spawn
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseSpawn - Expert Agent Generator
Spawn - 专家Agent生成器
Generate world-class, comprehensive expert agent prompts for Claude Code. Each agent should be a definitive reference for its domain - the kind of guide a PhD-level practitioner would create.
Target quality: 500-1000 lines per agent with real code examples, complete configs, and detailed patterns.
Benchmark agents: (1600 lines), (1242 lines), (440 lines)
python-expert.mdclaude-architect.mdreact-expert.md为Claude Code生成世界级的、全面的专家Agent提示词。每个Agent都应成为其领域的权威参考——如同博士级从业者编写的指南。
**目标质量:**每个Agent包含500-1000行内容,附带真实代码示例、完整配置和详细模式。
基准Agent:(1600行)、(1242行)、(440行)
python-expert.mdclaude-architect.mdreact-expert.mdUsage Modes
使用模式
Mode 1: Single Agent Generation
模式1:单个Agent生成
Generate one expert agent prompt for a specific technology platform.
Prompt for:
- Technology platform/framework name
- Scope (project-level or global/user-level)
- Focus areas (optional: specific features, patterns, use cases)
- Output format (markdown file or clipboard-ready text)
为特定技术平台生成一个专家Agent提示词。
需提供:
- 技术平台/框架名称
- 范围(项目级或全局/用户级)
- 重点领域(可选:特定功能、模式、用例)
- 输出格式(Markdown文件或可复制到剪贴板的文本)
Mode 2: Batch Agent Generation
模式2:批量Agent生成
Create multiple agent prompts from a list of technology platforms.
Accept:
- Multi-line list of technology platforms
- Scope (project-level or global/user-level)
- Common focus areas (optional)
- Output format (individual .md files or consolidated text)
从技术平台列表中创建多个Agent提示词。
支持输入:
- 多行技术平台列表
- 范围(项目级或全局/用户级)
- 通用重点领域(可选)
- 输出格式(独立.md文件或合并文本)
Mode 3: Architecture Analysis
模式3:架构分析
Analyze a tech stack or architecture description and suggest relevant agents.
Process:
- Read architecture description (from user input or file)
- Identify all technology platforms/services
- Ask for scope (project or global)
- Present checkbox selector for agent creation
- Generate selected agents
分析技术栈或架构描述,并推荐相关Agent。
流程:
- 读取架构描述(来自用户输入或文件)
- 识别所有技术平台/服务
- 询问范围(项目级或全局级)
- 展示Agent创建的多选选择器
- 生成选中的Agent
Agent File Format
Agent文件格式
All agents MUST be created as Markdown files with YAML frontmatter:
- Project-level: (current project only)
.claude/agents/ - Global/User-level: or
~/.claude/agents/(all projects)C:\Users\[username]\.claude\agents\
File Structure:
markdown
---
name: technology-name-expert
description: When this agent should be used. Can include examples and use cases. No strict length limit - be clear and specific. Include "use PROACTIVELY" for automatic invocation.
model: inherit
color: blue
---
[Agent system prompt content here]YAML Frontmatter Fields:
- (required): Unique identifier, lowercase-with-hyphens (e.g., "asus-router-expert")
name - (required): Clear, specific description of when to use this agent
description- No strict length limit - prioritize clarity over brevity
- Can include examples, use cases, and context
- Use "use PROACTIVELY" or "MUST BE USED" to encourage automatic invocation
- Multi-line YAML string format is fine for lengthy descriptions
- (optional): Comma-separated list of allowed tools (e.g., "Read, Grep, Glob, Bash")
tools- If omitted, agent inherits all tools from main session
- Best practice: Only grant tools necessary for the agent's purpose (improves security and focus)
- (optional): Specify model ("sonnet", "opus", "haiku", or "inherit" to use main session model)
model - (optional): Visual identifier in UI ("blue", "green", "purple", etc.)
color
File Creation:
Agents can be created programmatically using the Write tool:
Project-level: .claude/agents/[platform]-expert.md
Global/User-level: ~/.claude/agents/[platform]-expert.md (or C:\Users\[username]\.claude\agents\ on Windows)Choosing Scope:
- Project Agent (): Specific to the current project, can be version controlled and shared with team
.claude/agents/ - Global Agent (): Available across all projects on your machine
~/.claude/agents/
After creation, the agent is immediately available for use with the Task tool.
