create-ai-project 1.18.2 → 1.18.4
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/.claude/agents-en/task-decomposer.md +1 -1
- package/.claude/agents-en/technical-designer-frontend.md +4 -3
- package/.claude/agents-en/technical-designer.md +2 -2
- package/.claude/agents-en/work-planner.md +6 -5
- package/.claude/agents-ja/task-decomposer.md +1 -1
- package/.claude/agents-ja/technical-designer-frontend.md +4 -3
- package/.claude/agents-ja/technical-designer.md +2 -2
- package/.claude/agents-ja/work-planner.md +6 -5
- package/.claude/commands-en/add-integration-tests.md +53 -28
- package/.claude/commands-en/build.md +2 -1
- package/.claude/commands-en/front-build.md +2 -1
- package/.claude/commands-en/front-plan.md +1 -1
- package/.claude/commands-en/implement.md +1 -1
- package/.claude/commands-en/plan.md +9 -2
- package/.claude/commands-ja/add-integration-tests.md +53 -28
- package/.claude/commands-ja/build.md +2 -1
- package/.claude/commands-ja/front-build.md +2 -1
- package/.claude/commands-ja/front-plan.md +1 -1
- package/.claude/commands-ja/implement.md +1 -1
- package/.claude/commands-ja/plan.md +9 -2
- package/.claude/skills-en/documentation-criteria/SKILL.md +2 -3
- package/.claude/skills-en/documentation-criteria/references/design-template.md +1 -20
- package/.claude/skills-en/documentation-criteria/references/plan-template.md +2 -18
- package/.claude/skills-en/subagents-orchestration-guide/SKILL.md +1 -1
- package/.claude/skills-en/task-analyzer/references/skills-index.yaml +2 -1
- package/.claude/skills-ja/documentation-criteria/SKILL.md +2 -3
- package/.claude/skills-ja/documentation-criteria/references/design-template.md +1 -20
- package/.claude/skills-ja/documentation-criteria/references/plan-template.md +2 -18
- package/.claude/skills-ja/subagents-orchestration-guide/SKILL.md +1 -1
- package/.claude/skills-ja/task-analyzer/references/skills-index.yaml +1 -2
- package/CHANGELOG.md +39 -0
- package/package.json +1 -1
|
@@ -85,7 +85,7 @@ Decompose tasks based on implementation strategy patterns determined in implemen
|
|
|
85
85
|
- **Phase Completion Task Auto-generation (Required)**:
|
|
86
86
|
- Based on "Phase X" notation in work plan, generate after each phase's final task
|
|
87
87
|
- Filename: `{plan-name}-phase{number}-completion.md`
|
|
88
|
-
- Content:
|
|
88
|
+
- Content: All task completion checklist, list test skeleton file paths for verification
|
|
89
89
|
- Criteria: Always generate if the plan contains the string "Phase"
|
|
90
90
|
|
|
91
91
|
5. **Task Structuring**
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
name: technical-designer-frontend
|
|
3
3
|
description: Creates frontend ADR and Design Docs to evaluate React technical choices. Use when frontend PRD is complete and technical design is needed, or when "frontend design/React design/UI design/component design" is mentioned.
|
|
4
4
|
tools: Read, Write, Edit, MultiEdit, Glob, LS, Bash, TaskCreate, TaskUpdate, WebSearch
|
|
5
|
-
skills: documentation-criteria, frontend-technical-spec, frontend-typescript-rules, coding-standards, project-context, implementation-approach
|
|
5
|
+
skills: documentation-criteria, frontend-technical-spec, frontend-typescript-rules, coding-standards, project-context, implementation-approach, typescript-testing
|
|
6
6
|
---
|
|
7
7
|
|
|
8
8
|
You are a frontend technical design specialist AI assistant for creating Architecture Decision Records (ADR) and Design Documents.
|
|
@@ -22,6 +22,7 @@ Operates in an independent context without CLAUDE.md principles, executing auton
|
|
|
22
22
|
- Apply coding-standards skill for universal coding standards and pre-implementation existing code investigation process
|
|
23
23
|
- Apply project-context skill for project context
|
|
24
24
|
- Apply implementation-approach skill for metacognitive strategy selection process (used for implementation approach decisions)
|
|
25
|
+
- Apply typescript-testing skill for test design standards (testable AC format, coverage requirements)
|
|
25
26
|
|
|
26
27
|
## Main Responsibilities
|
|
27
28
|
|
|
@@ -308,9 +309,9 @@ class Button extends React.Component {
|
|
|
308
309
|
- [ ] **Agreement checklist completed** (most important)
|
|
309
310
|
- [ ] **Prerequisite common ADRs referenced** (required)
|
|
310
311
|
- [ ] **Change impact map created** (required)
|
|
311
|
-
- [ ] **Component verification procedures for each phase** (required)
|
|
312
312
|
- [ ] Response to requirements and design validity
|
|
313
|
-
- [ ]
|
|
313
|
+
- [ ] Error handling strategy
|
|
314
|
+
- [ ] Acceptance criteria written in testable format (concrete trigger, action, and expected result)
|
|
314
315
|
- [ ] Props change matrix completeness
|
|
315
316
|
- [ ] Implementation approach selection rationale (vertical/horizontal/hybrid)
|
|
316
317
|
- [ ] Latest best practices researched and references cited
|
|
@@ -276,9 +276,9 @@ Implementation sample creation checklist:
|
|
|
276
276
|
- [ ] **Agreement checklist completed** (most important)
|
|
277
277
|
- [ ] **Prerequisite common ADRs referenced** (required)
|
|
278
278
|
- [ ] **Change impact map created** (required)
|
|
279
|
-
- [ ] **E2E verification procedures for each phase** (required)
|
|
280
279
|
- [ ] Response to requirements and design validity
|
|
281
|
-
- [ ]
|
|
280
|
+
- [ ] Error handling strategy
|
|
281
|
+
- [ ] Acceptance criteria written in testable format (concrete trigger, action, and expected result)
|
|
282
282
|
- [ ] Interface change matrix completeness
|
|
283
283
|
- [ ] Implementation approach selection rationale (vertical/horizontal/hybrid)
|
|
284
284
|
- [ ] Latest best practices researched and references cited
|
|
@@ -25,7 +25,7 @@ Operates in an independent context without CLAUDE.md principles, executing auton
|
|
|
25
25
|
Read the Design Doc(s), UI Spec, PRD, and ADR (if provided). Extract:
|
|
26
26
|
- Acceptance criteria and implementation approach
|
|
27
27
|
- Technical dependencies and implementation order
|
|
28
|
-
- Integration points
|
|
28
|
+
- Integration points and their contracts
|
|
29
29
|
|
|
30
30
|
### 2. Process Test Design Information (when provided)
|
|
31
31
|
Read test skeleton files and extract meta information (see Test Design Information Processing section).
|
|
@@ -36,7 +36,8 @@ Choose Strategy A (TDD) if test skeletons are provided, Strategy B (implementati
|
|
|
36
36
|
### 4. Compose Phases
|
|
37
37
|
Structure phases based on technical dependencies from Design Doc:
|
|
38
38
|
- Place tasks with lowest dependencies in earlier phases
|
|
39
|
-
-
|
|
39
|
+
- When test skeletons are provided, place integration test implementation in corresponding phases and E2E test execution in the final phase
|
|
40
|
+
- When test skeletons are not provided, include test implementation tasks based on Design Doc acceptance criteria
|
|
40
41
|
- Include quality assurance in final phase
|
|
41
42
|
|
|
42
43
|
### 5. Define Tasks with Completion Criteria
|
|
@@ -180,8 +181,8 @@ Decompose tasks based on implementation approach and technical dependencies deci
|
|
|
180
181
|
Compose phases based on technical dependencies and implementation approach from Design Doc.
|
|
181
182
|
Always include quality assurance (all tests passing, acceptance criteria achieved) in final phase.
|
|
182
183
|
|
|
183
|
-
###
|
|
184
|
-
|
|
184
|
+
### Test Skeleton Integration
|
|
185
|
+
Follow the test skeleton placement rules defined in Step 4 of the Planning Process.
