← ClaudeAtlas

skill-creatorlisted

Design a new Claude Code skill from a concrete use case and produce a repo-ready skill package. Use when the user asks to create a new skill, define a skill's responsibility, draft SKILL.md, choose frontmatter, design supporting files, or prepare eval criteria for a new skill. Also trigger on "スキルを作りたい", "スキルを作って", "スキルを追加して", "新しいスキル", "SKILL.md生成".
s977043/PlanGate · ★ 2 · AI & Automation · score 69
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