universal-dev-standards 5.3.2 → 5.5.0
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.
- package/bundled/ai/standards/adversarial-test.ai.yaml +277 -0
- package/bundled/ai/standards/agent-communication-protocol.ai.yaml +32 -166
- package/bundled/ai/standards/agent-dispatch.ai.yaml +32 -58
- package/bundled/ai/standards/audit-trail.ai.yaml +113 -0
- package/bundled/ai/standards/branch-completion.ai.yaml +34 -70
- package/bundled/ai/standards/change-batching-standards.ai.yaml +31 -180
- package/bundled/ai/standards/chaos-injection-tests.ai.yaml +91 -0
- package/bundled/ai/standards/container-image-standards.ai.yaml +88 -0
- package/bundled/ai/standards/container-security.ai.yaml +331 -0
- package/bundled/ai/standards/cost-budget-test.ai.yaml +96 -0
- package/bundled/ai/standards/data-contract.ai.yaml +110 -0
- package/bundled/ai/standards/data-migration-testing.ai.yaml +96 -0
- package/bundled/ai/standards/data-pipeline.ai.yaml +113 -0
- package/bundled/ai/standards/disaster-recovery-drill.ai.yaml +89 -0
- package/bundled/ai/standards/execution-history.ai.yaml +30 -288
- package/bundled/ai/standards/flaky-test-management.ai.yaml +89 -0
- package/bundled/ai/standards/flow-based-testing.ai.yaml +240 -0
- package/bundled/ai/standards/iac-design-principles.ai.yaml +83 -0
- package/bundled/ai/standards/incident-response.ai.yaml +107 -0
- package/bundled/ai/standards/license-compliance.ai.yaml +106 -0
- package/bundled/ai/standards/llm-output-validation.ai.yaml +269 -0
- package/bundled/ai/standards/mock-boundary.ai.yaml +250 -0
- package/bundled/ai/standards/mutation-testing.ai.yaml +192 -0
- package/bundled/ai/standards/pii-classification.ai.yaml +109 -0
- package/bundled/ai/standards/pipeline-integration-standards.ai.yaml +28 -169
- package/bundled/ai/standards/policy-as-code-testing.ai.yaml +227 -0
- package/bundled/ai/standards/prd-standards.ai.yaml +88 -0
- package/bundled/ai/standards/product-metrics-standards.ai.yaml +111 -0
- package/bundled/ai/standards/prompt-regression.ai.yaml +94 -0
- package/bundled/ai/standards/property-based-testing.ai.yaml +105 -0
- package/bundled/ai/standards/release-quality-manifest.ai.yaml +135 -0
- package/bundled/ai/standards/replay-test.ai.yaml +111 -0
- package/bundled/ai/standards/runbook.ai.yaml +104 -0
- package/bundled/ai/standards/sast-advanced.ai.yaml +135 -0
- package/bundled/ai/standards/schema-evolution.ai.yaml +111 -0
- package/bundled/ai/standards/secret-management-standards.ai.yaml +105 -0
- package/bundled/ai/standards/secure-op.ai.yaml +365 -0
- package/bundled/ai/standards/security-testing.ai.yaml +171 -0
- package/bundled/ai/standards/server-ops-security.ai.yaml +274 -0
- package/bundled/ai/standards/slo-sli.ai.yaml +97 -0
- package/bundled/ai/standards/smoke-test.ai.yaml +87 -0
- package/bundled/ai/standards/supply-chain-attestation.ai.yaml +109 -0
- package/bundled/ai/standards/test-completeness-dimensions.ai.yaml +52 -5
- package/bundled/ai/standards/user-story-mapping.ai.yaml +108 -0
- package/bundled/ai/standards/workflow-enforcement.ai.yaml +34 -240
- package/bundled/ai/standards/workflow-state-protocol.ai.yaml +31 -107
- package/bundled/core/adversarial-test.md +212 -0
- package/bundled/core/chaos-injection-tests.md +116 -0
- package/bundled/core/container-security.md +521 -0
- package/bundled/core/cost-budget-test.md +69 -0
- package/bundled/core/data-migration-testing.md +110 -0
- package/bundled/core/disaster-recovery-drill.md +73 -0
- package/bundled/core/flaky-test-management.md +73 -0
- package/bundled/core/flow-based-testing.md +142 -0
- package/bundled/core/llm-output-validation.md +178 -0
- package/bundled/core/mock-boundary.md +100 -0
- package/bundled/core/mutation-testing.md +97 -0
- package/bundled/core/policy-as-code-testing.md +188 -0
- package/bundled/core/prompt-regression.md +72 -0
- package/bundled/core/property-based-testing.md +73 -0
- package/bundled/core/release-quality-manifest.md +147 -0
- package/bundled/core/replay-test.md +86 -0
- package/bundled/core/sast-advanced.md +300 -0
- package/bundled/core/secure-op.md +314 -0
- package/bundled/core/security-testing.md +87 -0
- package/bundled/core/server-ops-security.md +493 -0
- package/bundled/core/smoke-test.md +65 -0
- package/bundled/core/supply-chain-attestation.md +117 -0
- package/bundled/locales/zh-CN/CHANGELOG.md +3 -3
