SuperClaude/docs/Development/hypothesis-pm-autonomous-enhancement-2025-10-14.md

391 lines
10 KiB
Markdown
Raw Normal View History

# PM Agent Autonomous Enhancement - 改善提案
> **Date**: 2025-10-14
> **Status**: 提案中(ユーザーレビュー待ち)
> **Goal**: ユーザーインプット最小化 + 確信を持った先回り提案
---
## 🎯 現状の問題点
### 既存の `superclaude/commands/pm.md`
```yaml
良い点:
✅ PDCAサイクルが定義されている
✅ サブエージェント連携が明確
✅ ドキュメント記録の仕組みがある
改善が必要な点:
❌ ユーザーインプット依存度が高い
❌ 調査フェーズが受動的
❌ 提案が「どうしますか?」スタイル
❌ 確信を持った提案がない
```
---
## 💡 改善提案
### Phase 0: **自律的調査フェーズ**(新規追加)
#### ユーザーリクエスト受信時の自動実行
```yaml
Auto-Investigation (許可不要・自動実行):
1. Context Restoration:
- Read docs/Development/tasks/current-tasks.md
- list_memories() → 前回のセッション確認
- read_memory("project_context") → プロジェクト理解
- read_memory("past_mistakes") → 過去の失敗確認
2. Project Analysis:
- Read CLAUDE.md → プロジェクト固有ルール
- Glob **/*.md → ドキュメント構造把握
- mcp__serena__get_symbols_overview → コード構造理解
- Grep "TODO\|FIXME\|XXX" → 既知の課題確認
3. Current State Assessment:
- Bash "git status" → 現在の状態
- Bash "git log -5 --oneline" → 最近の変更
- Read tests/ → テストカバレッジ確認
- Security scan → セキュリティリスク確認
4. Competitive Research (必要時):
- tavily search → ベストプラクティス調査
- context7 → 公式ドキュメント参照
- Deep Research → 競合サービス分析
5. Architecture Evaluation:
- 既存アーキテクチャの強み分析
- 技術スタックの特徴把握
- 拡張可能性の評価
```
#### 出力形式
```markdown
📊 自律調査完了
現状分析:
- プロジェクト: [名前][技術スタック]
- 進捗: [前回セッションの続き or 新規タスク]
- コードベース: [ファイル数]、テストカバレッジ [%]
- 既知の課題: [TODO/FIXME数]
- 最近の変更: [git log要約]
アーキテクチャの強み:
- [強み1]: [具体的な理由]
- [強み2]: [具体的な理由]
不足している要素:
- [不足1]: [影響]
- [不足2]: [影響]
```
---
### Phase 1: **確信を持った提案**(強化)
#### ❌ 改善前(受動的)
```
User: "認証機能作って"
PM Agent: "認証機能を実装しますね。
どんな認証方式がいいですか?"
→ ユーザーに丸投げ
```
#### ✅ 改善後(能動的・確信あり)
```
User: "認証機能作って"
PM Agent:
📊 自律調査完了3秒:
- 既存: Supabase統合済み強み
- 不足: 認証機能なし
- テスト: カバレッジ45%目標80%
- 競合調査: Auth0、Clerk、Supabase Auth比較済み
- セキュリティ: OWASP推奨3項目未対応
💡 確信を持った提案:
このアーキテクチャはSupabase連携に強みがあるため、
**Supabase Auth統合**を推奨します。
具体的な実装方針:
1. Supabase Auth統合JWT + リフレッシュトークン)
2. MFA対応TOTP実装
3. セキュリティテスト追加カバレッジ85%目標)
4. 既存APIとのシームレス統合
選択理由:
✅ 既存のSupabase接続再利用実装コスト最小
✅ エンタープライズグレードのセキュリティ
✅ 無料枠で十分な機能(コスト効率◎)
✅ 将来のスケーラビリティ確保
代替案との比較:
- Auth0: 月$25〜、実装複雑度高
- Clerk: 月$25〜、React特化このプロジェクトはNext.js
- Supabase Auth: 無料、既存統合済み ← 推奨
この方針で進めてよろしいですか?
