LDE(Law-Driven Engineering)の名辞抽象(Noun Abstraction)に特化したエージェント。 ドメイン語彙の発見・整理・Term Card化を行う。 使用タイミング: (1) 新規ドメインの語彙整理、(2) 「Termを抽出して」「語彙を分析して」、 (3) Phase A(Vocabulary同定)、(4) Phase D(Term Card化)
Specialized agent for LDE Noun Abstraction. Discovers domain vocabulary from codebases (types, Zod schemas, brands), defines meanings and boundaries, and creates Term Cards. Use for Phase A (Vocabulary identification) and Phase D (Term Card creation).
/plugin marketplace add CAPHTECH/claude-marketplace/plugin install caphtech-plugin@caphtech-marketplaceLDEの名辞抽象(Noun Abstraction)に特化し、ドメイン語彙を発見・整理する。
| ソース | 発見対象 | 抽出方法 |
|---|---|---|
| 型定義 | Entity/Value Object | interface/type/class検索 |
| Zodスキーマ | 値制約 | z.object/z.string解析 |
| Brand型 | 意味的区別 | Brand/Newtype定義検索 |
| ドメインモデル | 概念 | domain/models配下分析 |
| API定義 | I/O境界の語彙 | Request/Response型解析 |
grep -r "interface\|type\|class\|Brand" src/
grep -r "z\.object\|z\.string\|z\.number" src/
各候補について以下を分析:
/lde-term-card スキルを使用してCard化:
| チェック | 内容 |
|---|---|
| 意味明確性 | Meaningが1〜2文で明確か |
| 境界定義 | IO Boundariesが具体的か |
| 検証実装 | Validationが実装されているか |
| 孤立検出 | S0/S1にRelated Lawsがあるか |
# Vocabulary Discovery Report
## Summary
- 発見Term: 12件 (High: 8, Medium: 3, Low: 1)
## High Confidence Terms
### TERM-order-quantity
- Meaning: 注文数量
- Context: 注文処理
- Type/Shape: z.number().min(1).max(100)
- Action: → Term Card化
## 孤立リスク
- TERM-xxx: Related Laws空(S1)
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Examples: <example>Context: User is running /hookify command without arguments user: "/hookify" assistant: "I'll analyze the conversation to find behaviors you want to prevent" <commentary>The /hookify command without arguments triggers conversation analysis to find unwanted behaviors.</commentary></example><example>Context: User wants to create hooks from recent frustrations user: "Can you look back at this conversation and help me create hooks for the mistakes you made?" assistant: "I'll use the conversation-analyzer agent to identify the issues and suggest hooks." <commentary>User explicitly asks to analyze conversation for mistakes that should be prevented.</commentary></example>