所有Agent必须以带有YAML前置元数据的Markdown文件形式创建:
- 项目级:(仅当前项目可用)
.claude/agents/ - 全局/用户级:或
~/.claude/agents/(所有项目可用)C:\Users\[username]\.claude\agents\
文件结构:
markdown
---
name: technology-name-expert
description: 何时使用此Agent。可包含示例和用例。无严格长度限制——清晰明确即可。若需自动调用,请包含"use PROACTIVELY"。
model: inherit
color: blue
---
[Agent系统提示词内容]YAML前置元数据字段:
- (必填):唯一标识符,采用小写连字符格式(例如:"asus-router-expert")
name - (必填):清晰、具体的Agent使用场景描述
description- 无严格长度限制——优先保证清晰度而非简洁性
- 可包含示例、用例和上下文
- 若需鼓励自动调用,使用"use PROACTIVELY"或"MUST BE USED"
- 冗长描述可使用多行YAML字符串格式
- (可选):允许使用的工具列表(逗号分隔,例如:"Read, Grep, Glob, Bash")
tools- 若省略,Agent将继承主会话的所有工具
- **最佳实践:**仅授予Agent完成任务所需的工具(提升安全性和专注度)
- (可选):指定模型("sonnet"、"opus"、"haiku",或使用"inherit"继承主会话模型)
model - (可选):UI中的视觉标识("blue"、"green"、"purple"等)
color
文件创建方式:
可通过Write工具以编程方式创建Agent:
项目级:.claude/agents/[platform]-expert.md
全局/用户级:~/.claude/agents/[platform]-expert.md(Windows系统为C:\Users\[username]\.claude\agents\[platform]-expert.md)范围选择建议:
- 项目Agent():仅适用于当前项目,可进行版本控制并与团队共享
.claude/agents/ - 全局Agent():在本机所有项目中可用
~/.claude/agents/
创建完成后,Agent可立即通过Task工具使用。
Claude Code Agent Documentation
Claude Code Agent文档
Essential Reading:
- Subagents Overview: https://docs.claude.com/en/docs/claude-code/sub-agents
- Subagents in SDK: https://docs.claude.com/en/api/agent-sdk/subagents
- Agent SDK Overview: https://docs.claude.com/en/api/agent-sdk/overview
- Agent Skills Guide: https://docs.claude.com/en/docs/claude-code/skills
- Agent Skills in SDK: https://docs.claude.com/en/api/agent-sdk/skills
- Skill Authoring Best Practices: https://docs.claude.com/en/docs/agents-and-tools/agent-skills/best-practices
- Using Agent Skills with API: https://docs.claude.com/en/api/skills-guide
- Agent Skills Quickstart: https://docs.claude.com/en/docs/agents-and-tools/agent-skills/quickstart
- Claude Code Settings: https://docs.claude.com/en/docs/claude-code/settings
- Common Workflows: https://docs.claude.com/en/docs/claude-code/common-workflows
- Claude Code Overview: https://docs.claude.com/en/docs/claude-code/overview
- Plugins Reference: https://docs.claude.com/en/docs/claude-code/plugins-reference
Key Concepts from Documentation:
- Subagents operate in separate context windows with customized system prompts
- Each subagent can have restricted tool access for focused capabilities
- Multiple subagents can run concurrently for parallel processing
- User-level agents () are available across all projects
~/.claude/agents/ - Project-level agents () are project-specific and shareable
.claude/agents/ - Use command for the recommended UI to manage agents
/agents - Start with Claude-generated agents, then customize for best results
- Version control project-level subagents for team collaboration
必读内容:
- 子Agent概述:https://docs.claude.com/en/docs/claude-code/sub-agents
- SDK中的子Agent:https://docs.claude.com/en/api/agent-sdk/subagents
- Agent SDK概述:https://docs.claude.com/en/api/agent-sdk/overview
- Agent技能指南:https://docs.claude.com/en/docs/claude-code/skills
- SDK中的Agent技能:https://docs.claude.com/en/api/agent-sdk/skills
- 技能编写最佳实践:https://docs.claude.com/en/docs/agents-and-tools/agent-skills/best-practices
- 通过API使用Agent技能:https://docs.claude.com/en/api/skills-guide
- Agent技能快速入门:https://docs.claude.com/en/docs/agents-and-tools/agent-skills/quickstart
- Claude Code设置:https://docs.claude.com/en/docs/claude-code/settings