|
|
185
186
|
|
|
186
187
|
### Task Dependencies
|
|
187
188
|
- Clearly define dependencies
|
|
@@ -198,7 +199,7 @@ When creating work plans, **Phase Structure Diagrams** and **Task Dependency Dia
|
|
|
198
199
|
- [ ] Phase composition based on technical dependencies
|
|
199
200
|
- [ ] All requirements converted to tasks
|
|
200
201
|
- [ ] Quality assurance exists in final phase
|
|
201
|
-
- [ ]
|
|
202
|
+
- [ ] Test skeleton file paths listed in corresponding phases (when provided)
|
|
202
203
|
- [ ] Test design information reflected (only when provided)
|
|
203
204
|
- [ ] Setup tasks placed in first phase
|
|
204
205
|
- [ ] Risk level-based prioritization applied
|
|
@@ -85,7 +85,7 @@ implementation-approachスキルで決定された実装戦略パターンに基
|
|
|
85
85
|
- **フェーズ完了タスクの自動生成(必須)**:
|
|
86
86
|
- 作業計画書の「Phase X」表記を基準に、各フェーズ最終タスクの後に生成
|
|
87
87
|
- ファイル名: `{計画書名}-phase{番号}-completion.md`
|
|
88
|
-
- 内容:
|
|
88
|
+
- 内容: 全タスク完了チェックリスト、テストスケルトンファイルパスを検証用に記載
|
|
89
89
|
- 判断基準: 計画書に「Phase」という文字列があれば必ず生成
|
|
90
90
|
|
|
91
91
|
5. **タスクの構造化**
|
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
name: technical-designer-frontend
|
|
3
3
|
description: フロントエンドADRとDesign Docを作成しReact技術選択肢を評価。Use when フロントエンドPRD完成後に技術設計が必要な時、または「フロントエンド設計/React設計/UI設計/コンポーネント設計」が言及された時。
|
|
4
4
|
tools: Read, Write, Edit, MultiEdit, Glob, LS, Bash, TaskCreate, TaskUpdate, WebSearch
|
|
5
|
-
skills: documentation-criteria, frontend-technical-spec, frontend-typescript-rules, coding-standards, project-context, implementation-approach
|
|
5
|
+
skills: documentation-criteria, frontend-technical-spec, frontend-typescript-rules, coding-standards, project-context, implementation-approach, typescript-testing
|
|
6
6
|
---
|
|
7
7
|
|
|
8
8
|
あなたはArchitecture Decision Record (ADR) と Design Document を作成するフロントエンド技術設計専門のAIアシスタントです。
|
|
@@ -22,6 +22,7 @@ CLAUDE.mdの原則を適用しない独立したコンテキストを持ち、
|
|
|
22
22
|
- coding-standardsスキルで普遍的コーディング規約を適用
|
|
23
23
|
- project-contextスキルでプロジェクトコンテキストを把握
|
|
24
24
|
- implementation-approachスキルでメタ認知的戦略選択プロセスを実行
|
|
25
|
+
- typescript-testingスキルでテスト設計基準を適用(テスト可能なAC形式、カバレッジ要件)
|
|
25
26
|
|
|
26
27
|
## UI Spec統合
|
|
27
28
|
|
|
@@ -308,9 +309,9 @@ class Button extends React.Component {
|
|
|
308
309
|
- [ ] **合意事項チェックリストの完了**(最重要)
|
|
309
310
|
- [ ] **前提となる共通ADRの参照**(必須)
|
|
310
311
|
- [ ] **変更影響マップの作成**(必須)
|
|
311
|
-
- [ ] **各フェーズのコンポーネント検証手順**(必須)
|
|
312
312
|
- [ ] 要件への対応と設計の妥当性
|
|
313
|
-
- [ ]
|
|
313
|
+
- [ ] エラーハンドリング戦略
|
|
314
|
+
- [ ] 受入条件がテスト可能な形式で記述されていること(具体的なトリガー、操作、期待結果)
|
|
314
315
|
- [ ] Props変更マトリクスの完成度
|
|
315
316
|
- [ ] 実装アプローチ(垂直/水平/ハイブリッド)の選択根拠
|
|
316
317
|
- [ ] 最新のベストプラクティスの調査と参考資料の記載
|
|
@@ -275,9 +275,9 @@ ADRに含まない:スケジュール、実装手順、具体的コード
|
|
|
275
275
|
- [ ] **合意事項チェックリストの完了**(最重要)
|
|
276
276
|
- [ ] **前提となる共通ADRの参照**(必須)
|
|
277
277
|
- [ ] **変更影響マップの作成**(必須)
|
|
278
|
-
- [ ] **各フェーズのE2E確認手順**(必須)
|
|
279
278
|
- [ ] 要件への対応と設計の妥当性
|
|
280
|
-
- [ ]
|
|
279
|
+
- [ ] エラーハンドリング戦略
|
|
280
|
+
- [ ] 受入条件がテスト可能な形式で記述されていること(具体的なトリガー、操作、期待結果)
|
|
281
281
|
- [ ] インターフェース変更マトリクスの完成度
|
|
282
282
|
- [ ] 実装アプローチ(垂直/水平/ハイブリッド)の選択根拠
|
|
283
283
|
- [ ] 最新のベストプラクティスの調査と参考資料の記載
|
|
@@ -25,7 +25,7 @@ CLAUDE.mdの原則を適用しない独立したコンテキストを持ち、
|
|
|
25
25
|
Design Doc、UI Spec、PRD、ADR(提供されている場合)を読み込み、以下を抽出:
|
|
26
26
|
- 受入条件と実装アプローチ
|
|
27
27
|
- 技術的依存関係と実装順序
|
|
28
|
-
-
|
|
28
|
+
- 統合ポイントとそのコントラクト
|
|
29
29
|
|
|
30
30
|
### 2. テスト設計情報の処理(提供時)
|
|
31
31
|
テストスケルトンファイルを読み込み、メタ情報を抽出(テスト設計情報の処理セクションを参照)。
|
|
@@ -36,7 +36,8 @@ Design Doc、UI Spec、PRD、ADR(提供されている場合)を読み込み
|
|
|
36
36
|
### 4. フェーズの構成
|
|
37
37
|
Design Docの技術的依存関係に基づいてフェーズを構成:
|
|
38
38
|
- 依存が最も少ないタスクを前のフェーズに配置
|
|
39
|
-
-
|
|
39
|
+
- テストスケルトンが提供されている場合、統合テスト実装を対応するフェーズに配置し、E2Eテスト実行を最終フェーズに配置
|
|
40
|
+
- テストスケルトンが提供されていない場合、Design Docの受入条件に基づくテスト実装タスクを含める
|
|
40
41
|
- 最終フェーズに品質保証を含める
|
|
41
42
|
|
|
42
43
|
### 5. 完了条件付きタスクの定義
|
|
@@ -179,8 +180,8 @@ Design Docで決定された実装アプローチと技術的依存関係に基
|
|
|
179
180
|
Design Docの技術的依存関係と実装アプローチに基づいてフェーズを構成。
|
|
180
181
|
最終フェーズには必ず品質保証(全テスト通過、受入条件達成)を含める。
|
|
181
182
|
|
|
182
|
-
###
|
|
183
|
-
|
|
183
|
+
### テストスケルトンの統合
|
|
184
|
+
計画プロセスのステップ4で定義したテストスケルトン配置ルールに従う。
|
|
184
185
|
|
|
185
186
|
### タスクの依存関係
|
|
186
187
|
- 依存関係を明確に定義
|
|
@@ -197,7 +198,7 @@ Design Docの統合ポイントごとの動作確認手順を、対応するフ
|
|
|
197
198
|
- [ ] 技術的依存関係に基づくフェーズ構成
|
|
198
199
|
- [ ] 全要件のタスク化
|
|
199
200
|
- [ ] 最終フェーズに品質保証の存在
|
|
200
|
-
- [ ]
|
|
201
|
+
- [ ] テストスケルトンファイルパスを対応するフェーズに記載(提供時)
|
|
201
202
|
- [ ] テスト設計情報の反映(提供された場合のみ)
|
|
202
203
|
- [ ] セットアップタスクが最初のフェーズに配置されている
|
|
203
204
|
- [ ] リスクレベルに基づく優先順位付けが適用されている
|
|
@@ -1,10 +1,8 @@
|
|
|
1
1
|
---
|
|
2
|
-
description: Add integration/E2E tests to existing
|
|
2
|
+
description: Add integration/E2E tests to existing codebase using Design Docs
|
|
3
3
|
---
|
|
4
4
|
|
|
5
|
-
**Command Context**: Test addition workflow for existing backend
|
|
6
|
-
|
|
7
|
-
**Scope**: Backend only (acceptance-test-generator supports backend only)
|
|
5
|
+
**Command Context**: Test addition workflow for existing implementations (backend, frontend, or fullstack)
|
|
8
6
|
|
|
9
7
|
## Orchestrator Definition
|
|
10
8
|
|
|
@@ -21,10 +19,11 @@ description: Add integration/E2E tests to existing backend codebase using Design
|
|
|
21
19
|
- Test review → delegate to integration-test-reviewer
|
|
22
20
|
- Quality checks → delegate to quality-fixer
|
|
23
21
|
|
|
24
|
-
|
|
22
|
+
Document paths: $ARGUMENTS
|
|
25
23
|
|
|
26
24
|
## Prerequisites
|
|
27
|
-
|
|
25
|
+
|
|
26
|
+
- At least one Design Doc must exist (created manually or via reverse-engineer)
|
|
28
27
|
- Existing implementation to test
|
|
29
28
|
|
|
30
29
|
## Execution Flow
|
|
@@ -33,30 +32,51 @@ Design Doc path: $ARGUMENTS
|
|
|
33
32
|
|
|
34
33
|
Execute Skill: documentation-criteria (for task file template in Step 3)
|
|
35
34
|
|
|
36
|
-
### Step 1: Validate
|
|
35
|
+
### Step 1: Discover and Validate Documents
|
|
37
36
|
|
|
38
37
|
```bash
|
|
39
|
-
# Verify
|
|
40
|
-
|
|
38
|
+
# Verify at least one document path was provided
|
|
39
|
+
test -n "$ARGUMENTS" || { echo "ERROR: No document paths provided"; exit 1; }
|
|
40
|
+
|
|
41
|
+
# Verify provided paths exist
|
|
42
|
+
ls $ARGUMENTS
|
|
43
|
+
|
|
44
|
+
# Discover additional documents
|
|
45
|
+
ls docs/design/*.md 2>/dev/null | grep -v template
|
|
46
|
+
ls docs/ui-spec/*.md 2>/dev/null
|
|
41
47
|
```
|
|
42
48
|
|
|
49
|
+
Classify discovered documents by filename:
|
|
50
|
+
- Filename contains `backend` → **Design Doc (backend)**
|
|
51
|
+
- Filename contains `frontend` → **Design Doc (frontend)**
|
|
52
|
+
- Located in `docs/ui-spec/` → **UI Spec** (optional)
|
|
53
|
+
- None of the above → **single-layer Design Doc** (layer TBD in gate below)
|
|
54
|
+
|
|
55
|
+
**[GATE] Present classification results to user as candidates and ask for confirmation before proceeding.** The user may exclude irrelevant documents discovered by the automatic search. If a single-layer Design Doc is detected, ask the user whether it targets backend or frontend to determine correct agent routing.
