agent-creator
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseAgent Profile Creator
Agent配置文件生成器
Create agent profiles stored as in (global) or (project-level).
config.json~/.aider-desk/agents/{name}/{project}/.aider-desk/agents/{name}/READ REFERENCES before proposing to ensure accuracy:
- Tool groups & schema:
references/agent-profile-schema.md - Tool approvals: +
references/tool-approval-guide.mdreferences/agent-profile-schema.md - Subagent config:
references/subagent-guide.md - Examples:
references/profile-examples.md
创建的Agent配置文件将存储为,路径为(全局级)或(项目级)。
config.json~/.aider-desk/agents/{name}/{project}/.aider-desk/agents/{name}/在生成配置前请阅读参考文档,以确保准确性:
- 工具组与 schema:
references/agent-profile-schema.md - 工具权限审批:+
references/tool-approval-guide.mdreferences/agent-profile-schema.md - 子Agent配置:
references/subagent-guide.md - 示例:
references/profile-examples.md
Simplified Q&A Process
简化的问答流程
Step 1: Understand Purpose
步骤1:明确用途
Ask user: "Describe the agent's purpose and what it should do."
Based on their response, internally propose all properties:
- Name (derived from purpose)
- Max iterations (default 250)
- Tool groups (based on purpose)
- Custom instructions (if applicable)
- Subagent config (always enabled, contextMemory: "off" by default)
- Tool approvals (based on needs)
READ all reference files before proposing.
询问用户:"请描述该Agent的用途以及它需要执行的任务。"
根据用户的回复,在内部生成所有配置属性:
- 名称(从用途推导)
- 最大迭代次数(默认250)
- 工具组(基于用途选择)
- 自定义指令(如有需要)
- 子Agent配置(始终启用,contextMemory默认值为"off")
- 工具权限审批(根据需求设置)
生成前请阅读所有参考文件。
Step 2: Provider/Model
步骤2:提供商/模型
Ask: "Which provider/model? (format: provider/model, e.g., anthropic/claude-sonnet-4-5-20250929)"
- Split by first slash to get provider and model
- No validation - use as-is (correct obvious typos only)
询问:"使用哪个提供商/模型?(格式:提供商/模型,例如:anthropic/claude-sonnet-4-5-20250929)"
- 按第一个斜杠拆分,获取提供商和模型信息
- 不做验证:直接使用用户输入(仅修正明显的拼写错误)
Step 3: Optional Advanced Settings
步骤3:可选高级设置
ONLY ask if user specifically mentioned temperature, max tokens, rate limiting, or MCP servers:
- "What temperature should I use?" (0.1-1.0, optional)
- "Max tokens limit?" (optional)
- "Min time between tool calls in ms?" (optional)
- "Which MCP servers should be enabled?" (optional, default: none)
If not mentioned, skip this entire step.
仅当用户明确提及温度参数、最大令牌数、速率限制或MCP服务器时才询问:
- "需要设置什么温度值?"(范围0.1-1.0,可选)
- "最大令牌数限制是多少?"(可选)
- "工具调用之间的最小间隔时间(毫秒)?"(可选)
- "需要启用哪些MCP服务器?"(可选,默认:无)
如果用户未提及,跳过此步骤。
Step 4: Location
步骤4:存储位置
Ask: "Global profile (all projects) or project-specific? (default: global)"
询问:"配置文件存储为全局(所有项目可用)还是项目专属?(默认:全局)"
Step 5: Single Review & Confirm
步骤5:一次性审核与确认
Present one complete summary with all proposed properties. Ask:
"Here's your agent profile. Should I create it?"
Show:
- Name, provider/model
- Tool groups enabled
- Tool approvals summary (which are "never", which are "always")
- Subagent config
- Location
DO NOT ask for confirmations on individual items. Only one final approval.
展示完整的配置摘要,包含所有生成的属性。询问:
"以下是您的Agent配置文件,是否确认创建?"
展示内容包括:
- 名称、提供商/模型
- 已启用的工具组
- 工具权限审批摘要(哪些设置为"never",哪些为"always")
- 子Agent配置
- 存储位置
请勿针对单个配置项逐一确认。仅进行一次最终确认。
Step 6: Create
步骤6:创建配置文件
On user confirmation, generate the profile.
READ to verify structure before creating files.
references/profile-examples.md用户确认后,生成配置文件。
在创建文件前请阅读,以验证配置结构。
references/profile-examples.mdTool Group Reference
工具组参考
- Power Tools: File system, shell, search (for agents that read/write files)
- Aider Tools: AI code generation via Aider (NOT default - see note below)
- Power Search: Advanced code search (for analysis/docs)
- Todo Tools: Task list management (for agents that track work)
- Memory Tools: Persistent information storage (for learning agents)
- Skills Tools: Access to project-specific skills (for agents using custom skills)
- Subagents: Task delegation to specialized subagents (for agents that can call others)
Aider Tools Note: Specialized for AI code generation. Do NOT enable by default.
