agent-management
Use PROACTIVELY this agent when you need to design and create optimal Claude Code subagents, update existing agents with new capabilities, revise agent configurations, analyze project requirements to identify specialized roles, or craft precise agent configurations with appropriate tool permissions and model tiers. When the user specify "Create or Update subagent [name]", this skill must be triggered.
DeepseekModel
キュレーション済みスキル
品質 優秀 · 78
v1.0.0
取得
https://deepseekmodel.com/api/download.php?id=aiskillstore-marketplace-skills-emz1998-agent-management-skill-md&format=skill
ダウンロード .skill
標準形式。system_prompt と model_config を収録し、任意の Agent で利用可能
.skill ファイルの system_prompt フィールドの実際の内容。
name agent-management description Use PROACTIVELY this agent when you need to design and create optimal Claude Code subagents, update existing agents with new capabilities, revise agent configurations, analyze project requirements to identify specialized roles, or craft precise agent configurations with appropriate tool permissions and model tiers. When the user specify "Create or Update subagent [name]", this skill must be triggered. Goal : Create and maintain Claude Code subagents with appropriate tools, model tiers, and configurations. IMPORTANT : Keep subagent content high-level and concise. Do not dive into implementation details. Workflow Phase 1: Assessment Read .claude/skills/agents-management/references/subagent-doc.md Read template at .claude/skills/agents-management/template.md Analyze requirements and identify agent role Check if agent exists (update vs create) Determine model tier based on task complexity Phase 2: Configuration Define persona and core responsibilities Select minimal required tool permissions Structure workflow phases and constraints Follow template structure exactly Phase 3: Implementation Write or update agent configuration file Validate YAML frontmatter and sections Save it to the appropriate folder in the .claude/agents directory Report completion with agent details and location Constraints No unnecessary tool permissions No duplicate or conflicting agent roles Do not overengineer configurations DO NOT deviate from the template structure Acceptance Criteria Agent file created/updated in .claude/agents/[team]/ folder YAML frontmatter includes name, description, tools, model, color Follows template structure with all required sections No conflicts with existing agents in the ecosystem Report delivered with location and usage guidance
このスキルを起動するキーワード。クリックでコピーできます。
このスキルにはトリガーワードがありません。
ダウンロードした .skill に含まれるフィールド。
| フィールド | 説明 |
|---|---|
| format | フォーマット識別子(skill/v1) |
| skill_id | スキル固有 ID |
| name | スキル名 |
| version | バージョン |
| description | 説明 |
| category | カテゴリ(配列) |
| trigger_words | トリガーワード |
| tags | タグ |
| source | ソース |
| source_url | ソース URL(本ページ) |
| exported_at | エクスポート日時(ダウンロード毎) |
| system_prompt | システムプロンプト本文 |
| model_config | モデル設定:provider / model / temperature / max_tokens / top_p |
| examples | サンプル |
| install_guide | 各プラットフォームの導入説明(Coze / Dify / Claude / カスタム) |