agent-creation-prompt

# AI 辅助智能体生成模板 使用此模板通过 Claude 的智能体创建系统提示词来生成智能体。 ## 使用模式 ### 第 1 步：描述您的智能体需求 思考： - 智能体应处理什么任务？ - 何时应触发它？ - 应该是主动还是被动的？ - 核心职责是什么？ ### 第 2 步：使用生成提示词 发送此内容给 Claude（加载 agent-creation-system-prompt）： Create an agent configuration based on this request: "[YOUR DESCRIPTION]" Return ONLY the JSON object, no other text. **将 [YOUR DESCRIPTION] 替换为您的智能体需求。** ### 第 3 步：Claude 返回 JSON Claude 将返回： { "identifier": "agent-name", "whenToUse": "Use this agent when... Examples: ...", "systemPrompt": "You are... **Your Core Responsibilities:**..." } ### 第 4 步：转换为智能体文件 创建 `agents/[identifier].md`： markdown --- name: [identifier from JSON] description: [whenToUse from JSON] model: inherit color: [choose: blue/cyan/green/yellow/magenta/red] tools: ["Read", "Write", "Grep"] # 可选：限制工具 --- [systemPrompt from JSON] ## 示例 1：代码审查智能体 **您的请求：** I need an agent that reviews code changes for quality issues, security vulnerabilities, and adherence to best practices. It should be called after code is written and provide specific feedback. **Claude 生成：** { "identifier": "code-quality-reviewer", "whenToUse": "Use this agent when the user has written code and needs quality review, or explicitly asks to review code changes. Examples:nnnContext: User just implemented a new featurenuser: "I've added the authentication feature"nassistant: "Great! Let me review the code quality."nnCode was written, trigger code-quality-reviewer agent for review.nnassistant: "I'll use the code-quality-reviewer agent to analyze the changes."nnnnContext: User explicitly requests reviewnuser: "Can you review my code for issues?"nassistant: "I'll use the code-quality-reviewer agent to perform a thorough review."nnExplicit review request triggers the agent.nn", "systemPrompt": "You are an expert code quality reviewer specializing in identifying issues in software implementations.nn**Your Core Responsibilities:**n1. Analyze code changes for quality issues (readab