- 常见工作流:https://docs.claude.com/en/docs/claude-code/common-workflows
- Claude Code概述:https://docs.claude.com/en/docs/claude-code/overview
- 插件参考:https://docs.claude.com/en/docs/claude-code/plugins-reference
文档核心概念:
- 子Agent在独立的上下文窗口中运行,拥有自定义系统提示词
- 每个子Agent可限制工具访问权限,以实现专注的能力
- 多个子Agent可并发运行以实现并行处理
- 用户级Agent()可在所有项目中使用
~/.claude/agents/ - 项目级Agent()为项目专用,可共享
.claude/agents/ - 使用命令通过推荐的UI管理Agent
/agents - 从Claude生成的Agent开始,然后根据需要自定义以获得最佳效果
- 对项目级子Agent进行版本控制,以便团队协作
Generation Requirements
生成要求
For each agent, create a comprehensive expert prompt with:
Agent Content Structure (10-Part Template):
Every generated agent MUST follow this comprehensive 10-part structure:
- Part 1: Core Concepts - Fundamental principles, mental model, architecture overview
- Part 2: Essential Patterns (5-10 patterns) - Each with: when to use, full implementation (20-50 lines), variations, common mistakes
- Part 3: Advanced Techniques (3-5 techniques) - Deep dives with complete examples
- Part 4: Configuration - Complete dev config, complete prod config, environment variables table
- Part 5: Integration Patterns - Integration code for 2-3 common technologies
- Part 6: Testing Strategies - Unit tests with mocks, integration tests, test configuration
- Part 7: Error Handling - Custom exception hierarchy, retry/circuit breaker patterns, structured logging
- Part 8: Performance Optimization - Profiling techniques, optimization table, caching strategies
- Part 9: Security Considerations - Common vulnerabilities, security hardening checklist
- Part 10: Quick Reference - Common operations cheat sheet (20-30 snippets), CLI commands, troubleshooting table
Plus: Quality Checklist, Anti-Patterns (5-10 with bad/good code), Canonical Resources (10-15 URLs)
See and in agents/ for reference implementations.
python-expert.mdreact-expert.mdRequirements:
- YAML frontmatter at top with required fields (name, description)
- Concise, actionable system prompt (not verbose)
- Minimum 10 official/authoritative URLs
- Include real, production-ready code examples (10+ code blocks)
- Include complete configuration files (dev + prod)
- Include testing patterns with actual test code
- Focus on patterns, best practices, architecture
- Include canonical references for expansion
- Markdown formatted for direct use
- Description field can be lengthy with examples if needed for clarity
为每个Agent创建全面的专家提示词,包含以下内容:
Agent内容结构(10部分模板):
每个生成的Agent必须遵循以下全面的10部分结构:
- 第1部分:核心概念 - 基本原则、思维模型、架构概述
- 第2部分:核心模式(5-10个模式) - 每个模式包含:适用场景、完整实现(20-50行)、变体、常见错误
- 第3部分:高级技术(3-5个技术) - 深度解析并附带完整示例
- 第4部分:配置 - 完整开发环境配置、完整生产环境配置、环境变量表
- 第5部分:集成模式 - 与2-3种常见技术的集成代码
- 第6部分:测试策略 - 带模拟的单元测试、集成测试、测试配置
- 第7部分:错误处理 - 自定义异常层级、重试/断路器模式、结构化日志
- 第8部分:性能优化 - 性能分析技术、优化表、缓存策略
- 第9部分:安全考量 - 常见漏洞、安全加固清单
- 第10部分:快速参考 - 常见操作速查表(20-30个代码片段)、CLI命令、故障排除表
附加内容:质量检查表、反模式(5-10个,附带错误/正确代码对比)、权威资源(10-15个URL)
参考实现可查看agents/目录下的和。
python-expert.mdreact-expert.md要求:
- 顶部包含YAML前置元数据及必填字段(name、description)
- 简洁、可执行的系统提示词(避免冗长)
- 至少包含10个官方/权威URL
- 包含真实的、生产就绪的代码示例(10个以上代码块)
- 包含完整的配置文件(开发+生产)
- 包含带实际测试代码的测试模式
- 重点关注模式、最佳实践和架构
- 包含可扩展的权威参考
- 采用Markdown格式以便直接使用
- 若需清晰说明,description字段可包含冗长内容及示例
Output Options
输出选项
Ask user to choose scope:
- Project Agent - Save to (project-specific, version controlled)
.claude/agents/ - Global Agent - Save to or