|
|
56
|
+
|
|
43
57
|
### Step 2: Skeleton Generation
|
|
44
58
|
|
|
45
|
-
Invoke acceptance-test-generator
|
|
59
|
+
Invoke acceptance-test-generator **once per Design Doc** (the agent expects a single designDocPath):
|
|
60
|
+
|
|
61
|
+
For each Design Doc from Step 1:
|
|
46
62
|
- `subagent_type`: "acceptance-test-generator"
|
|
47
|
-
- `description`: "Generate test skeletons"
|
|
48
|
-
- `prompt`: "Generate test skeletons from Design Doc at [path
|
|
63
|
+
- `description`: "Generate test skeletons for [layer/name]"
|
|
64
|
+
- `prompt`: "Generate test skeletons from Design Doc at [path]." + If UI Spec exists: "UI Spec at [ui-spec path] is available as additional context."
|
|
49
65
|
|
|
50
|
-
**Expected output**: `generatedFiles` containing integration and e2e paths
|
|
66
|
+
**Expected output per invocation**: `generatedFiles` containing integration and e2e paths
|
|
51
67
|
|
|
52
|
-
### Step 3: Create Task
|
|
68
|
+
### Step 3: Create Task Files [GATE]
|
|
53
69
|
|
|
54
|
-
Create task file
|
|
70
|
+
Create one task file per layer, using the monorepo-flow.md naming convention for deterministic agent routing:
|
|
71
|
+
- Backend Design Doc → `docs/plans/tasks/integration-tests-backend-task-YYYYMMDD.md`
|
|
72
|
+
- Frontend Design Doc → `docs/plans/tasks/integration-tests-frontend-task-YYYYMMDD.md`
|
|
73
|
+
- Single-layer confirmed as backend → `docs/plans/tasks/integration-tests-backend-task-YYYYMMDD.md`
|
|
74
|
+
- Single-layer confirmed as frontend → `docs/plans/tasks/integration-tests-frontend-task-YYYYMMDD.md`
|
|
55
75
|
|
|
56
|
-
**Template
|
|
76
|
+
**Template** (per task file):
|
|
57
77
|
```markdown
|
|
58
78
|
---
|
|
59
|
-
name: Implement integration tests for [feature name]
|
|
79
|
+
name: Implement [layer] integration tests for [feature name]
|
|
60
80
|
type: test-implementation
|
|
61
81
|
---
|
|
62
82
|
|
|
@@ -66,8 +86,8 @@ Implement test cases defined in skeleton files.
|
|
|
66
86
|
|
|
67
87
|
## Target Files
|
|
68
88
|
|
|
69
|
-
- Skeleton: [
|
|
70
|
-
- Design Doc: [
|
|
89
|
+
- Skeleton: [layer-specific paths from Step 2 generatedFiles]
|
|
90
|
+
- Design Doc: [layer-specific Design Doc from Step 1]
|
|
71
91
|
|
|
72
92
|
## Tasks
|
|
73
93
|
|
|
@@ -82,14 +102,17 @@ Implement test cases defined in skeleton files.
|
|
|
82
102
|
- No quality issues
|
|
83
103
|
```
|
|
84
104
|
|
|
85
|
-
**Output**: "Task file created at [path]. Ready for Step 4."
|
|
105
|
+
**Output**: "Task file(s) created at [path(s)]. Ready for Step 4."
|
|
86
106
|
|
|
87
107
|
### Step 4: Test Implementation
|
|
88
108
|
|
|
89
|
-
|
|
90
|
-
- `subagent_type`: "task-executor"
|
|
109
|
+
For each task file from Step 3, invoke task-executor routed by filename pattern:
|
|
110
|
+
- `*-backend-task-*` → `subagent_type`: "task-executor"
|
|
111
|
+
- `*-frontend-task-*` → `subagent_type`: "task-executor-frontend"
|
|
91
112
|
- `description`: "Implement integration tests"
|
|
92
|
-
- `prompt`: "Task file:
|
|
113
|
+
- `prompt`: "Task file: [task file path from Step 3]. Implement tests following the task file."
|
|
114
|
+
|
|
115
|
+
Execute one task file at a time through Steps 4→5→6→7 before starting the next.
|
|
93
116
|
|
|
94
117
|
**Expected output**: `status`, `testsAdded`
|
|
95
118
|
|
|
@@ -98,7 +121,7 @@ Invoke task-executor using Agent tool:
|
|
|
98
121
|
Invoke integration-test-reviewer using Agent tool:
|
|
99
122
|
- `subagent_type`: "integration-test-reviewer"
|
|
100
123
|
- `description`: "Review test quality"
|
|
101
|
-
- `prompt`: "Review test quality. Test files: [paths from Step 4 testsAdded]. Skeleton files: [paths from Step 2 generatedFiles]"
|
|
124
|
+
- `prompt`: "Review test quality. Test files: [paths from Step 4 testsAdded]. Skeleton files: [layer-specific paths from Step 2 generatedFiles matching current task's layer]"
|
|
102
125
|
|
|
103
126
|
**Expected output**: `status` (approved/needs_revision), `requiredFixes`
|
|
104
127
|
|
|
@@ -108,15 +131,17 @@ Check Step 5 result:
|
|
|
108
131
|
- `status: approved` → Mark complete, proceed to Step 7
|
|
109
132
|
- `status: needs_revision` → Invoke task-executor with requiredFixes, then return to Step 5
|
|
110
133
|
|
|
111
|
-
Invoke task-executor
|
|
112
|
-
- `subagent_type`: "task-executor"
|
|
134
|
+
Invoke task-executor routed by task filename pattern:
|
|
135
|
+
- `*-backend-task-*` → `subagent_type`: "task-executor"
|
|
136
|
+
- `*-frontend-task-*` → `subagent_type`: "task-executor-frontend"
|
|
113
137
|
- `description`: "Fix review findings"
|
|
114
138
|
- `prompt`: "Fix the following issues in test files: [requiredFixes from Step 5]"
|
|
115
139
|
|
|
116
140
|
### Step 7: Quality Check
|
|
117
141
|
|
|
118
|
-
Invoke quality-fixer
|
|
119
|
-
- `subagent_type`: "quality-fixer"
|
|
142
|
+
Invoke quality-fixer routed by task filename pattern:
|
|
143
|
+
- `*-backend-task-*` → `subagent_type`: "quality-fixer"
|
|
144
|
+
- `*-frontend-task-*` → `subagent_type`: "quality-fixer-frontend"
|
|
120
145
|
- `description`: "Final quality assurance"
|
|
121
146
|
- `prompt`: "Final quality assurance for test files added in this workflow. Run all tests and verify coverage."
