Agg. Score ≥ 3.5,不限筆數)中的每一個想法各跑一個 **Devil's Advocate**(「你的任務是論證此案會失敗」)與一個 **Steelman**(「說出反方最強而善意的版本」)。兩者一起壓力測試韌性,而非只是戳。
215
223
 
216
- 每個反對理由須為:「在 [具體情境] 下,此想法會失敗,因為 [具體原因]。」模糊顧慮(「這可能有點難」)不接受。
224
+ 約束:每個反對理由須指出**具體情境**與**具體原因**——模糊顧慮(「這可能有點難」)不接受。句型「在 [具體情境] 下,此想法會失敗,因為 [具體原因]」是參考格式,不是必用句式。
217
225
 
218
226
  使用者**必須**對每個給出回應才能繼續:
219
227
 
@@ -225,16 +233,17 @@ BQS 是**四層 × 時間軸**契約。它是 v3 的**疊加**——所有 v3
225
233
 
226
234
  **旗標:** `--no-rebuttal` 跳過此步驟;報告段落標注「Rebuttal: skipped」。
227
235
 
228
- > **BQS D4 — 判官≠產生者:** D4 唯有**評審/Devil's Advocate 在獨立 context 執行**(`--enhanced` 隔離 agent 宿主)才可 pass。baseline 單 context 下,面板是同 context 自評,標 `[degraded]`、**不得標 pass**——誠實但非獨立。不得把 baseline 跑當成 D4 pass 靜默通過。
236
+ > **BQS D4 — 判官≠產生者,兩軸:** D4 唯有**兩軸同時成立**才可 pass。**(1) 座位——獨立性**:評審/Devil's Advocate 在獨立 context 執行(`--enhanced` 隔離 agent 宿主)。**(2) 心智——宣告模型層級**:評審宣告其**模型層級**要求,以 [core/model-selection.md](../../../../core/model-selection.md) 的廠商中立標籤表達;選層依據為該標準的判準(引用,不複述)。指名具體廠商模型即違規——層級標籤是唯一合法的表達方式。缺任一軸→面板標 `[degraded]`、**不得標 pass**:獨立 context 跑字面遵循型模型會逐字滿足座位軸,成為一枚完全合規的橡皮圖章——認出「不同名字下的同一件事」是打勾做不到的判斷工作。baseline 單 context 下,面板是同 context 自評,標 `[degraded]`、不得 pass——誠實但非獨立。不得把 baseline 跑當成 D4 pass 靜默通過。
229
237
 
230
238
  #### Step 3c: BQS 第 2 層——對推薦集的產物閘
231
239
 
232
- 收斂後,**僅對推薦集**(Agg. Score ≥ 3.5 的想法,不限筆數)套用 **D5–D8**(絕不對全部發散想法)。若無想法達 3.5,仍保留分數最高的 1 個,標記 `[未達門檻——僅供參考]`,避免報告空白。對推薦集中每個想法:
240
+ 收斂後,**僅對推薦集**(Agg. Score ≥ 3.5 的想法,不限筆數)套用 **D5–D8**(絕不對全部發散想法)。若無想法達 3.5,仍保留分數最高的 1 個,標記 `[未達門檻——僅供參考]`,避免報告空白。D5–D8 是**判斷必須滿足的判準**——不限順序,不是程序。對推薦集中每個想法,判斷必須滿足:
233
241
 
234
242
  - **D5 接地:** 將每個主張分流為 `[現狀/外部事實]`(需 file:line 或來源,否則 fail)vs `[未來/假說]`(免接地、標 `[假說]`)。**外部事實宣稱為跨級地板**——creative 級也須接地。
235
243
  - **D6 淨值:** 推薦集中每個想法須答「解誰問題/我們真有嗎/不做的代價」;至少一個淘汰為「不值得做」;掛 **lagging 登記欄**(事後哪個訊號驗證)。
236
244
  - **D7 可證偽(二態):** 標 `[現可陳述證偽]` **或** `[需先做 X 才能定義證偽]`。後者**轉 next-step 餵 D8——不算 fail**。
237
245
  - **D8 可行動:** 每個存活想法需 next-step 裁決(含明確「暫不做」);無 → fail。
246
+ - 裁決為「暫不做」者,以及 **Seeds(來自被淘汰的想法)** 中每個被擱置的想法,皆為 [deferred-item-exit](../../../../core/deferred-item-exit.md) 所指的延後項目。
238
247
 
239
248
  > **Meta 停止規則(BQS 結構規則 1):** 當套用的維度全綠 **且** 再跑一輪後 **推薦集成員不變**(看集合成員、非內部排序)→停。**硬上限 2 輪。**
240
249
 
@@ -289,7 +298,7 @@ BQS 是**四層 × 時間軸**契約。它是 v3 的**疊加**——所有 v3
289
298
  - [ ] Proceed to `/sdd` if requirements are clear
290
299
  ```
291
300
 
292
- > **BQS 輸出新增(v4):** **Seeds** 區(規則:被殺 ≥1 則非空)、**爭議區**(高方差想法不按 mean 淘汰)、**Judgment Override** 通道(人類裁決凌駕聚合分)為 BQS 第 2/3 層所要求。Recommendations 區塊為推薦集(不限筆數)中每個想法逐項記錄 D5–D8 狀態。
301
+ > **BQS 輸出新增(v4):** **Seeds** 區(規則:被殺 ≥1 則非空)、**爭議區**(高方差想法不按 mean 淘汰)、**Judgment Override** 通道(人類裁決凌駕聚合分)為 BQS 第 2/3 層所要求。Recommendations 區塊為推薦集(不限筆數)中每個想法逐項記錄 D5–D8 狀態。自 v4.2 起,報告表頭並記錄評審宣告的**模型層級**(廠商中立標籤)——沒有它,D4 為 `[degraded]`,且宣告無處可驗。
293
302
 
294
303
  ## 多樣性崩塌防護
295
304
 
@@ -366,6 +375,7 @@ BQS 是**四層 × 時間軸**契約。它是 v3 的**疊加**——所有 v3
366
375
  ## 參考
367
376
 
368
377
  - 詳細指南:[guide.md](./guide.md)
378
+ - 模型層級依據:[core/model-selection.md](../../../../core/model-selection.md)——D4 心智軸與發散側層級皆以該標準的判準為準。**引用、不複述**——摘要會隨來源被更正而腐壞,指標不會。
369
379
 
370
380
  ## AI 代理行為
371
381