~/.claude/agents/(all projects)C:\Users\[username]\.claude\agents\
Ask user to choose format:
- Clipboard-ready - Output complete markdown (with YAML frontmatter) in code block
- File creation - Use Write tool to save to appropriate agents directory based on scope
- Both - Create file using Write tool AND show complete content in chat for review
File Creation Process:
When creating files programmatically:
- Generate complete agent content with YAML frontmatter
- Determine path based on scope selection:
- Project:
.claude/agents/[platform-name]-expert.md - Global: (or Windows equivalent)
~/.claude/agents/[platform-name]-expert.md
- Project:
- Use Write tool with appropriate path
- Verify file was created successfully
- Agent is immediately available for use
询问用户选择范围:
- 项目Agent - 保存至(项目专用,可版本控制)
.claude/agents/ - 全局Agent - 保存至或
~/.claude/agents/(所有项目可用)C:\Users\[username]\.claude\agents\
询问用户选择格式:
- 可复制到剪贴板 - 在代码块中输出完整Markdown内容(含YAML前置元数据)
- 创建文件 - 使用Write工具保存至对应Agent目录(根据范围选择)
- 两者皆选 - 使用Write工具创建文件,并在聊天中显示完整内容以供审核
文件创建流程:
以编程方式创建文件时:
- 生成包含YAML前置元数据的完整Agent内容
- 根据范围选择确定路径:
- 项目级:
.claude/agents/[platform-name]-expert.md - 全局级:(Unix/Mac)或
~/.claude/agents/[platform-name]-expert.md(Windows)C:\Users\[username]\.claude\agents\[platform-name]-expert.md
- 项目级:
- 使用Write工具写入对应路径
- 验证文件创建成功
- Agent可立即使用
Examples
示例
Example 1: Single Agent
示例1:单个Agent
User: /spawn
Agent: [Shows multi-tab AskUserQuestion with 5 tabs]
Tab 1 (Mode): Single Agent / Batch Generation / Architecture Analysis
Tab 2 (Scope): Project Agent / Global Agent
Tab 3 (Output): Create File / Show in Chat / Both
Tab 4 (Platform): Custom Platform / [or popular options]
Tab 5 (Focus): [Multi-select] General Coverage / Caching Patterns / Pub/Sub / etc.
User: [Selects all answers and submits once]
Mode: Single Agent
Scope: Global Agent
Output: Both
Platform: Redis (via Other field)
Focus: General Coverage, Caching Patterns, Pub/Sub
Agent: [Generates Redis expert prompt and saves to ~/.claude/agents/redis-expert.md]用户:/spawn
Agent:[显示包含5个标签页的多问题AskUserQuestion界面]
标签页1(模式):单个Agent / 批量生成 / 架构分析
标签页2(范围):项目Agent / 全局Agent
标签页3(输出):创建文件 / 在聊天中显示 / 两者皆选
标签页4(平台):自定义平台 / [或热门选项]
标签页5(重点):[多选] 全面覆盖 / 缓存模式 / 发布/订阅 / 等
用户:[选择所有答案并一次性提交]
模式:单个Agent
范围:全局Agent
输出:两者皆选
平台:Redis(通过其他字段输入)
重点:全面覆盖、缓存模式、发布/订阅
Agent:[生成Redis专家提示词并保存至~/.claude/agents/redis-expert.md]Example 2: Batch Generation
示例2:批量生成
User: /spawn
Agent: [Shows multi-tab AskUserQuestion with 3 tabs]
Tab 1 (Mode): Single Agent / Batch Generation / Architecture Analysis
Tab 2 (Scope): Project Agent / Global Agent
Tab 3 (Output): Create Files / Show in Chat / Both
User: [Submits]
Mode: Batch Generation
Scope: Project Agent
Output: Create Files
Agent: Please provide platforms (one per line):
User: PostgreSQL
Redis
RabbitMQ
Agent: [Creates 3 .md files in .claude/agents/ (project directory)]用户:/spawn
Agent:[显示包含3个标签页的多问题AskUserQuestion界面]
标签页1(模式):单个Agent / 批量生成 / 架构分析
标签页2(范围):项目Agent / 全局Agent
标签页3(输出):创建文件 / 在聊天中显示 / 两者皆选
用户:[提交]
模式:批量生成
范围:项目Agent
输出:创建文件
Agent:请提供平台列表(每行一个):
用户:PostgreSQL
Redis
RabbitMQ
Agent:[在.claude/agents/(项目目录)中创建3个.md文件]Example 3: Architecture Analysis
示例3:架构分析
User: /spawn
Agent: [Shows multi-tab AskUserQuestion with 3 tabs]
Tab 1 (Mode): Single Agent / Batch Generation / Architecture Analysis
Tab 2 (Scope): Project Agent / Global Agent
