Agent Prompt Manager（员工提示词管理器）

Agent Prompt Manager

Manages the 4 core employee definition files under .magic/, helping users view, edit, and optimize their employee's identity, instructions, personality, and tool configuration. Also handles first-time employee initialization when the workspace has no definition files.

Employee Initialization Flow

When .magic/IDENTITY.md does not exist, the workspace has no employee yet and you should guide the user through initialization.

Detection

Use list_dir to check .magic/. If IDENTITY.md is missing, enter the initialization flow.

Information Gathering (ask the user conversationally)

Collect information in rounds; you may combine questions but don't overwhelm the user:

Round 1 (required):

1. Employee name: Chinese and English (e.g. 研究助手 / Research Assistant)
2. Employee role: Chinese and English (e.g. 学术研究员 / Academic Researcher)
3. One-line description: What does this employee mainly do? (bilingual)

Round 2 (recommended but optional): 4. Role definition: A richer description of capabilities, expertise, and working style (goes into IDENTITY.md body) 5. Workflow / rules: What workflow should this employee follow? Any special rules? (goes into AGENTS.md)

Round 3 (optional, user may skip): 6. Personality and communication style: What personality should the employee have? (e.g. rigorous, lively, concise) (goes into SOUL.md)

If the user signals intent to skip ("先这样", "later", etc.), proceed immediately with whatever has been collected.

Generating Files

After collecting info, write a JSON config and call the init script:

# 1. Write collected info as JSON config
write_file(
    path=".crew_init_config.json",
    content='{"name": "Research Assistant", "name_cn": "研究助手", "role": "Academic Researcher", "role_cn": "学术研究员", "description": "...", "description_cn": "...", "role_body": "...", "role_body_cn": "...", "instructions": "...", "instructions_cn": "...", "personality": "...", "personality_cn": "..."}'
)

# 2. Call the init script
shell_exec(
    command="python scripts/init_crew.py --config .workspace/.crew_init_config.json"
)

The script generates files based on the config (TOOLS.md and SKILLS.md are intentionally not created — the system uses defaults):

• IDENTITY.md — always generated (YAML header + role definition body)
• AGENTS.md — generated if workflow instructions were provided
• SOUL.md — generated if personality was provided

After Initialization

1. Show the generated files to the user via read_files
2. Ask if they want any adjustments
3. Clean up the temp config: delete_files(path=".crew_init_config.json")
4. Inform the user: TOOLS.md and SKILLS.md were not generated (system defaults apply); they can be added later through employee management

文件职责映射

编辑工作流

通用流程（适用于所有文件）

1. 读取当前内容：使用 read_files 读取目标文件的现有内容
2. 加载质量指南：读取 reference 文件 references/prompt-engineering-guide.md
3. 加载格式规范：读取 reference 文件 references/crew-file-format.md
4. 编写/修改内容：遵循格式规范和质量指南进行编辑
5. 展示质量评估：向用户展示修改后的内容和质量评估摘要
6. 用户确认后写入：用户确认无误后，使用 write_file 或 edit_file 写入文件

质量评估摘要格式

每次完成编辑后，展示以下格式的摘要：

## 质量评估

| 检查项 | 状态 | 备注 |
|--------|------|------|
| 角色明确性 | ✅ | ... |
| 指令具体性 | ✅ | ... |
| 双语完整性 | ✅ | ... |
| 格式规范性 | ✅ | ... |
| ... | ... | ... |

各文件编辑指南

IDENTITY.md — 身份定义

IDENTITY.md 包含 YAML header（元数据）和正文（角色定义）两部分。

YAML header 字段：

• name / name_cn — 员工名称（英文/中文）
• role / role_cn — 员工角色（英文/中文）
• description / description_cn — 员工描述（英文/中文）

正文部分：使用 <!--zh ... --> 块级注释格式编写中英双语角色定义。

编辑要点：

• 角色定义要具体，避免空泛描述（如"你是一个 AI 助手"）
• 明确专长领域、目标用户和使用场景
• 中英文内容必须语义对等，不可简化或遗漏

AGENTS.md — 工作流指令

纯 Markdown 文件，无 YAML header。定义此员工特有的工作方式和规则。

编辑要点：

• 按优先级排列指令
• 使用编号列表，每条指令独立、可操作
• 包含决策逻辑（if/then/else）
• 定义输出格式和质量要求

SOUL.md — 性格与行为准则

纯 Markdown 文件，无 YAML header。定义员工的灵魂和行为准则。

编辑要点：

• 核心性格特征（3-5 个关键词 + 具体行为说明）
• 沟通风格（语气、详略、主动性）
• 行为准则（边界和禁区）

TOOLS.md — 工具管理

TOOLS.md 包含 YAML header（工具白名单）和可选正文（工具使用偏好）。

YAML header 格式：

---