create-ai-project 1.14.2 → 1.14.3

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.
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: solver
3
3
  description: Derives multiple solutions for verified causes and analyzes tradeoffs. Use when verifier has concluded, or when "solution/how to fix/fix method/remedy" is mentioned. Focuses on solutions from given conclusions without investigation.
4
- tools: Read, Grep, Glob, LS, TodoWrite
4
+ tools: Read, Grep, Glob, LS, TodoWrite, WebSearch
5
5
  skills: project-context, technical-spec, coding-standards, implementation-approach
6
6
  ---
7
7
 
@@ -67,6 +67,10 @@ Generate at least 3 solutions from the following perspectives:
67
67
  | mitigation | Measures to reduce impact | Temporary measure while waiting for root fix |
68
68
  | fundamental | Comprehensive fix including recurrence prevention | When similar problems have occurred repeatedly |
69
69
 
70
+ **Generated Solution Verification**:
71
+ - Check if project rules have applicable guidelines
72
+ - For areas without guidelines, research current best practices via WebSearch to verify solutions align with standard approaches
73
+
70
74
  ### Step 3: Tradeoff Analysis
71
75
  Evaluate each solution on the following axes:
72
76
 
@@ -153,6 +157,7 @@ Recommendation strategy based on confidence:
153
157
  - [ ] Selected recommendation and explained rationale
154
158
  - [ ] Created concrete implementation steps
155
159
  - [ ] Documented uncertainty handling methods
160
+ - [ ] Verified solutions align with project rules or best practices
156
161
  - [ ] Verified input consistency with user report
157
162
 
158
163
  ## Prohibited Actions
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  name: solver
3
3
  description: 検証済み原因に対して複数の解決策を導出しトレードオフを分析。Use when verifierが結論を出した後、または「解決策/どうすれば/修正方法/対処法」が言及された時。調査は行わず与えられた結論から解決に集中。
4
- tools: Read, Grep, Glob, LS, TodoWrite
4
+ tools: Read, Grep, Glob, LS, TodoWrite, WebSearch
5
5
  skills: project-context, technical-spec, coding-standards, implementation-approach
6
6
  ---
7
7
 
@@ -67,7 +67,11 @@ CLAUDE.mdの原則を適用しない独立したコンテキストを持ち、
67
67
  | mitigation | 影響を軽減する対策 | 根本解決まで時間がかかる場合の暫定策 |
68
68
  | fundamental | 再発防止を含む抜本対策 | 同様の問題が繰り返し発生している場合 |
69
69
 
70
- ### ステップ3: トレードオフ分析
70
+ **生成した解決策の検証**:
71
+ - プロジェクトルールに該当指針があるか確認
72
+ - 指針がない領域は、WebSearchでその領域の現在のベストプラクティスを調査し、解決策が標準的アプローチに沿っているか検証
73
+
74
+ ### ステップ3: トレードオフ分析と推奨案選定
71
75
  各解決策を以下の軸で評価:
72
76
 
73
77
  | 評価軸 | 説明 |
@@ -153,6 +157,7 @@ CLAUDE.mdの原則を適用しない独立したコンテキストを持ち、
153
157
  - [ ] 推奨案を選定し理由を説明した
154
158
  - [ ] 具体的な実装ステップを作成した
155
159
  - [ ] 不確実性への対処方法を記載した
160
+ - [ ] 解決策がプロジェクトルールまたはベストプラクティスに沿っているか検証した
156
161
  - [ ] 入力がユーザー報告と整合しているか確認した
157
162
 
158
163
  ## 禁止事項
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "create-ai-project",
3
- "version": "1.14.2",
3
+ "version": "1.14.3",
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": [