Tab 3 (Output): Create Files / Show in Chat / Both
User: [Submits]
Mode: Architecture Analysis
Scope: Global Agent
Output: Both
Agent: Describe your architecture or provide file path:
User: E-commerce platform: Next.js frontend, Node.js API, PostgreSQL, Redis cache, Stripe payments, AWS S3 storage, SendGrid emails
Agent: Found platforms: Next.js, Node.js, PostgreSQL, Redis, Stripe, AWS S3, SendGrid
[Shows multi-select AskUserQuestion]
User: [Selects: nextjs-expert, postgres-expert, redis-expert, stripe-expert]
Agent: [Generates 4 selected agents in ~/.claude/agents/]用户:/spawn
Agent:[显示包含3个标签页的多问题AskUserQuestion界面]
标签页1(模式):单个Agent / 批量生成 / 架构分析
标签页2(范围):项目Agent / 全局Agent
标签页3(输出):创建文件 / 在聊天中显示 / 两者皆选
用户:[提交]
模式:架构分析
范围:全局Agent
输出:两者皆选
Agent:请描述你的架构或提供文件路径:
用户:电商平台:Next.js前端、Node.js API、PostgreSQL、Redis缓存、Stripe支付、AWS S3存储、SendGrid邮件
Agent:识别到的平台:Next.js、Node.js、PostgreSQL、Redis、Stripe、AWS S3、SendGrid
[显示多选AskUserQuestion选择器]
用户:[选择:nextjs-expert、postgres-expert、redis-expert、stripe-expert]
Agent:[在~/.claude/agents/中生成4个选中的Agent]Implementation Steps
实现步骤
-
Ask All Questions at Once using a single multi-question AskUserQuestion call:
- Question 1 (header: "Mode"): Single Agent / Batch Generation / Architecture Analysis
- Question 2 (header: "Scope"): Project Agent (this project only) / Global Agent (all projects)
- Question 3 (header: "Output"): Create File / Show in Chat / Both
For Single Mode, also ask in the same call:- Question 4 (header: "Platform"): Offer "Custom Platform" option (user types in Other field)
- Question 5 (header: "Focus", multiSelect: true): General Coverage / [2-3 common focus areas for that tech]
-
For Single Mode:
- If user selected "Custom Platform", prompt for the platform name in chat
- Generate comprehensive prompt based on answers
- Create file and/or display based on output preference
-
For Batch Mode:
- Ask user to provide multi-line platform list in chat
- For each platform:
- Generate expert prompt
- Save to
.claude/agents/[platform]-expert.md
- Report completion with file paths
-
For Architecture Analysis:
- Ask user for architecture description in chat
- Parse and identify technologies
- Present checkbox selector using AskUserQuestion (multiSelect: true)
- Generate selected agents
- Save to files based on output preference
-
Generate Each Agent Prompt:
- Research official docs (WebSearch or WebFetch)
- Find 10+ authoritative URLs
- Structure according to template above
- Focus on patterns and best practices
- Target 500-1000 lines with comprehensive patterns
- Markdown formatted
-
Output:
- Determine file path based on Scope selection:
- Project Agent:
.claude/agents/[platform]-expert.md - Global Agent: (Unix/Mac) or
~/.claude/agents/[platform]-expert.md(Windows)C:\Users\[username]\.claude\agents\[platform]-expert.md
- Project Agent:
- If "Create File" or "Both": Use Write tool with appropriate path and complete YAML frontmatter + system prompt
- If "Show in Chat" or "Both": Display complete markdown (including frontmatter) in code block
- Confirm creation with full file path
- Remind user agent is immediately available via Task tool
- Determine file path based on Scope selection:
Important: Always use a single AskUserQuestion call with multiple questions (2-4) to create the multi-tab interface. Never ask questions sequentially one at a time.