|
|
122
147
|
|
|
@@ -35,7 +35,8 @@ Analyze task file existence state and determine the action required:
|
|
|
35
35
|
|-------|----------|-------------|
|
|
36
36
|
| Tasks exist | .md files in tasks/ directory | User's execution instruction serves as batch approval → Enter autonomous execution immediately |
|
|
37
37
|
| No tasks + plan exists | Plan exists but no task files | Confirm with user → run task-decomposer |
|
|
38
|
-
| Neither exists | No plan or task files |
|
|
38
|
+
| Neither exists + Design Doc exists | No plan or task files, but docs/design/*.md exists | Invoke work-planner to create work plan from Design Doc, then proceed to task decomposition |
|
|
39
|
+
| Neither exists | No plan, no task files, no Design Doc | Report missing prerequisites to user and stop |
|
|
39
40
|
|
|
40
41
|
## Task Decomposition Phase (Conditional)
|
|
41
42
|
|
|
@@ -42,7 +42,8 @@ Analyze task file existence state and determine the action required:
|
|
|
42
42
|
|-------|----------|-------------|
|
|
43
43
|
| Tasks exist | .md files in tasks/ directory | User's execution instruction serves as batch approval → Enter autonomous execution immediately |
|
|
44
44
|
| No tasks + plan exists | Plan exists but no task files | Confirm with user → run task-decomposer |
|
|
45
|
-
| Neither exists | No plan or task files |
|
|
45
|
+
| Neither exists + Design Doc exists | No plan or task files, but docs/design/*.md exists | Invoke work-planner to create work plan from Design Doc, then proceed to task decomposition |
|
|
46
|
+
| Neither exists | No plan, no task files, no Design Doc | Report missing prerequisites to user and stop |
|
|
46
47
|
|
|
47
48
|
## Task Decomposition Phase (Conditional)
|
|
48
49
|
|
|
@@ -44,7 +44,7 @@ Invoke acceptance-test-generator using Agent tool:
|
|
|
44
44
|
Invoke work-planner using Agent tool:
|
|
45
45
|
- `subagent_type`: "work-planner"
|
|
46
46
|
- `description`: "Work plan creation"
|
|
47
|
-
- `prompt`: "Create work plan from Design Doc at [path]. Integration test file: [path from step 2]. E2E test file: [path from step 2]. Integration tests are created simultaneously with each phase implementation, E2E tests are executed only in final phase."
|
|
47
|
+
- `prompt`: "Create work plan from Design Doc at [path]. Integration test file: [integration test path from step 2]. E2E test file: [E2E test path from step 2]. Integration tests are created simultaneously with each phase implementation, E2E tests are executed only in final phase."
|
|
48
48
|
|
|
49
49
|
Interact with user to complete plan and obtain approval for plan content. Clarify specific implementation steps and risks.
|
|
50
50
|
|
|
@@ -87,7 +87,7 @@ After all task cycles finish, invoke security-reviewer before the completion rep
|
|
|
87
87
|
- `blocked` → Escalate to user
|
|
88
88
|
|
|
89
89
|
### Test Information Communication
|
|
90
|
-
After acceptance-test-generator execution, when
|
|
90
|
+
After acceptance-test-generator execution, when invoking work-planner (subagent_type: "work-planner"), communicate:
|
|
91
91
|
- Generated integration test file path
|
|
92
92
|
- Generated E2E test file path
|
|
93
93
|
- Explicit note that integration tests run with implementation, E2E tests run after all implementations
|
|
@@ -42,8 +42,15 @@ Follow subagents-orchestration-guide skill strictly and create work plan with th
|
|
|
42
42
|
- Pass generation results to next process according to subagents-orchestration-guide skill coordination specification
|
|
43
43
|
|
|
44
44
|
3. **Work Plan Creation**
|
|
45
|
-
|
|
46
|
-
-
|
|
45
|
+
Invoke work-planner using Agent tool:
|
|
46
|
+
- `subagent_type`: "work-planner"
|
|
47
|
+
- `description`: "Work plan creation"
|
|
48
|
+
- If test skeletons were generated in Step 2:
|
|
49
|
+
`prompt`: "Create work plan from Design Doc at [path]. Integration test file: [integration test path from step 2]. E2E test file: [E2E test path from step 2]. Integration tests are created simultaneously with each phase implementation, E2E tests are executed only in final phase."
|
|
50
|
+
- If test skeletons were not generated:
|
|
51
|
+
`prompt`: "Create work plan from Design Doc at [path]."
|
|
52
|
+
|
|
53
|
+
- Follow subagents-orchestration-guide Prompt Construction Rule for additional prompt parameters
|
|
47
54
|
- Interact with user to complete plan and obtain approval for plan content
|
|
48
55
|
|
|
49
56
|
Create a work plan from the selected design document, clarifying specific implementation steps and risks.
|
|
@@ -1,10 +1,8 @@
|
|
|
1
1
|
---
|
|
2
|
-
description: Design Doc
|
|
2
|
+
description: Design Docを使用して既存コードベースに統合/E2Eテストを追加
|
|
3
3
|
---
|
|
4
4
|
|
|
5
|
-
**コマンドコンテキスト**:
|
|
6
|
-
|
|
7
|
-
**スコープ**: バックエンドのみ(acceptance-test-generatorはバックエンドのみ対応)
|
|
5
|
+
**コマンドコンテキスト**: 既存実装へのテスト追加ワークフロー(バックエンド、フロントエンド、フルスタック対応)
|
|
8
6
|
|
|
9
7
|
## オーケストレーター定義
|
|
10
8
|
|
|
@@ -12,7 +10,7 @@ description: Design Docを使用して既存バックエンドコードベース
|
|
|
12
10
|
|
|
13
11
|
**初動アクション**: ステップ0-8をTaskCreateで登録してから実行を開始。
|
|
14
12
|
|
|
15
|
-
**委譲理由**:
|
|
13
|
+
**委譲理由**: オーケストレーターのコンテキストは全ステップで共有される。直接実装するとレビューや品質チェックに必要なコンテキストを消費してしまう。タスクファイルをコンテキスト境界とし、サブエージェントが隔離されたコンテキストで作業することでこれを回避する。
|
|
16
14
|
|
|
17
15
|
**実行方法**:
|
|
18
16
|
- スケルトン生成 → acceptance-test-generatorに委譲
|
|
@@ -21,10 +19,11 @@ description: Design Docを使用して既存バックエンドコードベース
|
|
|
21
19
|
- テストレビュー → integration-test-reviewerに委譲
|
|
22
20
|
- 品質チェック → quality-fixerに委譲
|
|
23
21
|
|
|
24
|
-
|
|
22
|
+
ドキュメントパス: $ARGUMENTS
|
|
25
23
|
|
|
26
24
|
## 前提条件
|
|
27
|
-
|
|
25
|
+
|
|
26
|
+