```
---
### Phase 2: **自律実行**(既存を強化)
#### 承認後の自動フロー
```yaml
User: "OK"
PM Agent完全自律実行:
1. Architecture Design:
- system-architect: Supabase Auth設計
- security-engineer: セキュリティレビュー
2. Implementation:
- backend-architect: API統合実装
- frontend-architect: UI実装
- Load magic: Login/Register components
3. Testing:
- Write tests/auth/*.test.ts
- pytest実行 → 失敗検出
4. Self-Correction:
- context7 → Supabase公式ドキュメント確認
- エラー原因特定: "JWTシークレット未設定"
- 修正実装
- 再テスト → 合格
5. Documentation:
- Update docs/patterns/supabase-auth-integration.md
- Update CLAUDE.md認証パターン追加
- write_memory("success_pattern", 詳細)
6. Report:
✅ 認証機能実装完了
実装内容:
- Supabase Auth統合JWT + リフレッシュ)
- MFA対応TOTP
- テストカバレッジ: 45% → 87%(目標達成)
- セキュリティ: OWASP準拠確認済み
学習記録:
- 成功パターン: docs/patterns/supabase-auth-integration.md
- 遭遇したエラー: JWT設定不足修正済み
- 次回の改善: 環境変数チェックリスト更新
```
---
## 🔧 実装方針
### `superclaude/commands/pm.md` への追加セクション
#### 1. Autonomous Investigation Phase新規
```markdown
## Phase 0: Autonomous Investigation (Auto-Execute)
**Trigger**: Any user request received
**Execution**: Automatic, no permission required
### Investigation Steps:
1. **Context Restoration**
- Read `docs/Development/tasks/current-tasks.md`
- Serena memory restoration
- Project context loading
2. **Project Analysis**
- CLAUDE.md → Project rules
- Code structure analysis
- Test coverage check
- Security scan
- Known issues detection (TODO/FIXME)
3. **Competitive Research** (when relevant)
- Best practices research (Tavily)
- Official documentation (Context7)
- Alternative solutions analysis
4. **Architecture Evaluation**
- Identify architectural strengths
- Detect technology stack characteristics
- Assess extensibility
### Output Format:
```
📊 Autonomous Investigation Complete
Current State:
- Project: [name] ([stack])
- Progress: [status]
- Codebase: [files count], Test Coverage: [%]
- Known Issues: [count]
- Recent Changes: [git log summary]
Architectural Strengths:
- [strength 1]: [rationale]
- [strength 2]: [rationale]
Missing Elements:
- [gap 1]: [impact]
- [gap 2]: [impact]
```
```
#### 2. Confident Proposal Phase強化
```markdown
## Phase 1: Confident Proposal (Enhanced)
**Principle**: Never ask "What do you want?" - Always propose with conviction
### Proposal Format:
```
💡 Confident Proposal:
[Implementation approach] is recommended.
Specific Implementation Plan:
1. [Step 1 with rationale]
2. [Step 2 with rationale]
3. [Step 3 with rationale]
Selection Rationale:
✅ [Reason 1]: [Evidence]
✅ [Reason 2]: [Evidence]
✅ [Reason 3]: [Evidence]
Alternatives Considered:
- [Alt 1]: [Why not chosen]
- [Alt 2]: [Why not chosen]
- [Recommended]: [Why chosen] ← Recommended
Proceed with this approach?
```
### Anti-Patterns (Never Do):
❌ "What authentication do you want?" (Passive)
❌ "How should we implement this?" (Uncertain)
❌ "There are several options..." (Indecisive)
✅ "Supabase Auth is recommended because..." (Confident)
✅ "Based on your architecture's Supabase integration..." (Evidence-based)
```
#### 3. Autonomous Execution Phase既存を明示化
```markdown
## Phase 2: Autonomous Execution
**Trigger**: User approval ("OK", "Go ahead", "Yes")
**Execution**: Fully autonomous, systematic PDCA
### Self-Correction Loop:
```yaml
Implementation:
- Execute with sub-agents
- Write comprehensive tests
- Run validation
Error Detected:
→ Context7: Check official documentation
→ Identify root cause
→ Implement fix
→ Re-test
→ Repeat until passing
Success:
→ Document pattern (docs/patterns/)
→ Update learnings (write_memory)
→ Report completion with evidence
```
### Quality Gates:
- Tests must pass (no exceptions)
- Coverage targets must be met
- Security checks must pass
- Documentation must be updated
```
---
## 📊 期待される効果
### Before (現状)
```yaml
User Input Required: 高
- 認証方式の選択
- 実装方針の決定
- エラー対応の指示
- テスト方針の決定
Proposal Quality: 受動的
- "どうしますか?"スタイル
- 選択肢の羅列のみ
- ユーザーが決定
Execution: 半自動
- エラー時にユーザーに報告
- 修正方針をユーザーが指示
```
### After (改善後)
```yaml
User Input Required: 最小
- "認証機能作って"のみ
- 提案への承認/拒否のみ
Proposal Quality: 能動的・確信あり
- 調査済みの根拠提示
- 明確な推奨案
- 代替案との比較
Execution: 完全自律
- エラー自己修正
- 公式ドキュメント自動参照
- テスト合格まで自動実行
- 学習自動記録
```
### 定量的目標
- ユーザーインプット削減: **80%削減**
- 提案品質向上: **確信度90%以上**
- 自律実行成功率: **95%以上**
---
## 🚀 実装ステップ
### Step 1: pm.md 修正
- [ ] Phase 0: Autonomous Investigation 追加
- [ ] Phase 1: Confident Proposal 強化
- [ ] Phase 2: Autonomous Execution 明示化
- [ ] Examples セクションに具体例追加
### Step 2: テスト作成
- [ ] `tests/test_pm_autonomous.py`
- [ ] 自律調査フローのテスト
- [ ] 確信提案フォーマットのテスト
- [ ] 自己修正ループのテスト
### Step 3: 動作確認
- [ ] 開発版インストール
- [ ] 実際のワークフローで検証
- [ ] フィードバック収集
### Step 4: 学習記録
- [ ] `docs/patterns/pm-autonomous-workflow.md`
- [ ] 成功パターンの文書化
---
## ✅ ユーザー承認待ち
**この方針で実装を進めてよろしいですか?**
承認いただければ、すぐに `superclaude/commands/pm.md` の修正を開始します。