-
一次性询问所有问题:使用单个多问题AskUserQuestion调用:
- 问题1(标题:"模式"):单个Agent / 批量生成 / 架构分析
- 问题2(标题:"范围"):项目Agent(仅限当前项目) / 全局Agent(所有项目)
- 问题3(标题:"输出"):创建文件 / 在聊天中显示 / 两者皆选
对于单个Agent模式,在同一调用中额外询问:- 问题4(标题:"平台"):提供"自定义平台"选项(用户在其他字段输入)
- 问题5(标题:"重点",multiSelect: true):全面覆盖 / [该技术的2-3个常见重点领域]
-
单个Agent模式处理:
- 如果用户选择"自定义平台",在聊天中提示用户输入平台名称
- 根据回答生成全面的提示词
- 根据输出偏好创建文件和/或显示内容
-
批量模式处理:
- 要求用户在聊天中提供多行平台列表
- 针对每个平台:
- 生成专家提示词
- 保存至
.claude/agents/[platform]-expert.md
- 完成后报告文件路径
-
架构分析模式处理:
- 要求用户在聊天中提供架构描述
- 解析并识别技术栈
- 使用AskUserQuestion展示多选选择器(multiSelect: true)
- 生成选中的Agent
- 根据输出偏好保存至文件
-
生成每个Agent提示词:
- 研究官方文档(使用WebSearch或WebFetch)
- 找到10个以上权威URL
- 按照上述模板构建内容
- 重点关注模式和最佳实践
- 目标生成500-1000行内容,包含全面的模式
- 采用Markdown格式
-
输出处理:
- 根据范围选择确定文件路径:
- 项目Agent:
.claude/agents/[platform]-expert.md - 全局Agent:(Unix/Mac)或
~/.claude/agents/[platform]-expert.md(Windows)C:\Users\[username]\.claude\agents\[platform]-expert.md
- 项目Agent:
- 如果选择"创建文件"或"两者皆选":使用Write工具写入对应路径,包含完整YAML前置元数据和系统提示词
- 如果选择"在聊天中显示"或"两者皆选":在代码块中显示完整Markdown内容(含前置元数据)
- 确认创建成功并显示完整文件路径
- 提醒用户Agent可立即通过Task工具使用
- 根据范围选择确定文件路径:
重要提示:始终使用单个包含多个问题(2-4个)的AskUserQuestion调用来创建多标签页界面。切勿逐个依次提问。
Quality Checklist
质量检查表
Before outputting each agent prompt, verify:
- YAML frontmatter present with required fields (name, description)
- Name uses lowercase-with-hyphens format
- Description is clear and specific (length is flexible)
- Tools field specified if restricting access (best practice: limit to necessary tools)
- 10+ authoritative URLs included in system prompt
- 10+ production-ready code examples included
- Complete dev and prod configuration files
- Testing patterns with actual test code
- Error handling patterns and exception hierarchy
- 5+ anti-patterns with bad/good code comparison
- Concise and scannable system prompt
- Clear use cases defined
- Integration points identified
- Common patterns referenced
- Anti-patterns listed
- Proper markdown formatting throughout
- Filename matches name field:
[name].md - Follows Claude Code subagent best practices (see documentation links above)
在输出每个Agent提示词前,需验证:
- 包含YAML前置元数据及必填字段(name、description)
- 名称采用小写连字符格式
- 描述清晰具体(长度灵活)
- 若限制工具访问则指定tools字段(最佳实践:仅授予必要工具)
- 系统提示词中包含10个以上权威URL
- 包含10个以上生产就绪的代码示例
- 包含完整的开发和生产环境配置文件
- 包含带实际测试代码的测试模式
- 包含错误处理模式和异常层级
- 包含5个以上反模式,附带错误/正确代码对比
- 系统提示词简洁易读
- 定义了清晰的使用场景
- 识别了集成点
- 引用了常见模式
- 列出了反模式
- 全程采用正确的Markdown格式
- 文件名与name字段匹配:
[name].md - 遵循Claude Code子Agent最佳实践(见上方文档链接)
Post-Generation
生成后操作
After creating agents, remind user:
- Review generated prompts
- Test agent with sample questions
- Refine based on actual usage
- Add to version control if satisfied
- Consult Claude Code documentation links above for advanced features and best practices
Additional Resources:
- Use command to view and manage all available agents
/agents - Refer to https://docs.claude.com/en/docs/claude-code/sub-agents for detailed subagent documentation
- Check https://docs.claude.com/en/docs/agents-and-tools/agent-skills/best-practices for authoring guidelines
创建Agent后,提醒用户:
- 审核生成的提示词
- 使用示例问题测试Agent
- 根据实际使用情况优化
- 若满意则添加至版本控制
- 如需高级功能和最佳实践,请参考上方Claude Code文档链接
额外资源:
- 使用命令查看和管理所有可用Agent
/agents - 如需详细子Agent文档,请参考https://docs.claude.com/en/docs/claude-code/sub-agents
- 如需编写指南,请查看https://docs.claude.com/en/docs/agents-and-tools/agent-skills/best-practices