- package/bundled/locales/zh-CN/README.md +1 -1
- package/bundled/locales/zh-CN/skills/ai-instruction-standards/SKILL.md +5 -5
- package/bundled/locales/zh-TW/CHANGELOG.md +3 -3
- package/bundled/locales/zh-TW/README.md +1 -1
- package/bundled/locales/zh-TW/skills/ai-instruction-standards/SKILL.md +183 -79
- package/bundled/skills/README.md +4 -3
- package/bundled/skills/SKILL_NAMING.md +94 -0
- package/bundled/skills/ai-instruction-standards/SKILL.md +181 -88
- package/bundled/skills/atdd-assistant/SKILL.md +8 -0
- package/bundled/skills/bdd-assistant/SKILL.md +7 -0
- package/bundled/skills/checkin-assistant/SKILL.md +8 -0
- package/bundled/skills/code-review-assistant/SKILL.md +7 -0
- package/bundled/skills/journey-test-assistant/SKILL.md +203 -0
- package/bundled/skills/orchestrate/SKILL.md +167 -0
- package/bundled/skills/plan/SKILL.md +234 -0
- package/bundled/skills/pr-automation-assistant/SKILL.md +8 -0
- package/bundled/skills/push/SKILL.md +49 -2
- package/bundled/skills/{process-automation → skill-builder}/SKILL.md +1 -1
- package/bundled/skills/{forward-derivation → spec-derivation}/SKILL.md +1 -1
- package/bundled/skills/spec-driven-dev/SKILL.md +7 -0
- package/bundled/skills/sweep/SKILL.md +145 -0
- package/bundled/skills/tdd-assistant/SKILL.md +7 -0
- package/package.json +1 -1
- package/src/commands/flow.js +8 -0
- package/src/commands/start.js +14 -0
- package/src/commands/sweep.js +8 -0
- package/src/commands/workflow.js +8 -0
- package/standards-registry.json +474 -12
- package/bundled/locales/zh-CN/skills/ac-coverage-assistant/SKILL.md +0 -190
- package/bundled/locales/zh-CN/skills/forward-derivation/SKILL.md +0 -71
- package/bundled/locales/zh-CN/skills/forward-derivation/guide.md +0 -130
- package/bundled/locales/zh-CN/skills/methodology-system/SKILL.md +0 -88
- package/bundled/locales/zh-CN/skills/methodology-system/create-methodology.md +0 -350
- package/bundled/locales/zh-CN/skills/methodology-system/guide.md +0 -131
- package/bundled/locales/zh-CN/skills/methodology-system/runtime.md +0 -279
- package/bundled/locales/zh-CN/skills/process-automation/SKILL.md +0 -143
- package/bundled/locales/zh-TW/skills/ac-coverage-assistant/SKILL.md +0 -195
- package/bundled/locales/zh-TW/skills/deploy-assistant/SKILL.md +0 -178
- package/bundled/locales/zh-TW/skills/forward-derivation/SKILL.md +0 -69
- package/bundled/locales/zh-TW/skills/forward-derivation/guide.md +0 -415
- package/bundled/locales/zh-TW/skills/methodology-system/SKILL.md +0 -86
- package/bundled/locales/zh-TW/skills/methodology-system/create-methodology.md +0 -350
- package/bundled/locales/zh-TW/skills/methodology-system/guide.md +0 -131
- package/bundled/locales/zh-TW/skills/methodology-system/runtime.md +0 -279
- package/bundled/locales/zh-TW/skills/process-automation/SKILL.md +0 -144
- /package/bundled/skills/{ac-coverage-assistant → ac-coverage}/SKILL.md +0 -0
- /package/bundled/skills/{methodology-system → dev-methodology}/SKILL.md +0 -0
- /package/bundled/skills/{methodology-system → dev-methodology}/create-methodology.md +0 -0
- /package/bundled/skills/{methodology-system → dev-methodology}/guide.md +0 -0
- /package/bundled/skills/{methodology-system → dev-methodology}/integrated-flow.md +0 -0
- /package/bundled/skills/{methodology-system → dev-methodology}/prerequisite-check.md +0 -0
- /package/bundled/skills/{methodology-system → dev-methodology}/runtime.md +0 -0
- /package/bundled/skills/{forward-derivation → spec-derivation}/guide.md +0 -0
|
@@ -1,8 +1,8 @@
|
|
|
1
1
|
---
|
|
2
2
|
source: ../../../../skills/ai-instruction-standards/SKILL.md
|
|
3
|
-
source_version:
|
|
4
|
-
translation_version:
|
|
5
|
-
last_synced: 2026-
|
|
3
|
+
source_version: 2.0.0
|
|
4
|
+
translation_version: 2.0.0
|
|
5
|
+
last_synced: 2026-05-05
|
|
6
6
|
status: current
|
|
7
7
|
scope: partial
|
|
8
8
|
description: |
|
|
@@ -15,8 +15,8 @@ description: |
|
|
|
15
15
|
|
|
16
16
|
> **语言**: [English](../../../../skills/ai-instruction-standards/SKILL.md) | 简体中文
|
|
17
17
|
|
|
18
|
-
**版本**:
|
|
19
|
-
**最后更新**: 2026-
|
|
18
|
+
**版本**: 2.0.0
|
|
19
|
+
**最后更新**: 2026-05-05
|
|
20
20
|
**适用范围**: Claude Code Skills
|
|
21
21
|
|
|
22
22
|
---
|
|
@@ -14,7 +14,7 @@ status: current
|
|
|
14
14
|
|
|
15
15
|
> **語言**: [English](../../README.md) | 繁體中文 | [简体中文](../zh-CN/README.md)