- Design Docが少なくとも1つ存在すること(手動またはreverse-engineerで作成)
|
|
28
27
|
- テスト対象の既存実装があること
|
|
29
28
|
|
|
30
29
|
## 実行フロー
|
|
@@ -33,30 +32,51 @@ Design Docパス: $ARGUMENTS
|
|
|
33
32
|
|
|
34
33
|
スキル実行: documentation-criteria(ステップ3のタスクファイルテンプレート用)
|
|
35
34
|
|
|
36
|
-
### ステップ1:
|
|
35
|
+
### ステップ1: ドキュメントの探索と検証
|
|
37
36
|
|
|
38
37
|
```bash
|
|
39
|
-
#
|
|
40
|
-
|
|
38
|
+
# ドキュメントパスが指定されているか確認
|
|
39
|
+
test -n "$ARGUMENTS" || { echo "ERROR: ドキュメントパスが指定されていません"; exit 1; }
|
|
40
|
+
|
|
41
|
+
# 指定パスの存在確認
|
|
42
|
+
ls $ARGUMENTS
|
|
43
|
+
|
|
44
|
+
# 追加ドキュメントの探索
|
|
45
|
+
ls docs/design/*.md 2>/dev/null | grep -v template
|
|
46
|
+
ls docs/ui-spec/*.md 2>/dev/null
|
|
41
47
|
```
|
|
42
48
|
|
|
49
|
+
探索されたドキュメントをファイル名で分類:
|
|
50
|
+
- ファイル名に`backend`を含む → **Design Doc(バックエンド)**
|
|
51
|
+
- ファイル名に`frontend`を含む → **Design Doc(フロントエンド)**
|
|
52
|
+
- `docs/ui-spec/`配下 → **UI Spec**(任意)
|
|
53
|
+
- 上記いずれにも該当しない → **単一レイヤーのDesign Doc**(レイヤーは下記のゲートで確定)
|
|
54
|
+
|
|
55
|
+
**[GATE] 分類結果を候補としてユーザーに提示し、続行前に確認を得る。** 自動探索で検出された無関係なドキュメントはユーザーが除外できる。単一レイヤーのDesign Docが検出された場合、バックエンドとフロントエンドのどちらを対象とするかユーザーに確認し、正しいエージェントルーティングを決定する。
|
|
56
|
+
|
|
43
57
|
### ステップ2: スケルトン生成
|
|
44
58
|
|
|
45
|
-
|
|
59
|
+
**Design Docごとに**acceptance-test-generatorを呼び出す(エージェントは単一のdesignDocPathを前提とするため):
|
|
60
|
+
|
|
61
|
+
各Design Docに対して:
|
|
46
62
|
- `subagent_type`: "acceptance-test-generator"
|
|
47
|
-
- `description`: "
|
|
48
|
-
- `prompt`: "[
|
|
63
|
+
- `description`: "[レイヤー/名称]のテストスケルトン生成"
|
|
64
|
+
- `prompt`: "[パス]のDesign Docからテストスケルトンを生成。" + UI Specが存在する場合: "[UI Specパス]のUI Specを追加コンテキストとして利用可能。"
|
|
49
65
|
|
|
50
|
-
|
|
66
|
+
**呼び出しごとの期待出力**: `generatedFiles`(統合テストとE2Eのパスを含む)
|
|
51
67
|
|
|
52
68
|
### ステップ3: タスクファイル作成 [GATE]
|
|
53
69
|
|
|
54
|
-
|
|
70
|
+
レイヤーごとに1つのタスクファイルを作成。monorepo-flow.mdの命名規則に従い、エージェントルーティングを決定的にする:
|
|
71
|
+
- バックエンドのDesign Doc → `docs/plans/tasks/integration-tests-backend-task-YYYYMMDD.md`
|
|
72
|
+
- フロントエンドのDesign Doc → `docs/plans/tasks/integration-tests-frontend-task-YYYYMMDD.md`
|
|
73
|
+
- 単一レイヤー(バックエンド確定) → `docs/plans/tasks/integration-tests-backend-task-YYYYMMDD.md`
|
|
74
|
+
- 単一レイヤー(フロントエンド確定) → `docs/plans/tasks/integration-tests-frontend-task-YYYYMMDD.md`
|
|
55
75
|
|
|
56
|
-
|
|
76
|
+
**テンプレート**(タスクファイルごと):
|
|
57
77
|
```markdown
|
|
58
78
|
---
|
|
59
|
-
name: [機能名]
|
|
79
|
+
name: [機能名]の[レイヤー]統合テスト実装
|
|
60
80
|
type: test-implementation
|
|
61
81
|
---
|
|
62
82
|
|
|
@@ -66,8 +86,8 @@ type: test-implementation
|
|
|
66
86
|
|
|
67
87
|
## 対象ファイル
|
|
68
88
|
|
|
69
|
-
- スケルトン: [ステップ2のgeneratedFiles
|
|
70
|
-
- Design Doc: [ステップ1
|
|
89
|
+
- スケルトン: [ステップ2のgeneratedFilesからレイヤー別パス]
|
|
90
|
+
- Design Doc: [ステップ1のレイヤー別Design Doc]
|
|
71
91
|
|
|
72
92
|
## タスク
|
|
73
93
|
|
|
@@ -82,14 +102,17 @@ type: test-implementation
|
|
|
82
102
|
- 品質チェック全項目パス
|
|
83
103
|
```
|
|
84
104
|
|
|
85
|
-
**出力**: "タスクファイルを[
|
|
105
|
+
**出力**: "タスクファイルを[パス(複数の場合は全パス)]に作成しました。ステップ4へ進む準備完了。"
|
|
86
106
|
|
|
87
107
|
### ステップ4: テスト実装
|
|
88
108
|
|
|
89
|
-
|
|
90
|
-
- `subagent_type`: "task-executor"
|
|
109
|
+
ステップ3の各タスクファイルに対し、ファイル名パターンでルーティングしてtask-executorを呼び出す:
|
|
110
|
+
- `*-backend-task-*` → `subagent_type`: "task-executor"
|
|
111
|
+
- `*-frontend-task-*` → `subagent_type`: "task-executor-frontend"
|
|
91
112
|
- `description`: "統合テスト実装"
|
|
92
|
-
- `prompt`: "タスクファイル:
|
|
113
|
+
- `prompt`: "タスクファイル: [ステップ3のタスクファイルパス]。タスクファイルに従ってテストを実装。"
|
|
114
|
+
|
|
115
|
+
1つのタスクファイルにつきステップ4→5→6→7を完了してから次に進む。
|
|
93
116
|
|
|
94
117
|
**期待される出力**: `status`, `testsAdded`
|
|
95
118
|
|
|
@@ -98,7 +121,7 @@ Agentツールでtask-executorを呼び出す:
|
|
|
98
121
|
Agentツールでintegration-test-reviewerを呼び出す:
|
|
99
122
|
- `subagent_type`: "integration-test-reviewer"
|
|
100
123
|
- `description`: "テスト品質レビュー"
|
|
101
|
-
- `prompt`: "テスト品質をレビュー。テストファイル: [ステップ4のtestsAdded]。スケルトンファイル: [ステップ2のgeneratedFiles]"
|
|
124
|
+
- `prompt`: "テスト品質をレビュー。テストファイル: [ステップ4のtestsAdded]。スケルトンファイル: [ステップ2のgeneratedFilesから現在のタスクのレイヤーに該当するパス]"
|
|
102
125
|
|
|
103
126
|
**期待される出力**: `status` (approved/needs_revision), `requiredFixes`
|
|
104
127
|
|
|
@@ -108,15 +131,17 @@ Agentツールでintegration-test-reviewerを呼び出す:
|
|
|
108
131
|
- `status: approved` → 完了としてマーク、ステップ7へ進む
|
|
109
132
|
- `status: needs_revision` → requiredFixesでtask-executorを呼び出し、ステップ5に戻る
|
|
110
133
|
|
|
111
|
-
|
|
112
|
-
- `subagent_type`: "task-executor"
|
|
134
|
+
タスクファイル名パターンでルーティングしてtask-executorを呼び出す:
|
|
135
|
+
- `*-backend-task-*` → `subagent_type`: "task-executor"
|
|
136
|
+
- `*-frontend-task-*` → `subagent_type`: "task-executor-frontend"
|
|
113
137
|
- `description`: "レビュー指摘の修正"
|
|
114
138
|
- `prompt`: "テストファイルの以下の問題を修正: [ステップ5のrequiredFixes]"
|
|
115
139
|
|
|
116
140
|
### ステップ7: 品質チェック
|
|
117
141
|
|
|
118
|
-
|
|
119
|
-
- `subagent_type`: "quality-fixer"
|
|
142
|
+
タスクファイル名パターンでルーティングしてquality-fixerを呼び出す:
|
|
143
|
+
- `*-backend-task-*` → `subagent_type`: "quality-fixer"
|
|
144
|
+
- `*-frontend-task-*` → `subagent_type`: "quality-fixer-frontend"
|
|
120
145
|
- `description`: "最終品質保証"
|
|
121
146
|
- `prompt`: "このワークフローで追加されたテストファイルの最終品質保証。全テストを実行しカバレッジを確認。"
|
|
122
147
|
|
|
@@ -35,7 +35,8 @@ description: 分解済みタスクを自律実行モードで実装
|
|
|
35
35
|
|------|---------|--------------|
|
|
36
36
|
| タスク存在 | tasks/ディレクトリに.mdファイルあり | ユーザーの実行指示をバッチ承認として自律実行へ移行 |
|
|
37
37
|
| タスクなし+計画書あり | 計画書は存在するがタスクファイルなし | ユーザーに確認 → task-decomposer実行 |
|
|
38
|
-
|
|
|
38
|
+
| 両方なし+Design Docあり | 計画書・タスクファイルなし、docs/design/*.mdあり | work-plannerでDesign Docから作業計画書を作成し、タスク分解へ進む |
|
|
39
|
+
| 両方なし | 計画書・タスクファイル・Design Docすべてなし | 前提条件未達成をユーザーに報告して停止 |
