create-ai-project 1.18.6 → 1.18.7

package/.claude/skills-en/skill-optimization/SKILL.md

@@ -39,7 +39,7 @@ Quality policies, role boundaries, scoring criteria, and general work rules alwa
 
 | Detection | Transform |
 |-----------|-----------|
-| "appropriate", "good", "proper", "best", "should be clear" | Replace with measurable if-then criteria or concrete thresholds |
+| "appropriate", "good", "proper", "best", "should be clear" | Replace with measurable if-then criteria or concrete thresholds. **Skill exception**: Expressions that the LLM can resolve unambiguously from input context (e.g., "where the user left gaps" when the user's prompt is available for comparison) are not vague — they describe a deterministic operation, not a subjective judgment. |
 | Missing output format, scope, or success criteria | Add explicit constraints |
 
 **Skill example:**
@@ -87,7 +87,7 @@ Issues that reduce skill effectiveness when addressed.
 | Detection | Transform |
 |-----------|-----------|
 | Skill assumes knowledge not stated | Add Prerequisites section listing required context |
-| Domain terms used without definition | Add definitions inline or in a glossary table |
+| Domain terms used without definition | Add definitions inline or in a glossary table. **Skill exception**: Terms within the LLM's baseline knowledge (widely-used technical terminology, standard domain vocabulary) require no definition. Only project-specific terms, internal naming conventions, or domain jargon outside common LLM training data need explicit definition. |
 | No "when to use" guidance | Add trigger conditions with concrete scenarios |
 
 **Skill example:**
@@ -136,7 +136,7 @@ Measurable quality criteria for skill content. Each principle includes a pass/fa
 | # | Principle | Pass Criteria | Fail Example |
 |---|-----------|---------------|--------------|
 | 1 | Context efficiency | Every sentence contributes to LLM decision-making. No filler. | "This is an important skill that helps with..." |
-| 2 | Deduplication | No concept explained twice within the skill or across skills | Same error handling rules in both coding-standards and typescript-rules |
+| 2 | Deduplication | No concept explained twice at the same abstraction level within the skill or across skills. Mentions at different structural roles (e.g., classification framework vs execution detail) are not duplicates, provided the re-mention adds new constraints or criteria | Same error handling rules in both coding-standards and typescript-rules |
 | 3 | Grouping | Related criteria in single section (minimize read operations) | Scattered error handling rules across 4 sections |
 | 4 | Measurability | All criteria use if-then format or concrete thresholds | "Write clean code" without definition of clean |
 | 5 | Positive form | Instructions state what to do (BP-001 applied) | "Don't use any" instead of "Use only X" |

package/.claude/skills-ja/skill-optimization/SKILL.md

@@ -39,7 +39,7 @@ description: スキルファイルの品質を8つのコンテンツパターン
 
 | 検出条件 | 変換方法 |
 |----------|----------|
-| 「適切に」「良い」「正しく」「ベスト」「明確に」等 | 測定可能なif-then基準または具体的な閾値に置換 |
+| 「適切に」「良い」「正しく」「ベスト」「明確に」等 | 測定可能なif-then基準または具体的な閾値に置換。**スキル例外**: 入力コンテキストから一意に解決できる表現（例: ユーザーのプロンプトが参照可能な状況での「ユーザーが省略した箇所」）は曖昧ではない。主観的判断ではなく機械的に特定できる処理を記述している。 |
 | 出力形式・スコープ・成功基準が未定義 | 明示的な制約を追加 |
 
 **スキルでの例:**
@@ -87,7 +87,7 @@ description: スキルファイルの品質を8つのコンテンツパターン
 | 検出条件 | 変換方法 |
 |----------|----------|
 | 記述されていない前提知識に依存 | 必要な前提を列挙したPrerequisitesセクションを追加 |
-| 定義なしにドメイン用語を使用 | インラインまたは用語テーブルで定義を追加 |
+| 定義なしにドメイン用語を使用 | インラインまたは用語テーブルで定義を追加。**スキル例外**: LLMのベースライン知識に含まれる用語（広く使われる技術用語、標準的なドメイン語彙）は定義不要。プロジェクト固有の用語、内部命名規則、LLMの一般知識に含まれないドメイン用語のみ明示的な定義が必要。 |
 | 使用場面の指針がない | 具体的なシナリオ付きのトリガー条件を追加 |
 
 **スキルでの例:**
@@ -136,7 +136,7 @@ description: スキルファイルの品質を8つのコンテンツパターン
 | # | 原則 | 合格基準 | 不合格例 |
 |---|------|----------|----------|
 | 1 | コンテキスト効率 | 全文がLLMの判断に寄与する。冗長な記述なし | 「これは〜に役立つ重要なスキルで...」 |
-| 2 | 重複排除 | スキル内・スキル間で同じ概念の重複説明なし | coding-standardsとtypescript-rulesに同じエラーハンドリング規則 |
+| 2 | 重複排除 | スキル内・スキル間で同じ抽象レベルにおける概念の重複説明なし。異なる構造的役割（例: 分類体系と実行詳細）での言及は、新たな制約や判断基準を伴う場合に限り重複に該当しない | coding-standardsとtypescript-rulesに同じエラーハンドリング規則 |
 | 3 | 関連内容の集約 | 関連する基準を1セクションに集約（読み込み回数最小化） | エラーハンドリング規則が4セクションに散在 |
 | 4 | 測定可能性 | 全基準がif-then形式または具体的閾値 | 「きれいなコードを書く」の定義なし |
 | 5 | 肯定形 | 指示は「何をするか」を記述（BP-001適用済み） | 「一切使わないこと」→「Xのみ使用する」 |

package/CHANGELOG.md

@@ -5,6 +5,18 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.18.7] - 2026-03-30
+
+### Fixed
+
+#### Skill Review False Positives from LLM-Consumer Unawareness
+
+skill-reviewer was applying BP patterns as if skills were human-facing documents, causing false positives that blocked valid skill content.
+
+- **BP-002**: Expressions resolvable from input context (e.g., "where the user left gaps" when the user's prompt is available) were flagged as vague. Added skill exception — deterministic operations derived from available input are not vague.
+- **BP-005**: Standard technical terms already in the LLM's baseline knowledge were flagged as undefined. Added skill exception — only project-specific terms, internal naming conventions, and domain jargon outside the LLM's general knowledge require explicit definition.
+- **Principle 2 (Deduplication)**: Mentions of the same concept at different structural roles (e.g., classification framework vs execution detail) were flagged as duplicates. Refined criteria — re-mentions at different structural roles are permitted when they add new constraints or criteria.
+
 ## [1.18.6] - 2026-03-29
 
 ### Fixed

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "create-ai-project",
-  "version": "1.18.6",
+  "version": "1.18.7",
   "packageManager": "npm@10.8.2",
   "description": "TypeScript boilerplate with skills and sub-agents for Claude Code. Prevents context exhaustion through role-based task splitting.",
   "keywords": [