|
|
16
16
|
|
|
17
|
-
**版本**: 5.
|
|
17
|
+
**版本**: 5.5.0 | **發布日期**: 2026-04-13 | **授權**: [雙重授權](../../LICENSE) (CC BY 4.0 + MIT)
|
|
18
18
|
|
|
19
19
|
語言無關、框架無關的軟體專案文件標準。透過 AI 原生工作流,確保不同技術堆疊之間的一致性、品質和可維護性。
|
|
20
20
|
|
|
@@ -1,42 +1,78 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: ai-instruction-standards
|
|
3
3
|
source: ../../../../skills/ai-instruction-standards/SKILL.md
|
|
4
|
-
source_version:
|
|
5
|
-
translation_version:
|
|
6
|
-
last_synced: 2026-
|
|
4
|
+
source_version: 2.0.0
|
|
5
|
+
translation_version: 2.0.0
|
|
6
|
+
last_synced: 2026-04-28
|
|
7
7
|
status: current
|
|
8
8
|
scope: partial
|
|
9
|
-
description: "[UDS] 建立和維護 AI 指令檔案(CLAUDE.md、.
|
|
9
|
+
description: "[UDS] 建立和維護 AI 指令檔案(CLAUDE.md、AGENTS.md、.cursor/rules/ 等)並採用適當結構"
|
|
10
10
|
---
|
|
11
11
|
|
|
12
12
|
# AI 指令檔案標準指南
|
|
13
13
|
|
|
14
14
|
> **語言**: [English](../../../../skills/ai-instruction-standards/SKILL.md) | 繁體中文
|
|
15
15
|
|
|
16
|
-
**版本**:
|
|
17
|
-
**最後更新**: 2026-
|
|
18
|
-
**適用範圍**:
|
|
16
|
+
**版本**: 2.0.0
|
|
17
|
+
**最後更新**: 2026-04-28
|
|
18
|
+
**適用範圍**: 所有主流 AI 輔助編程工具
|
|
19
19
|
|
|
20
20
|
---
|
|
21
21
|
|
|
22
22
|
> **核心標準**: 本技能實作 [AI 指令檔案標準](../../core/ai-instruction-standards.md)。完整方法論文件請參閱核心標準。
|
|
23
23
|
|
|
24
|
+
## AI 技能層級
|
|
25
|
+
|
|
26
|
+
本技能是三層 AI 協作系統的一部分:
|
|
27
|
+
|
|
28
|
+
| 層級 | 技能 | 回答的問題 |
|
|
29
|
+
|------|------|-----------|
|
|
30
|
+
| **行為**(即時) | `/ai-collaboration` | 「AI 如何準確回應?」 |
|
|
31
|
+
| **配置**(Session) | `/ai-instruction-standards`(本技能) | 「CLAUDE.md / AGENTS.md 該寫什麼?」 |
|
|
32
|
+
| **架構**(長期) | `/ai-friendly-architecture` | 「如何讓專案對 AI 友善?」 |
|
|
33
|
+
|
|
24
34
|
## 目的
|
|
25
35
|
|
|
26
|
-
本技能協助建立和維護 AI
|
|
36
|
+
本技能協助建立和維護 AI 指令檔案,適當區分通用標準與專案特定配置,適用於所有主流 AI 輔助編程工具。
|
|
37
|
+
|
|
38
|
+
---
|
|
27
39
|
|
|
28
40
|
## 快速參考
|
|
29
41
|
|
|
30
|
-
### 支援的 AI
|
|
42
|
+
### 支援的 AI 工具(2026-04-28 更新)
|
|
43
|
+
|
|
44
|
+
#### CLI / Agent 型(終端機代理)
|
|
45
|
+
|
|
46
|
+
| 工具 | 主要指令檔案 | Workflow 機制 | MCP |
|
|
47
|
+
|------|------------|--------------|-----|
|
|
48
|
+
| **Claude Code** | `CLAUDE.md` + `.claude/rules/*.md` | Skills (`.claude/skills/` → `/{name}`) | ✅ |
|
|
49
|
+
| **Gemini CLI** | `GEMINI.md` | `.gemini/commands/*.toml` → `/{name}` | ✅ |
|
|
50
|
+
| **OpenAI Codex CLI** | `AGENTS.md`(+ `AGENTS.override.md`) | 團隊指令;`/review` 內建 | ✅ |
|
|
51
|
+
| **OpenCode** | `AGENTS.md`(相容 CLAUDE.md) | 僅內建(`/init` `/undo` `/share`) | ✅ |
|
|
52
|
+
|
|
53
|
+
#### AI-native IDE / 編輯器整合
|
|
54
|
+
|
|
55
|
+
| 工具 | 主要指令檔案 | Workflow 機制 | MCP |
|
|
56
|
+
|------|------------|--------------|-----|
|
|
57
|
+
| **Cursor** | `.cursor/rules/*.mdc` ⚠️ | `@`-mention;`/multitask` | ✅ |
