スキル agent-creator
📦

agent-creator

低リスク 🌐 ネットワークアクセス📁 ファイルシステムへのアクセス⚙️ 外部コマンド

Create Specialized AI Agents

Building AI agents with consistent, high-quality performance requires deep domain knowledge and optimized system prompts. This skill provides a structured 4-phase methodology to create production-ready agents with embedded expertise.

対応: Claude Codex Code(CC)
⚠️ 67 貧弱
1

スキルZIPをダウンロード

2

Claudeでアップロード

設定 → 機能 → スキル → スキルをアップロードへ移動

3

オンにして利用開始

テストする

「agent-creator」を使用しています。 Create a code review agent for JavaScript projects

期待される結果:

  • Agent Name: js-code-reviewer
  • System Prompt: You are an expert JavaScript code reviewer...
  • Constraints: [list]
  • Workflow Phases: [description]

「agent-creator」を使用しています。 Build a research agent for medical literature

期待される結果:

  • Agent Name: medical-lit-researcher
  • System Prompt: You are a medical research specialist...
  • Evidence Standards: [requirements]
  • Citation Format: [specification]

「agent-creator」を使用しています。 Design an agent for customer onboarding

期待される結果:

  • Agent Name: onboarding-guide
  • System Prompt: You help new customers get started...
  • Step Workflow: [process]
  • Escalation Triggers: [conditions]

セキュリティ監査

低リスク
v6 • 1/21/2026

Static analysis flagged 81 potential issues in documentation and diagram files. All findings are false positives: DOT files contain GraphViz workflow diagrams, SKILL.md is documentation with no executable code, and metadata fields triggered false positives. The skill is a prompt/documentation skill for agent creation with no actual security risks.

3
スキャンされたファイル
1,463
解析された行数
3
検出結果
6
総監査数
監査者: claude 監査履歴を表示 →

品質スコア

38
アーキテクチャ
100
保守性
87
コンテンツ
21
コミュニティ
90
セキュリティ
87
仕様準拠

作れるもの

Build Domain-Specific Research Agents

Create AI agents optimized for specific research domains like legal document review, scientific literature analysis, or market research. The agent embeds domain-specific terminology, constraints, and workflow patterns.

Develop Code Review Automation Agents

Generate specialized agents for code review tasks with embedded coding standards, language-specific rules, and security scanning patterns. Agents follow consistent review workflows.

Create Customer Support Workflow Agents

Build agents trained on support scripts, knowledge base content, and escalation procedures. These agents handle common queries with consistent responses and proper handoff logic.

これらのプロンプトを試す

Basic Agent Creation
Create a new AI agent named [agent-name] for [task-description]. Use the 4-phase SOP methodology to define its system prompt with embedded domain knowledge about [domain-area].
Agent with Tools
Design an agent that can [primary-capability]. Include tools for [tool-list]. Define the agent constraints and response formats for [use-case].
Multi-Phase Agent Workflow
Create an agent that follows this workflow: Phase 1 [phase-1-description], Phase 2 [phase-2-description], Phase 3 [phase-3-description]. Embed evidence-based prompting for quality outputs.
Production-Ready Agent
Generate a production-ready Claude Code agent with: name=[agent-name], purpose=[purpose], constraints=[constraints], escalation-rules=[rules]. Include error handling and validation prompts.

ベストプラクティス

  • Define clear agent boundaries and constraints before generating the system prompt
  • Use evidence-based prompting to embed verifiable domain knowledge
  • Test agent responses with edge cases before deployment

回避

  • Avoid creating agents without defined escalation paths for unknown inputs
  • Do not skip the 4-phase methodology for complex agent requirements
  • Avoid overloading agents with too many conflicting constraints

よくある質問

What is the 4-phase SOP methodology?
The 4-phase SOP methodology structures agent creation into four phases: analysis, design, implementation, and validation. Each phase adds layers of domain knowledge and constraints to the system prompt.
Can I use this skill with Claude Code?
Yes. This skill is compatible with Claude Code and generates agents using Claude Agent SDK patterns. The output includes ready-to-use configuration files.
Does this skill execute code?
No. This skill generates agent configurations, system prompts, and documentation. You must manually implement and test the generated agent code.
What makes evidence-based prompting different?
Evidence-based prompting requires agents to cite sources and verify claims. This improves response quality and makes agent outputs auditable and trustworthy.
Can I modify generated prompts?
Yes. All generated prompts are templates meant for customization. Review and adjust constraints, workflows, and domain knowledge for your specific use case.
How do I deploy created agents?
Export the generated system prompt and configuration. Deploy using your preferred method: Claude Code, custom integration, or Claude Agent SDK deployment pipeline.

開発者の詳細

ファイル構成