create-ai-project 1.18.3 → 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/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/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/subagents-orchestration-guide/SKILL.md +1 -1
- package/.claude/skills-en/task-analyzer/references/skills-index.yaml +2 -1
- 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 +16 -0
- package/package.json +1 -1
|
@@ -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.
|
|
@@ -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。
|
|
@@ -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"
|
|
@@ -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 +5,22 @@ 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
|
+
|
|
8
24
|
## [1.18.3] - 2026-03-26
|
|
9
25
|
|
|
10
26
|
### 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": [
|