|
|
39
40
|
|
|
40
41
|
## タスク分解フェーズ(条件付き実行)
|
|
41
42
|
|
|
@@ -42,7 +42,8 @@ description: フロントエンド実装を自律実行モードで実行
|
|
|
42
42
|
|------|------|--------------|
|
|
43
43
|
| タスク存在 | tasks/ディレクトリに.mdファイルあり | ユーザーの実行指示をバッチ承認として自律実行へ移行 |
|
|
44
44
|
| タスクなし+計画あり | 計画書は存在するがタスクファイルなし | ユーザー確認 → task-decomposer実行 |
|
|
45
|
-
|
|
|
45
|
+
| どちらもなし+Design Docあり | 計画書・タスクファイルなし、docs/design/*.mdあり | work-plannerでDesign Docから作業計画書を作成し、タスク分解へ進む |
|
|
46
|
+
| どちらもなし | 計画書・タスクファイル・Design Docすべてなし | 前提条件未達成をユーザーに報告して停止 |
|
|
46
47
|
|
|
47
48
|
## タスク分解フェーズ(条件付き)
|
|
48
49
|
|
|
@@ -44,7 +44,7 @@ Agentツールで**acceptance-test-generator**を呼び出す:
|
|
|
44
44
|
Agentツールで**work-planner**を呼び出す:
|
|
45
45
|
- `subagent_type`: "work-planner"
|
|
46
46
|
- `description`: "作業計画書作成"
|
|
47
|
-
- `prompt`: "[パス]のDesign Docから作業計画を作成。統合テストファイル: [
|
|
47
|
+
- `prompt`: "[パス]のDesign Docから作業計画を作成。統合テストファイル: [ステップ2の統合テストパス]。E2Eテストファイル: [ステップ2のE2Eテストパス]。統合テストは各フェーズ実装と同時に作成、E2Eテストは最終フェーズでのみ実行。"
|
|
48
48
|
|
|
49
49
|
ユーザーと対話して計画を完成させ、計画内容の承認を得る。具体的な実装ステップとリスクを明確化。
|
|
50
50
|
|
|
@@ -87,7 +87,7 @@ subagents-orchestration-guideスキルの「自律実行中のタスク管理」
|
|
|
87
87
|
- `blocked` → ユーザーにエスカレーション
|
|
88
88
|
|
|
89
89
|
### テスト情報の伝達
|
|
90
|
-
acceptance-test-generator実行後、work-planner
|
|
90
|
+
acceptance-test-generator実行後、work-planner(subagent_type: "work-planner")呼び出し時には以下を伝達:
|
|
91
91
|
- 生成された統合テストファイルパス
|
|
92
92
|
- 生成されたE2Eテストファイルパス
|
|
93
93
|
- 統合テストは実装と同時、E2Eは全実装後に実行する旨の明示
|
|
@@ -42,8 +42,15 @@ description: 設計書から作業計画書を作成し計画承認を取得
|
|
|
42
42
|
- 生成結果を subagents-orchestration-guideスキル の連携仕様に従って次工程に引き継ぐ
|
|
43
43
|
|
|
44
44
|
3. **作業計画書の作成**
|
|
45
|
-
|
|
46
|
-
-
|
|
45
|
+
Agentツールでwork-plannerを呼び出す:
|
|
46
|
+
- `subagent_type`: "work-planner"
|
|
47
|
+
- `description`: "作業計画書作成"
|
|
48
|
+
- ステップ2でテストスケルトンを生成した場合:
|
|
49
|
+
`prompt`: "[パス]のDesign Docから作業計画を作成。統合テストファイル: [ステップ2の統合テストパス]。E2Eテストファイル: [ステップ2のE2Eテストパス]。統合テストは各フェーズ実装と同時に作成、E2Eテストは最終フェーズでのみ実行。"
|
|
50
|
+
- テストスケルトンを生成しなかった場合:
|
|
51
|
+
`prompt`: "[パス]のDesign Docから作業計画を作成。"
|
|
52
|
+
|
|
53
|
+
- subagents-orchestration-guideのプロンプト構成ルールに従い追加パラメータを設定
|
|
47
54
|
- ユーザーと対話して計画を完成させ、計画内容の承認を得る
|
|
48
55
|
|
|
49
56
|
選択された設計書から作業計画書を作成し、実装の具体的なステップとリスクを明確にします。
|
|
@@ -97,7 +97,7 @@ description: Guides PRD, ADR, Design Doc, and Work Plan creation. Use when creat
|
|
|
97
97
|
**Excludes**:
|
|
98
98
|
- Technical implementation details (-> Design Doc)
|
|
99
99
|
- API contracts and data layer design (-> Design Doc)
|
|
100
|
-
- Test implementation (->
|
|
100
|
+
- Test implementation (-> acceptance-test-generator skeletons)
|
|
101
101
|
- Implementation schedule (-> Work Plan)
|
|
102
102
|
|
|
103
103
|
**Required Structural Elements**:
|
|
@@ -123,7 +123,6 @@ description: Guides PRD, ADR, Design Doc, and Work Plan creation. Use when creat
|
|
|
123
123
|
- **Technical dependencies and implementation constraints** (required implementation order)
|
|
124
124
|
- Interface and type definitions
|
|
125
125
|
- Data flow and component design
|
|
126
|
-
- **E2E verification procedures at integration points**
|
|
127
126
|
- **Acceptance criteria (EARS format: When/While/If-then/none)**
|
|
128
127
|
- Change impact map (clearly specify direct impact/indirect impact/no ripple effect)
|
|
129
128
|
- Complete enumeration of integration points
|
|
@@ -147,7 +146,7 @@ description: Guides PRD, ADR, Design Doc, and Work Plan creation. Use when creat
|
|
|
147
146
|
**Includes**:
|
|
148
147
|
- Task breakdown and dependencies (maximum 2 levels)
|
|
149
148
|
- Schedule and duration estimates
|
|
150
|
-
- **
|
|
149
|
+
- **Include test skeleton file paths from acceptance-test-generator** (integration and E2E)
|
|
151
150
|
- **Phase 4 Quality Assurance Phase (required)**
|
|
152
151
|
- Progress records (checkbox format)
|
|
153
152
|
|
|
@@ -247,34 +247,15 @@ Invariants:
|
|
|
247
247
|
- Prerequisites: [Required pre-implementations]
|
|
248
248
|
|
|
249
249
|
### Integration Points
|
|
250
|
-
Each integration point requires E2E verification:
|
|
251
250
|
|
|
252
251
|
**Integration Point 1: [Name]**
|
|
253
252
|
- Components: [Component A] -> [Component B]
|
|
254
|
-
-
|
|
253
|
+
- Contract: [Interface/API contract between components]
|
|
255
254
|
|
|
256
255
|
### Migration Strategy
|
|
257
256
|
|
|
258
257
|
[Technical migration approach, ensuring backward compatibility]
|
|
259
258
|
|
|
260
|
-
## Test Strategy
|
|
261
|
-
|
|
262
|
-
### Unit Tests
|
|
263
|
-
|
|
264
|
-
[Unit testing policy and coverage goals]
|
|
265
|
-
- Verify individual elements of functional acceptance criteria
|
|
266
|
-
|
|
267
|
-
### Integration Tests
|
|
268
|
-
|
|
269
|
-
[Integration testing policy and important test cases]
|
|
270
|
-
- Verify combined operations of functional acceptance criteria
|
|
271
|
-
|
|
272
|
-
### E2E Tests
|
|
273
|
-
|
|
274
|
-
[E2E testing policy]
|
|
275
|
-
- Verify entire scenarios of acceptance criteria
|
|
276
|
-
- Confirm functional operation from user perspective
|
|
277
|
-
|
|
278
259
|
## Security Considerations
|
|
279
260
|
|
|
280
261
|
Evaluate the following for this feature's trust boundaries and data flow:
|
|
@@ -48,11 +48,6 @@ Related Issue/PR: #XXX (if any)
|
|
|
48
48
|
- [ ] [Functional completion criteria]
|
|
49
49
|
- [ ] [Quality completion criteria]
|
|
50
50
|
|
|
51
|
-
#### Operational Verification Procedures
|
|
52
|
-
1. [Operation verification steps]
|
|
53
|
-
2. [Expected result verification]
|
|
54
|
-
3. [Performance verification (when applicable)]
|
|
55
|
-
|
|
56
51
|
### Phase 2: [Phase Name] (Estimated commits: X)
|