|
|
58
|
+
| **GitHub Copilot** | `.github/copilot-instructions.md` | `.github/prompts/*.prompt.md` → `/{name}` | ✅ |
|
|
59
|
+
| **Windsurf** | `.windsurfrules` / `.windsurf/rules/*.md` | `.windsurf/workflows/*.md` → `/{name}` | ✅ |
|
|
60
|
+
| **Cline** | `.clinerules` | 無 | ✅ |
|
|
61
|
+
|
|
62
|
+
> ⚠️ **Cursor**:`.cursorrules` 已**棄用** — 請遷移至 `.cursor/rules/*.mdc`
|
|
63
|
+
|
|
64
|
+
---
|
|
65
|
+
|
|
66
|
+
### 跨工具通用標準:`AGENTS.md`
|
|
31
67
|
|
|
32
|
-
|
|
33
|
-
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
|
|
39
|
-
|
|
68
|
+
`AGENTS.md` 正成為事實上的跨工具指令標準:
|
|
69
|
+
|
|
70
|
+
**支援的工具**:Gemini CLI、OpenAI Codex CLI、OpenCode、GitHub Copilot、Windsurf、Cursor
|
|
71
|
+
**不支援的工具**:Claude Code(使用 `CLAUDE.md`)、Cline(使用 `.clinerules`)
|
|
72
|
+
|
|
73
|
+
**建議**:多工具專案使用 `AGENTS.md` 作為通用基準,再為各工具添加特定檔案(Skills、Workflows、Prompts)。
|
|
74
|
+
|
|
75
|
+
---
|
|
40
76
|
|
|
41
77
|
### 核心原則:通用 vs 專案特定
|
|
42
78
|
|
|
@@ -45,6 +81,8 @@ description: "[UDS] 建立和維護 AI 指令檔案(CLAUDE.md、.cursorrules
|
|
|
45
81
|
| **通用** | 通用規則 | 「提交前執行測試」 |
|
|
46
82
|
| **專案特定** | 具體命令 | 「提交前執行 `npm test`」 |
|
|
47
83
|
|
|
84
|
+
---
|
|
85
|
+
|
|
48
86
|
### 建議配置
|
|
49
87
|
|
|
50
88
|
```markdown
|
|
@@ -72,89 +110,152 @@ description: "[UDS] 建立和維護 AI 指令檔案(CLAUDE.md、.cursorrules
|
|
|
72
110
|
[你的專案結構]
|
|
73
111
|
```
|
|
74
112
|
|
|
75
|
-
|
|
113
|
+
---
|
|
76
114
|
|
|
77
|
-
|
|
78
|
-
- [AI 指令檔案標準](../../core/ai-instruction-standards.md)
|
|
115
|
+
## 各工具設定指南
|
|
79
116
|
|
|
80
|
-
###
|
|
117
|
+
### Claude Code
|
|
81
118
|
|
|
82
|
-
|
|
83
|
-
|
|
119
|
+
```
|
|
120
|
+
CLAUDE.md # 主要指令(階層式:全域 → 專案 → 子目錄)
|
|
121
|
+
.claude/rules/ # Glob 範圍的附加規則
|
|
122
|
+
.claude/skills/{name}/SKILL.md # 自訂斜線命令 → /{name}
|
|
123
|
+
.claude/agents/{name}.md # 子代理定義
|
|
124
|
+
```
|
|
84
125
|
|
|
85
|
-
|
|
126
|
+
### Gemini CLI
|
|
86
127
|
|
|
87
|
-
|
|
128
|
+
```
|
|
129
|
+
GEMINI.md # 主要指令
|
|
130
|
+
.gemini/commands/{name}.toml # 自訂斜線命令 → /{name}
|
|
131
|
+
.gemini/agents/{name}.yaml # 子代理定義
|
|
132
|
+
```
|
|
88
133
|
|
|
89
|
-
|
|
90
|
-
|
|
91
|
-
|
|
92
|
-
|
|
93
|
-
|
|
94
|
-
| **AI 行為** | 「分析前務必先讀取程式碼」 |
|
|
134
|
+
`.gemini/commands/review.toml` 範例:
|
|
135
|
+
```toml
|
|
136
|
+
description = "執行程式碼審查清單"
|
|
137
|
+
prompt = "審查以下變更:!{git diff HEAD}"
|
|
138
|
+
```
|
|
95
139
|
|
|
96
|
-
|
|
97
|
-
- 特定命令(`npm test`、`pytest`)
|
|
98
|
-
- 固定路徑(`cli/src/`、`/var/www/`)
|
|
99
|
-
- 版本號(`Node.js 18`、`Python 3.11`)
|
|
100
|
-
- 專案名稱和 URL
|
|
140
|
+
### OpenAI Codex CLI
|
|
101
141
|
|
|
102
|
-
|
|
142
|
+
```
|
|
143
|
+
AGENTS.md # 主要指令(從 Git root 到 cwd 逐層讀取)
|
|
