메뉴
This skill guides creating autonomous agents for Claude Code plugins using markdown files with YAML frontmatter. Use when building new agents, designing agent system prompts, or configuring agent behavior.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Expert skill for the Jotai state management library. Use when implementing atom-based state management in React applications. Use this skill for: (1) Jotai atom design and implementation (2) Derived atoms, async atoms, atomFamily implementation (3) Refactoring based on Jotai best practices (4) Performance optimization (selectAtom, splitAtom, etc.) (5) Persistence (localStorage/sessionStorage integration) (6) TypeScript type definitions (7) Test implementation Triggered when users ask questions or request implementations related to "Jotai", "atom", or "state management".
Jotai状態管理ライブラリのエキスパートスキル。Reactアプリケーションでのatomベースの状態管理を実装する際に使用。以下の場合にこのスキルを使用: (1) Jotaiのatom設計・実装 (2) 派生atom、非同期atom、atomFamilyの実装 (3) Jotaiのベストプラクティスに基づくリファクタリング (4) パフォーマンス最適化（selectAtom、splitAtom等） (5) 永続化（localStorage/sessionStorage連携） (6) TypeScript型定義 (7) テスト実装 ユーザーが「Jotai」「atom」「状態管理」に関する質問や実装依頼をした場合に発動。
This skill provides structured question-asking capabilities for gathering user input, clarifying requirements, and making decisions during task execution. Use this skill when needing to present multiple choice questions, gather preferences, or get user confirmation on implementation choices.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Generate beautiful infographic PNG images from Claude Code changelog summaries. Use this skill after changelog-interpreter has generated a user-friendly summary, to create a visual representation that can be saved and shared.
Interpret Claude Code changelogs and generate user-friendly usage guides
| name | agent-development |
| description | This skill guides creating autonomous agents for Claude Code plugins using markdown files with YAML frontmatter. Use when building new agents, designing agent system prompts, or configuring agent behavior. |
Agents are autonomous AI specialists defined as markdown files with YAML frontmatter and system prompt body.
---
name: my-agent
description: Use this agent when... with 2-4 triggering examples
model: inherit
color: blue
tools: Tool1, Tool2
---
System prompt instructions here.
| Field | Description |
|---|---|
name | Lowercase identifier (3-50 chars, hyphens only) |
description | "Use this agent when..." with triggering conditions |
| Field | Description |
|---|---|
model | inherit, sonnet, opus, or haiku |
color | Visual identifier: blue, cyan, green, yellow, magenta, red |
tools | Array restricting tool access |
Use second-person language in the markdown body:
You are a [role] specialized in [domain].
## Process
1. First, analyze...
2. Then, evaluate...
3. Finally, provide...
## Output Format
Structure your response as...
## Quality Standards
Ensure all outputs...
The description teaches Claude when to activate the agent:
description: |
Use this agent when reviewing code changes for quality and security.
Examples:
- User asks "review my PR" → triggers because code review requested
- User commits changes and wants feedback → triggers for post-commit review
- User mentions security concerns in code → triggers for security-focused review
.claude/agents/my-agent.md # Project scope
~/.claude/agents/my-agent.md # User scope
plugin/agents/my-agent.md # Plugin scope