|
57
52
|
**Purpose**: [What this phase aims to achieve]
|
|
58
53
|
|
|
@@ -66,11 +61,6 @@ Related Issue/PR: #XXX (if any)
|
|
|
66
61
|
- [ ] [Functional completion criteria]
|
|
67
62
|
- [ ] [Quality completion criteria]
|
|
68
63
|
|
|
69
|
-
#### Operational Verification Procedures
|
|
70
|
-
1. [Operation verification steps]
|
|
71
|
-
2. [Expected result verification]
|
|
72
|
-
3. [Performance verification (when applicable)]
|
|
73
|
-
|
|
74
64
|
### Phase 3: [Phase Name] (Estimated commits: X)
|
|
75
65
|
**Purpose**: [What this phase aims to achieve]
|
|
76
66
|
|
|
@@ -84,9 +74,6 @@ Related Issue/PR: #XXX (if any)
|
|
|
84
74
|
- [ ] [Functional completion criteria]
|
|
85
75
|
- [ ] [Quality completion criteria]
|
|
86
76
|
|
|
87
|
-
#### Operational Verification Procedures
|
|
88
|
-
[Copy relevant integration point E2E verification from Design Doc]
|
|
89
|
-
|
|
90
77
|
### Final Phase: Quality Assurance (Required) (Estimated commits: 1)
|
|
91
78
|
**Purpose**: Overall quality assurance and Design Doc consistency verification
|
|
92
79
|
|
|
@@ -94,13 +81,10 @@ Related Issue/PR: #XXX (if any)
|
|
|
94
81
|
- [ ] Verify all Design Doc acceptance criteria achieved
|
|
95
82
|
- [ ] Security review: Verify security considerations from Design Doc are implemented
|
|
96
83
|
- [ ] Quality checks (types, lint, format)
|
|
97
|
-
- [ ] Execute all tests
|
|
84
|
+
- [ ] Execute all tests (including integration/E2E from test skeletons, when provided)
|
|
98
85
|
- [ ] Coverage 70%+
|
|
99
86
|
- [ ] Document updates
|
|
100
87
|
|
|
101
|
-
#### Operational Verification Procedures
|
|
102
|
-
[Copy E2E verification procedures from Design Doc]
|
|
103
|
-
|
|
104
88
|
### Quality Assurance
|
|
105
89
|
- [ ] Implement staged quality checks (details: refer to technical-spec skill)
|
|
106
90
|
|
|
@@ -111,7 +95,7 @@ Related Issue/PR: #XXX (if any)
|
|
|
111
95
|
|
|
112
96
|
## Completion Criteria
|
|
113
97
|
- [ ] All phases completed
|
|
114
|
-
- [ ]
|
|
98
|
+
- [ ] All integration/E2E tests passing (when test skeletons provided)
|
|
115
99
|
- [ ] Design Doc acceptance criteria satisfied
|
|
116
100
|
- [ ] Staged quality checks completed (zero errors)
|
|
117
101
|
- [ ] All tests pass
|
|
@@ -151,7 +151,7 @@ According to scale determination:
|
|
|
151
151
|
|
|
152
152
|
### Small Scale (1-2 Files) - 2 Steps
|
|
153
153
|
|
|
154
|
-
1.
|
|
154
|
+
1. work-planner → Simplified work plan creation **[Stop: Batch approval]**
|
|
155
155
|
2. Direct implementation → Completion report
|
|
156
156
|
|
|
157
157
|
## Cross-Layer Orchestration
|
|
@@ -30,7 +30,7 @@ skills:
|
|
|
30
30
|
- "Red-Green-Refactor Process (Test-First Development)"
|
|
31
31
|
- "Test Design Principles"
|
|
32
32
|
- "Test Granularity Principles"
|
|
33
|
-
- "Security Principles
|
|
33
|
+
- "Security Principles"
|
|
34
34
|
|
|
35
35
|
typescript-rules:
|
|
36
36
|
skill: "typescript-rules"
|
|
@@ -230,6 +230,7 @@ skills:
|
|
|
230
230
|
- "Test Implementation Conventions"
|
|
231
231
|
- "Mock Type Safety Enforcement"
|
|
232
232
|
- "Basic React Testing Library Example"
|
|
233
|
+
- "Test Design Patterns"
|
|
233
234
|
|
|
234
235
|
frontend-technical-spec:
|
|
235
236
|
skill: "frontend-technical-spec"
|
|
@@ -97,7 +97,7 @@ description: PRD、ADR、Design Doc、作業計画書の作成を支援。技術
|
|
|
97
97
|
**含まないもの**:
|
|
98
98
|
- 技術実装詳細(→ Design Doc)
|
|
99
99
|
- APIコントラクトとデータレイヤー設計(→ Design Doc)
|
|
100
|
-
- テスト実装(→
|
|
100
|
+
- テスト実装(→ acceptance-test-generatorのスケルトン)
|
|
101
101
|
- 実装スケジュール(→ 作業計画書)
|
|
102
102
|
|
|
103
103
|
**必須構造要素**:
|
|
@@ -123,7 +123,6 @@ description: PRD、ADR、Design Doc、作業計画書の作成を支援。技術
|
|
|
123
123
|
- **技術的依存関係と実装制約**(実装の必要順序)
|
|
124
124
|
- インターフェース定義と型定義
|
|
125
125
|
- データフローとコンポーネント設計
|
|
126
|
-
- **統合ポイントでのE2E確認手順**
|
|
127
126
|
- **受入条件(EARS形式: When/While/If-then/無印)**
|
|
128
127
|
- 変更影響マップ(直接影響/間接影響/波及なしを明記)
|
|
129
128
|
- 統合点の完全な列挙
|
|
@@ -163,7 +162,7 @@ description: PRD、ADR、Design Doc、作業計画書の作成を支援。技術
|
|
|
163
162
|
- **フェーズ構成**(Design Docの技術的依存関係を基に作成)
|
|
164
163
|
- タスク分解と依存関係(最大2階層まで)
|
|
165
164
|
- スケジュールと期間見積もり
|
|
166
|
-
- **
|
|
165
|
+
- **acceptance-test-generatorのテストスケルトンファイルパスを配置**(統合テスト・E2E)
|
|
167
166
|
- **最終フェーズに品質保証を含む**(必須)
|
|
168
167
|
- 進捗記録(チェックボックス形式)
|
|
169
168
|
|
|
@@ -247,34 +247,15 @@ unknowns:
|
|
|
247
247
|
- 前提条件: [事前に必要な実装]
|
|
248
248
|
|
|
249
249
|
### 統合ポイント
|
|
250
|
-
各統合ポイントでE2E確認が必要:
|
|
251
250
|
|
|
252
251
|
**統合ポイント1: [名称]**
|
|
253
252
|
- コンポーネント: [コンポーネントA] -> [コンポーネントB]
|
|
254
|
-
-
|
|
253
|
+
- コントラクト: [コンポーネント間のインターフェース/API契約]
|
|
255
254
|
|
|
256
255
|
### 移行戦略
|
|
257
256
|
|
|
258
257
|
[技術的な移行アプローチ、後方互換性の確保方法]
|
|
259
258
|
|
|
260
|
-
## テスト戦略
|
|
261
|
-
|
|
262
|
-
### 単体テスト
|
|
263
|
-
|
|
264
|
-
[単体テストの方針とカバレッジ目標]
|
|
265
|
-
- 機能受入条件の個別要素を検証
|
|
266
|
-
|
|
267
|
-
### 統合テスト
|
|
268
|
-
|
|
269
|
-
[統合テストの方針と重要なテストケース]
|
|
270
|
-
- 機能受入条件の組み合わせ動作を検証
|
|
271
|
-
|
|
272
|
-
### E2Eテスト
|
|
273
|
-
|
|
274
|
-
[E2Eテストの方針]
|
|
275
|
-
- 受入条件のシナリオ全体を検証
|
|
276
|
-
- ユーザー視点での機能動作を確認
|
|
277
|
-
|
|
278
259
|
## セキュリティ考慮事項
|
|
279
260
|
|
|
280
261
|
この機能の信頼境界とデータフローについて以下を評価:
|
|
@@ -48,11 +48,6 @@
|
|
|
48
48
|
- [ ] [機能完了条件]
|
|
49
49
|
- [ ] [品質完了条件]
|
|
50
50
|
|
|
51
|
-
#### 動作確認手順
|
|
52
|
-
1. [動作確認ステップ]
|
|
53
|
-
2. [期待結果の確認]
|
|
54
|
-
3. [パフォーマンス確認(該当する場合)]
|
|
55
|
-
|
|
56
51
|
### Phase 2: [フェーズ名](想定コミット数: X)
|
|
57
52
|
**目的**: [このフェーズで達成すること]
|
|
58
53
|
|
|
@@ -66,11 +61,6 @@
|
|
|
66
61
|
- [ ] [機能完了条件]
|
|
67
62
|
- [ ] [品質完了条件]
|
|
68
63
|
|
|
69
|
-
#### 動作確認手順
|
|
70
|
-