144
|
+
AGENTS.override.md # 暫時覆蓋(最高優先級)
|
|
145
|
+
~/.codex/AGENTS.md # 全域備援
|
|
146
|
+
.codex/agents/ # 自訂代理定義
|
|
147
|
+
```
|
|
103
148
|
|
|
104
|
-
|
|
105
|
-
|------|------|
|
|
106
|
-
| **技術棧** | Node.js 18、React 18、PostgreSQL 15 |
|
|
107
|
-
| **命令** | `npm run lint`、`./scripts/deploy.sh` |
|
|
108
|
-
| **檔案結構** | `src/`、`cli/`、`tests/` |
|
|
109
|
-
| **團隊慣例** | 繁體中文註解 |
|
|
149
|
+
### OpenCode
|
|
110
150
|
|
|
111
|
-
|
|
151
|
+
```
|
|
152
|
+
AGENTS.md # 主要(自動識別)
|
|
153
|
+
CLAUDE.md # 同樣識別(遷移相容性)
|
|
154
|
+
.opencode/agents/ # 自訂代理定義
|
|
155
|
+
opencode.json (instructions) # Glob 模式檔案引用
|
|
156
|
+
```
|
|
112
157
|
|
|
113
|
-
###
|
|
158
|
+
### Cursor
|
|
114
159
|
|
|
115
|
-
```
|
|
116
|
-
|
|
117
|
-
|
|
160
|
+
```
|
|
161
|
+
.cursor/rules/ # MDC 格式規則(取代 .cursorrules)
|
|
162
|
+
{name}.mdc # Frontmatter: description, globs, alwaysApply
|
|
163
|
+
AGENTS.md # 也支援(代理上下文)
|
|
164
|
+
```
|
|
118
165
|
|
|
119
|
-
|
|
120
|
-
|
|
166
|
+
MDC frontmatter 範例:
|
|
167
|
+
```yaml
|
|
168
|
+
---
|
|
169
|
+
description: "TypeScript 編碼標準"
|
|
170
|
+
globs: ["**/*.ts", "**/*.tsx"]
|
|
171
|
+
alwaysApply: false
|
|
172
|
+
---
|
|
121
173
|
```
|
|
122
174
|
|
|
123
|
-
|
|
175
|
+
> **遷移指引**:若有 `.cursorrules`,請將內容移至 `.cursor/rules/*.mdc`。
|
|
124
176
|
|
|
125
|
-
|
|
126
|
-
> ⚠️ **專案特定**:本區段包含此專案獨有的配置。
|
|
177
|
+
### GitHub Copilot
|
|
127
178
|
|
|
128
|
-
|
|
129
|
-
|
|
179
|
+
```
|
|
180
|
+
.github/copilot-instructions.md # 永遠啟用,所有對話
|
|
181
|
+
.github/instructions/*.instructions.md # 條件式,Glob 範圍(applyTo frontmatter)
|
|
182
|
+
.github/prompts/*.prompt.md # 可重用模板 → /{name} 斜線命令
|
|
183
|
+
.github/agents/*.agent.md # 自訂代理,精細工具存取控制
|
|
184
|
+
AGENTS.md # 也被識別
|
|
130
185
|
```
|
|
131
186
|
|
|
132
|
-
###
|
|
187
|
+
### Windsurf
|
|
133
188
|
|
|
134
|
-
```
|
|
135
|
-
|
|
136
|
-
|
|
137
|
-
|
|
189
|
+
```
|
|
190
|
+
.windsurfrules # 專案規則(可 Git 共享)
|
|
191
|
+
.windsurf/rules/*.md # MDC frontmatter 結構化規則
|
|
192
|
+
.windsurf/workflows/*.md # 可重用任務序列 → /{name}
|
|
193
|
+
AGENTS.md # 也被識別
|
|
194
|
+
```
|
|
138
195
|
|
|
139
|
-
|
|
140
|
-
|
|
141
|
-
|
|
196
|
+
Workflow 範例(`.windsurf/workflows/review.md`):
|
|
197
|
+
```markdown
|
|
198
|
+
執行程式碼審查:
|
|
199
|
+
1. 執行 `git diff HEAD`
|
|
200
|
+
2. 檢查 BLOCKING 問題(安全性、正確性)
|
|
201
|
+
3. 檢查 IMPORTANT 問題(設計、測試)
|
|
202
|
+
4. 以 BLOCKING/IMPORTANT/SUGGESTION 前綴輸出發現
|
|
142
203
|
```
|
|
143
204
|
|
|
144
|
-
|
|
205
|
+
---
|
|
206
|
+
|
|
207
|
+
## 多工具專案配置
|
|
145
208
|
|
|
146
|
-
|
|
209
|
+
當專案使用多個 AI 工具時:
|
|
147
210
|
|
|
148
211
|
```
|
|
149
212
|
project/
|
|
150
|
-
├──
|
|
151
|
-
├── .
|
|
152
|
-
├── .
