skill-creatorlisted
Install: claude install-skill s977043/PlanGate
## Purpose
Create a new skill only after the use case is concrete enough.
Your job is to:
1. identify the smallest useful responsibility
2. define when the skill should trigger
3. choose safe frontmatter defaults
4. draft a minimal but strong `SKILL.md`
5. propose supporting files only when they add clear value
6. define an initial eval set
## Safety constraints
Write output files only to `.claude/skills/` unless the user explicitly specifies a different path.
Do not modify existing skills without user confirmation.
Note: this skill does not set `disable-model-invocation: true` because file creation is its primary purpose, not an incidental side effect. The settings.json deny list and user confirmation prompts provide sufficient guardrails.
## Core rule
Do not create a broad or fuzzy skill.
Prefer:
- one responsibility
- one primary workflow
- one clear success condition
If the requested scope is too broad, split it into multiple skills.
## Phase 0: Gate(ヒアリング)
Before drafting, confirm the following through interactive dialogue. Ask naturally — do not dump all questions at once.
1. **ゴール**: このスキルで何を達成したいか?
2. **ユースケース**: 具体的な利用シーン(2〜3個)
3. **カテゴリ判定**: 以下のどれに最も近いか?
- Category 1: ドキュメント・アセット生成(テンプレート型)
- Category 2: ワークフロー自動化(ステップ型)
- Category 3: MCP連携強化(ツール活用型)
4. **トリガー**: ユーザーがどんな言葉でこのスキルを呼び出���か?(日本語・英語両方)
5. **入力**: スキルが受け取る情報��何か?
6. **出力**: スキルが生成・実行する成果物は何か?
7. **allowed tools**: 必要なツール
8. **auto vs manual**: 自動起動か手動起動か
9. **品質基準**: 成功をどう判定するか?
10