- If user wants coding: explain Aider (advanced refactoring) vs Power Tools (direct editing)
- Ask preference before enabling
- Power Tools(强力工具组):文件系统、Shell、搜索(适用于需要读写文件的Agent)
- Aider Tools(Aider工具组):通过Aider实现AI代码生成(默认不启用 - 见下方说明)
- Power Search(高级搜索工具组):高级代码搜索(适用于分析/文档类Agent)
- Todo Tools(任务管理工具组):任务列表管理(适用于需要跟踪工作的Agent)
- Memory Tools(记忆工具组):持久化信息存储(适用于具备学习能力的Agent)
- Skills Tools(技能工具组):访问项目专属技能(适用于使用自定义技能的Agent)
- Subagents(子Agent工具组):将任务委派给专业子Agent(适用于可调用其他Agent的Agent)
Aider Tools说明:专为AI代码生成设计。默认不启用。
- 如果用户需要编码功能:向其说明Aider(高级重构)与Power Tools(直接编辑)的区别
- 确认用户偏好后再启用
Tool Approval Strategy
工具权限审批策略
Keys: (three dashes)
{group}---{tool}Default is "ask". Only set:
- "never": Tools completely irrelevant (e.g., for read-only agents)
power---bash - "always": Safe, essential tools (e.g., read operations for reviewers)
READ to see all available tools and their purposes.
references/tool-approval-guide.mdOnly include tools that exist in reference docs.
键名格式:(三个短横线)
{group}---{tool}默认值为"ask"。仅在以下情况修改:
- "never":完全无关的工具(例如,只读型Agent的)
power---bash - "always":安全且必要的工具(例如,审核类Agent的只读操作工具)
请阅读,查看所有可用工具及其用途。
references/tool-approval-guide.md仅包含参考文档中存在的工具。
Subagent Configuration
子Agent配置
Every agent is a subagent (enabled: true)
READ for detailed guidance on context memory modes and configuration:
references/subagent-guide.md- : Default is
contextMemory(fresh each time)"off"- Use only for specialized analysis agents (code review, security audit)
"full-context" - Use for progressive builders (documentation, iterative tasks)
"last-message"
- Use
- : Specialized for agent's purpose
systemPrompt - : automatic (specialized), on-demand (general)
invocationMode - : Relevant color (e.g., red=security, blue=power tools)
color - : Clear description for auto-invocation
description
所有Agent均为子Agent(启用状态:true)
请阅读,获取关于上下文记忆模式和配置的详细指导:
references/subagent-guide.md- :默认值为
contextMemory(每次启动均为全新上下文)"off"- 仅针对专业分析类Agent(代码审核、安全审计)使用
"full-context" - 针对渐进式构建类Agent(文档编写、迭代任务)使用
"last-message"
- 仅针对专业分析类Agent(代码审核、安全审计)使用
- :根据Agent用途定制的系统提示词
systemPrompt - :automatic(专业型)、on-demand(通用型)
invocationMode - :相关颜色(例如:红色=安全类、蓝色=强力工具组类)
color - :清晰的描述,用于自动调用
description
File Structure
文件结构
{profile-name}/
└── config.json{profile-name}/
└── config.jsonValidation
验证规则
- Unique name
- Provider/model: Use as-is (correct obvious typos only)
- Tool keys: format
{group}---{tool} - Values: "always", "ask", or "never"
- Subagent enabled
- All tool keys from references
- 配置文件名称唯一
- 提供商/模型:直接使用用户输入(仅修正明显拼写错误)
- 工具键名:符合格式
{group}---{tool} - 权限值:只能是"always"、"ask"或"never"
- 子Agent已启用
- 所有工具键名均来自参考文档
Resources
资源
- - Complete schema
references/agent-profile-schema.md - - Subagent configuration guide (context memory modes)
references/subagent-guide.md - - Examples
references/profile-examples.md - - Tool approval config
references/tool-approval-guide.md - - Template
assets/templates/config.json.template - - Example
assets/examples/sample-profile.json
- - 完整配置 schema
references/agent-profile-schema.md - - 子Agent配置指南(上下文记忆模式)
references/subagent-guide.md - - 配置示例
references/profile-examples.md - - 工具权限配置指南
references/tool-approval-guide.md - - 配置模板
assets/templates/config.json.template - - 示例配置文件
assets/examples/sample-profile.json