|
|
213
|
+
├── AGENTS.md # 通用基準(跨工具)
|
|
214
|
+
├── CLAUDE.md # Claude Code(擴展 AGENTS.md)
|
|
215
|
+
├── GEMINI.md # Gemini CLI
|
|
216
|
+
├── .cursor/rules/
|
|
217
|
+
│ └── standards.mdc # Cursor
|
|
218
|
+
├── .windsurf/
|
|
219
|
+
│ └── workflows/ # Windsurf Workflows
|
|
220
|
+
│ ├── review.md
|
|
221
|
+
│ └── checkin.md
|
|
153
222
|
└── .github/
|
|
154
|
-
|
|
223
|
+
├── copilot-instructions.md # Copilot 永遠啟用
|
|
224
|
+
└── prompts/
|
|
225
|
+
└── review.prompt.md # Copilot 斜線命令
|
|
155
226
|
```
|
|
156
227
|
|
|
157
|
-
|
|
228
|
+
**最佳實踐**:將通用內容寫在 `AGENTS.md` 一次,從各工具特定檔案引用,避免重複。
|
|
229
|
+
|
|
230
|
+
---
|
|
231
|
+
|
|
232
|
+
## 內容指南
|
|
233
|
+
|
|
234
|
+
### 通用內容(保持通用)
|
|
235
|
+
|
|
236
|
+
| 類別 | 良好範例 |
|
|
237
|
+
|------|----------|
|
|
238
|
+
| **提交標準** | 「遵循 Conventional Commits 格式」 |
|
|
239
|
+
| **程式碼審查** | 「使用 BLOCKING、IMPORTANT、SUGGESTION 前綴」 |
|
|
240
|
+
| **測試** | 「維持最低 80% 覆蓋率」 |
|
|
241
|
+
| **AI 行為** | 「分析前務必先讀取程式碼」 |
|
|
242
|
+
|
|
243
|
+
**通用區段應避免:**
|
|
244
|
+
- 特定命令(`npm test`、`pytest`)
|
|
245
|
+
- 固定路徑(`cli/src/`、`/var/www/`)
|
|
246
|
+
- 版本號(`Node.js 18`、`Python 3.11`)
|
|
247
|
+
- 專案名稱和 URL
|
|
248
|
+
|
|
249
|
+
### 專案特定內容
|
|
250
|
+
|
|
251
|
+
| 類別 | 範例 |
|
|
252
|
+
|------|------|
|
|
253
|
+
| **技術棧** | Node.js 18、React 18、PostgreSQL 15 |
|
|
254
|
+
| **命令** | `npm run lint`、`./scripts/deploy.sh` |
|
|
255
|
+
| **檔案結構** | `src/`、`cli/`、`tests/` |
|
|
256
|
+
| **團隊慣例** | 繁體中文註解 |
|
|
257
|
+
|
|
258
|
+
---
|
|
158
259
|
|
|
159
260
|
## 維護檢查清單
|
|
160
261
|
|
|
@@ -164,27 +265,29 @@ project/
|
|
|
164
265
|
- [ ] 專案特定區段有明確標記
|
|
165
266
|
- [ ] 標準文件的交叉引用正確
|
|
166
267
|
- [ ] 格式與現有區段一致
|
|
268
|
+
- [ ] 若使用 Cursor:`.cursorrules` 已遷移至 `.cursor/rules/*.mdc`
|
|
269
|
+
- [ ] 若為多工具專案:`AGENTS.md` 已涵蓋通用基準
|
|
167
270
|
|
|
168
271
|
---
|
|
169
272
|
|
|
170
273
|
## 配置偵測
|
|
171
274
|
|
|
172
|
-
本技能支援專案特定配置。
|
|
173
|
-
|
|
174
275
|
### 偵測順序
|
|
175
276
|
|
|
176
|
-
1. 檢查是否存在 `CLAUDE.md` 或等效檔案
|
|
177
|
-
2.
|
|
178
|
-
3.
|
|
277
|
+
1. 檢查是否存在 `CLAUDE.md`、`AGENTS.md`、`GEMINI.md` 或等效檔案
|
|
278
|
+
2. 偵測使用中的 AI 工具(檢查 `.cursor/`、`.windsurf/`、`.github/copilot-instructions.md` 等)
|
|
279
|
+
3. 分析內容結構是否區分通用/專案特定
|
|
280
|
+
4. 若未找到,**建議建立結構化 AI 指令檔案**
|
|
179
281
|
|
|
180
282
|
### 首次設定
|
|
181
283
|
|
|
182
284
|
若未找到 AI 指令檔案:
|
|
183
285
|
|
|
184
|
-
1. 詢問:「此專案沒有 AI
|
|
185
|
-
2.
|
|
186
|
-
3.
|
|
187
|
-
4.