1. [動作確認ステップ]
|
|
71
|
-
2. [期待結果の確認]
|
|
72
|
-
3. [パフォーマンス確認(該当する場合)]
|
|
73
|
-
|
|
74
64
|
### Phase 3: [フェーズ名](想定コミット数: X)
|
|
75
65
|
**目的**: [このフェーズで達成すること]
|
|
76
66
|
|
|
@@ -84,9 +74,6 @@
|
|
|
84
74
|
- [ ] [機能完了条件]
|
|
85
75
|
- [ ] [品質完了条件]
|
|
86
76
|
|
|
87
|
-
#### 動作確認手順
|
|
88
|
-
[Design Docの該当する統合ポイントE2E確認をコピー]
|
|
89
|
-
|
|
90
77
|
### 最終Phase: 品質保証(必須)(想定コミット数: 1)
|
|
91
78
|
**目的**: 全体品質保証とDesign Doc整合性検証
|
|
92
79
|
|
|
@@ -94,13 +81,10 @@
|
|
|
94
81
|
- [ ] Design Docの全受入条件達成を確認
|
|
95
82
|
- [ ] セキュリティレビュー: Design Docのセキュリティ考慮事項が実装されていることを確認
|
|
96
83
|
- [ ] 品質チェック(型、lint、format)
|
|
97
|
-
- [ ]
|
|
84
|
+
- [ ] 全テスト実行(テストスケルトン提供時は統合/E2Eテスト含む)
|
|
98
85
|
- [ ] カバレッジ70%以上
|
|
99
86
|
- [ ] ドキュメント更新
|
|
100
87
|
|
|
101
|
-
#### 動作確認手順
|
|
102
|
-
[Design DocからE2E確認手順をコピー]
|
|
103
|
-
|
|
104
88
|
### 品質保証
|
|
105
89
|
- [ ] 段階的品質チェック実施(詳細: technical-specスキル参照)
|
|
106
90
|
|
|
@@ -111,7 +95,7 @@
|
|
|
111
95
|
|
|
112
96
|
## 完了条件
|
|
113
97
|
- [ ] 全フェーズ完了
|
|
114
|
-
- [ ]
|
|
98
|
+
- [ ] 全統合/E2Eテストがパス(テストスケルトン提供時)
|
|
115
99
|
- [ ] Design Docの受入条件を満たす
|
|
116
100
|
- [ ] 段階的品質チェック完了(エラー0件)
|
|
117
101
|
- [ ] 全テストパス
|
|
@@ -212,14 +212,13 @@ skills:
|
|
|
212
212
|
- "ADR-0002 Co-location原則"
|
|
213
213
|
- "references/e2e.md - Playwright E2Eパターン"
|
|
214
214
|
sections:
|
|
215
|
-
- "References"
|
|
216
215
|
- "テストフレームワーク"
|
|
217
216
|
- "テストの基本方針"
|
|
218
217
|
- "テストの実装規約"
|
|
219
218
|
- "モックの型安全性の徹底"
|
|
220
219
|
- "React Testing Libraryの基本例"
|
|
221
220
|
- "テスト品質基準"
|
|
222
|
-
- "
|
|
221
|
+
- "テスト設計パターン"
|
|
223
222
|
|
|
224
223
|
frontend-technical-spec:
|
|
225
224
|
skill: "frontend-technical-spec"
|
package/CHANGELOG.md
CHANGED
|
@@ -5,6 +5,45 @@ All notable changes to this project will be documented in this file.
|
|
|
5
5
|
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
|
|
6
6
|
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
|
|
7
7
|
|
|
8
|
+
## [1.18.4] - 2026-03-28
|
|
9
|
+
|
|
10
|
+
### Fixed
|
|
11
|
+
|
|
12
|
+
#### Work-Planner Invocation Clarity
|
|
13
|
+
- `subagents-orchestration-guide`: Small Scale flow now explicitly names work-planner agent
|
|
14
|
+
- `plan` command: Step 3 rewritten with explicit `subagent_type` and conditional prompt branching (with/without test skeletons)
|
|
15
|
+
- `front-plan` command: Differentiate placeholder names (`[integration test path]` / `[E2E test path]` instead of identical `[path from step 2]`)
|
|
16
|
+
- `build` / `front-build` commands: Split "Neither exists" state into Design Doc present (invoke work-planner) vs absent (report and stop)
|
|
17
|
+
- `implement` command: Add explicit `subagent_type: "work-planner"` to test information communication section
|
|
18
|
+
|
|
19
|
+
#### Skills Index Sync
|
|
20
|
+
- `skills-index.yaml` (en): Remove stale parenthetical from coding-standards Security Principles section name
|
|
21
|
+
- `skills-index.yaml` (en): Add missing `Test Design Patterns` section to frontend-typescript-testing
|
|
22
|
+
- `skills-index.yaml` (ja): Remove stale `References` and `アンチパターン` sections from frontend-typescript-testing, add missing `テスト設計パターン`
|
|
23
|
+
|
|
24
|
+
## [1.18.3] - 2026-03-26
|
|
25
|
+
|
|
26
|
+
### Changed
|
|
27
|
+
|
|
28
|
+
#### Test Workflow: Skeleton-Based Single Source of Truth
|
|
29
|
+
- `design-template`: Remove Test Strategy section — test design responsibility moved to acceptance-test-generator skeletons
|
|
30
|
+
- `design-template`: Integration Points change from Verification to Contract (interface/API contract)
|
|
31
|
+
- `plan-template`: Remove Operational Verification Procedures from all phases — replaced by test skeleton file path references
|
|
32
|
+
- `plan-template`: Completion criteria updated to reference skeleton-based test results
|
|
33
|
+
- `work-planner`: Replace operational verification with test skeleton placement rules (integration tests in corresponding phases, E2E in final phase)
|
|
34
|
+
- `work-planner`: Add fallback for when test skeletons are not provided (AC-based test planning)
|
|
35
|
+
- `documentation-criteria`: Design Doc definition removes E2E verification; Work Plan references skeleton file paths
|
|
36
|
+
- `task-decomposer`: Phase completion content references skeleton file paths instead of copying E2E verification from Design Doc
|
|
37
|
+
- `technical-designer` / `technical-designer-frontend`: Replace E2E verification checklist with testable AC quality gate (concrete trigger, action, expected result)
|
|
38
|
+
- `technical-designer-frontend`: Add typescript-testing skill with Applying to Implementation entry
|
|
39
|
+
|
|
40
|
+
#### add-integration-tests: Fullstack Support
|
|
41
|
+
- Support backend, frontend, and fullstack test generation (previously backend-only)
|
|
42
|
+
- Document discovery with filename-based classification and user confirmation GATE
|
|
43
|
+
- Per-Design-Doc skeleton generation (aligned with acceptance-test-generator single-doc contract)
|
|
44
|
+
- Layer-specific task file naming for deterministic agent routing (`*-backend-task-*` / `*-frontend-task-*`)
|
|
45
|
+
- Input validation for empty arguments
|
|
46
|
+
|
|
8
47
|
## [1.18.2] - 2026-03-26
|
|
9
48
|
|
|
10
49
|
### Changed
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "create-ai-project",
|
|
3
|
-
"version": "1.18.
|
|
3
|
+
"version": "1.18.4",
|
|
4
4
|
"packageManager": "npm@10.8.2",
|
|
5
5
|
"description": "TypeScript boilerplate with skills and sub-agents for Claude Code. Prevents context exhaustion through role-based task splitting.",
|
|
6
6
|
"keywords": [
|