|
|
286
|
+
1. 詢問:「此專案沒有 AI 指令檔案。你使用哪些 AI 工具?」
|
|
287
|
+
2. 多工具專案推薦 `AGENTS.md` 作為基準,純 Claude Code 使用 `CLAUDE.md`
|
|
288
|
+
3. 確定專案類型和技術棧
|
|
289
|
+
4. 產生包含適當區段的範本
|
|
290
|
+
5. 若包含敏感資訊,新增到 `.gitignore`
|
|
188
291
|
|
|
189
292
|
---
|
|
190
293
|
|
|
@@ -201,6 +304,7 @@ project/
|
|
|
201
304
|
|
|
202
305
|
| 版本 | 日期 | 變更 |
|
|
203
306
|
|------|------|------|
|
|
307
|
+
| 2.0.0 | 2026-04-28 | 新增 Gemini CLI、OpenAI Codex CLI;更新 Cursor(MDC 格式,標記 .cursorrules 棄用);更新 OpenCode(AGENTS.md 為主);更新 Copilot(多種指令檔案類型);更新 Windsurf(Workflows);新增 AGENTS.md 跨工具標準章節 |
|
|
204
308
|
| 1.0.0 | 2026-01-25 | 初始發布 |
|
|
205
309
|
|
|
206
310
|
---
|
package/bundled/skills/README.md
CHANGED
|
@@ -34,14 +34,15 @@ These skills provide standard guidance and workflows. They can be accessed via s
|
|
|
34
34
|
| `bdd-assistant` | `/bdd` | [UDS] Behavior-Driven Development |
|
|
35
35
|
| `atdd-assistant` | `/atdd` | [UDS] Acceptance Test-Driven Development |
|
|
36
36
|
| `e2e-assistant` | `/e2e` | [UDS] E2E test skeleton generation from BDD scenarios |
|
|
37
|
+
| `journey-test-assistant` | `/journey-test` | [UDS] Connected user journey test plan (TESTPLAN) + E2E skeleton generation |
|
|
37
38
|
| `release-standards` | `/release` | [UDS] Release & Changelog management |
|
|
38
39
|
| `documentation-guide` | `/docs` | [UDS] Documentation management |
|
|
39
40
|
| `requirement-assistant` | `/requirement` | [UDS] Requirement writing |
|
|
40
41
|
| `reverse-engineer` | `/reverse` | [UDS] Reverse engineer code |
|
|
41
|
-
| `
|
|
42
|
+
| `spec-derivation` | `/spec-derive` | [UDS] Derive BDD/TDD/ATDD artifacts from spec |
|
|
42
43
|
| `spec-driven-dev` | `/sdd` | [UDS] Spec-Driven Development |
|
|
43
44
|
| `test-coverage-assistant` | `/coverage` | [UDS] Test coverage analysis |
|
|
44
|
-
| `methodology
|
|
45
|
+
| `dev-methodology` | `/methodology` | [UDS] Development methodology |
|
|
45
46
|
| `refactoring-assistant` | `/refactor` | [UDS] Refactoring guidance |
|
|
46
47
|
| `project-discovery` | `/discover` | [UDS] Assess project health and risks |
|
|
47
48
|
| `brainstorm-assistant` | `/brainstorm` | [UDS] Structured AI-assisted ideation |
|
|
@@ -62,7 +63,7 @@ These skills provide standard guidance and workflows. They can be accessed via s
|
|
|
62
63
|
| `observability-assistant` | `/observability` | [UDS] Observability setup, metrics, alerting 🆕 |
|
|
63
64
|
| `slo-assistant` | `/slo` | [UDS] SLI selection, SLO setting, Error Budget 🆕 |
|
|
64
65
|
| `runbook-assistant` | `/runbook` | [UDS] Runbook creation, drills, coverage 🆕 |
|
|
65
|
-
| `
|
|
66
|
+
| `skill-builder` | `/skill-builder` | [UDS] Identify repeated processes and build Skills with the right development depth |
|
|
66
67
|
|
|
67
68
|
> **Note**: For reference guides (e.g., Git Workflow, Logging, Error Codes), use the `/guide` command.
|
|
68
69
|
|
|
@@ -0,0 +1,94 @@
|
|
|
1
|
+
# UDS Skill 命名規範
|
|
2
|
+
|
|
3
|
+
> **版本**: 1.0.0 | **建立**: 2026-04-29 | **依據**: XSPEC-100
|
|
4
|
+
|
|
5
|
+
本文件定義所有 UDS Skill 的命名規則,確保命令一致、可猜測、不需背景知識即可理解。
|
|
6
|
+
|
|
7
|
+
---
|
|
8
|
+
|
|
9
|
+
## 規則
|
|
10
|
+
|
|
11
|
+
### 規則 1:目錄名稱以功能領域為主詞
|
|
12
|
+
|
|
13
|
+
- **格式**:`{領域}-{動作/角色}` 或 `{領域}-{類型}`
|
|
14
|
+
- **良好範例**:`tdd-assistant`、`api-design-assistant`、`dev-methodology`
|
|
15
|
+
- **避免**:`methodology-system`(`-system` 不傳遞任何資訊)、`process-automation`(太廣泛)
|
|
16
|
+
|
|
17
|
+
### 規則 2:後綴使用 `-assistant` 或無後綴
|
|
18
|
+
|
|
19
|
+
| 後綴 | 使用時機 |
|
|
20
|
+
|------|---------|
|
|
21
|
+
| `-assistant` | Skill 提供互動式引導流程(問答式、多階段) |
|
|
22
|
+
| 無後綴 | 工具型(`push`)、短命令(`xspec`)、名詞型(`dev-methodology`) |
|
|
23
|
+
| **禁止** `-guide` 與 `-standards` 混用 | 改為描述性名詞(`logging-guide` → `logging`,長期計畫) |
|
|
24
|
+
|
|
25
|
+
### 規則 3:縮寫只限業界公認的詞彙
|
|
26
|
+
|
|
27
|
+
| 允許縮寫 | 全稱 | 說明 |
|
|
28
|
+
|---------|------|------|
|
|
29
|
+
| `tdd` | Test-Driven Development | 業界公認 |
|
|
30
|
+
| `bdd` | Behavior-Driven Development | 業界公認 |
|
|
31
|
+
| `atdd` | Acceptance TDD | 業界公認(需在 README 說明) |
|
|
32
|
+
| `e2e` | End-to-End | 業界公認 |
|
|
33
|
+
| `api` | Application Programming Interface | 通用 |
|
|
34
|
+
| `ci-cd` | Continuous Integration/Delivery | 業界公認 |
|
|
35
|
+
| `slo` | Service Level Objective | SRE 領域公認(需在 README 說明) |
|
|
36
|
+
|
|
37
|
+
**禁止使用未說明的專案特定縮寫作為主要識別名稱**(如 `xspec`、`dec` 屬於工具型短命令,已在說明文件補充全稱)。
|
|
38
|
+
|
|
39
|
+
### 規則 4:slash command(`name:` 欄位)必須比目錄名更短
|
|
40
|
+
|
|
41
|
+
- 目錄名用於 system-reminder 顯示(描述性)
|
|
42
|
+
- `name:` 欄位是使用者實際輸入的命令(應短、清楚)
|
|
43
|
+
- 例:目錄 `tdd-assistant` → `name: tdd`;目錄 `api-design-assistant` → `name: api-design`
|
|
44
|
+
|
|
45
|
+
### 規則 5:命令名稱必須能預測功能
|
|
46
|
+
|
|
47
|
+
判斷標準:對不認識此 Skill 的開發者說「這個命令叫 `/xxx`」,他能否猜出大概是做什麼?
|
|
48
|
+
|
|
49
|
+
- `/tdd` ✅ → 測試驅動開發
|
|
50
|
+
- `/eval-source` ✅ → 評估外部來源
|
|
51
|
+
- `/borrow` ❌ → 借什麼?
|
|
52
|
+
- `/derive` ⚠️ → 可接受(SDD 脈絡下清楚),但 `/spec-derive` 更明確
|
|
53
|
+
|
|
54
|
+
---
|
|
55
|
+
|
|
56
|
+
## 命名範例對照表
|
|
57
|
+
|
|
58
|
+
| 舊命令目錄 | 新命令目錄 | slash command | 改名原因 |
|
|
59
|
+
|----------|----------|--------------|---------|
|
|
60
|
+
| `ac-coverage-assistant` | `ac-coverage` | `/ac-coverage` | 去冗餘後綴;已有 `name: ac-coverage` |
|
|
61
|
+
| `forward-derivation` | `spec-derivation` | `/derive` | 明確「從規格衍生」語意 |
|
|
62
|
+
| `methodology-system` | `dev-methodology` | `/methodology` | `-system` 無意義,改為名詞形式 |
|
|
63
|
+
| `process-automation` | `skill-builder` | `/skill-builder` | 功能是「建立 Skill」,非廣義自動化 |
|
|
64
|
+
| `borrow-assistant` | `eval-source` | `/eval-source` | 明確「評估外部來源」語意 |
|
|
65
|
+
| `dec-update-assistant` | `dec-update` | `/dec-update` | 去冗餘後綴;已有 `name: dec-update` |
|
|
66
|
+
| `session-prompt-assistant` | `session-init` | `/session-init` | 明確「初始化 session」語意 |
|
|
67
|
+
| `xspec-assistant` | `xspec` | `/xspec` | 工具型短命令,已有 `name: xspec` |
|
|
68
|
+
|
|
69
|
+
---
|
|
70
|
+
|
|
71
|
+
## 新增 Skill 命名檢查清單
|
|
72
|
+
|
|
73
|
+
新增 Skill 時,依序確認:
|
|
74
|
+
|
|
75
|
+
- [ ] 目錄名以功能領域為主詞(非動詞或系統名詞)
|
|
76
|
+
- [ ] 後綴:引導式用 `-assistant`,工具型無後綴
|
|
77
|
+
- [ ] 只用業界公認縮寫;專案特定縮寫需在 README 補說明
|
|
78
|
+
- [ ] `name:` 欄位比目錄名短,且能預測功能
|
|
79
|
+
- [ ] 更新 `skills/README.md` 加入新 Skill 的縮寫說明
|
|
80
|
+
|
|
81
|
+
---
|
|
82
|
+
|
|
83
|
+
## 歷史改名紀錄
|
|
84
|
+
|
|
85
|
+
| 日期 | 舊名 | 新名 | XSPEC |
|
|
86
|
+
|------|------|------|-------|
|
|
87
|
+
| 2026-04-29 | `ac-coverage-assistant` | `ac-coverage` | XSPEC-100 |
|
|
88
|
+
| 2026-04-29 | `forward-derivation` | `spec-derivation` | XSPEC-100 |
|
|
89
|
+
| 2026-04-29 | `methodology-system` | `dev-methodology` | XSPEC-100 |
|
|
90
|
+
| 2026-04-29 | `process-automation` | `skill-builder` | XSPEC-100 |
|
|
91
|
+
| 2026-04-29 | `borrow-assistant` | `eval-source` | XSPEC-100 |
|
|
92
|
+
| 2026-04-29 | `dec-update-assistant` | `dec-update` | XSPEC-100 |
|
|
93
|
+
| 2026-04-29 | `session-prompt-assistant` | `session-init` | XSPEC-100 |
|
|
94
|
+
| 2026-04-29 | `xspec-assistant` | `xspec` | XSPEC-100 |
|