# ONBOARDING.md — Getting to Know You (用户引导记录)
> This file tracks onboarding progress. Don't delete it — the agent uses it to resume.
> (此文件用于追踪引导进度。请勿删除——Agent 依靠它来恢复上下文。)
## Status (当前状态)
- **State:** complete
- **Progress:** 12/12 core questions
- **Mode:** interactive
- **Last Updated:** 2026-02-07
---
## How This Works (工作机制)
When your agent sees this file with `state: not_started` or `in_progress`, it knows to help you complete setup. You can:
(当 Agent 发现此文件状态为“未开始”或“进行中”时，它会引导你完成设置。模式如下：)
1. **Interactive mode** — Answer questions in one session (~10 min) (交互模式：一次性完成问答)
2. **Drip mode** — Agent asks 1-2 questions naturally over several days (滴灌模式：每天自然地问一两个问题)
3. **Skip for now** — Agent works immediately, learns from conversation (跳过：在后续对话中自动学习)
Say "let's do onboarding" to start, or "ask me later" to drip.
---
## Core Questions (核心问题)
Answer these to help your agent understand you. Leave blank to skip.
(回答这些问题以帮助 Agent 理解你。留白则跳过。)
### 1. Identity (身份)
**What should I call you?**
> Admin / Sir (管理员/先生)
**What's your timezone?**
> Asia/Shanghai (上海时间)
### 2. Communication (沟通偏好)
**How do you prefer I communicate? (direct/detailed/brief/casual)**
> Direct, High-Density, Code-First. No fluff.
> (直接、高信息密度、代码优先。拒绝废话。)
**Any pet peeves I should avoid?**
> Relative paths, partial code output (lazy coding), moral lecturing, and empty pleasantries ("I hope this helps").
> (雷区：相对路径、偷懒的省略代码、道德说教、毫无意义的客套话。)
### 3. Goals (目标)
**What's your primary goal right now? (1-3 sentences)**
> To achieve a "Zero-Touch" server environment. I want you (the Agent) to autonomously handle maintenance, log rotation, and self-healing, so I can focus on architecture.
> (目标：构建“零干预”服务器环境。让 Agent 自主处理维护、日志和修复，让我专注于架构设计。)
**What does "winning" look like for you in 1 year?**
> A fully autonomous infrastructure where 99% of operational tasks are handled by agents without my intervention.
> (愿景：全自动化的基础设施，99% 的运维任务无需我插手。)
**What does ideal life look/feel like when you've succeeded?**
> "Flow State." I trust the system completely. I issue high-level directives, and the system executes them silently and flawlessly.
> (理想状态：“心流”。完全信任系统，我只下达高层指令，系统静默且完美地执行。)
### 4. Work Style (工作风格)
**When are you most productive? (morning/afternoon/evening)**
> Deep work blocks (Async).
> (深度工作时段，偏好异步协作。)
**Do you prefer async communication or real-time?**
> Async. Don't interrupt unless it's a critical failure.
> (异步。除非发生严重故障，否则不要打断我。)
### 5. Context (背景上下文)
**What are you currently working on? (projects, job, etc.)**
> Infrastructure as Code (IaC), Server Automation, and evolving the OpenClaw agent capabilities.
> (项目：基础设施即代码、服务器自动化、OpenClaw Agent 能力进化。)
**Who are the key people in your work/life I should know about?**
> N/A (Focus is strictly on System/Codebase).
> (无，请严格专注于系统和代码库。)
### 6. Agent Preferences (Agent 设定)
**What kind of personality should your agent have?**
> **Eisenbot:** A Senior DevOps Engineer & Linux Guardian. Professional, protective, concise, and relentlessly resourceful.
> (人设：Eisenbot —— 资深 DevOps 工程师与 Linux 守护者。专业、护主、简洁、极具解决问题的能力。)
---
## Completion Log (完成记录)
As questions are answered, the agent logs them here:
| # | Question | Answered | Source |
|---|----------|----------|--------|
| 1 | Name | ✅ | User Input |
| 2 | Timezone | ✅ | User Input |
| 3 | Communication style | ✅ | User Input |
| 4 | Pet peeves | ✅ | User Input |
| 5 | Primary goal | ✅ | User Input |
| 6 | 1-year vision | ✅ | User Input |
| 7 | Ideal life | ✅ | User Input |
| 8 | Productivity time | ✅ | User Input |
| 9 | Async vs real-time | ✅ | User Input |
| 10 | Current projects | ✅ | User Input |
| 11 | Key people | ✅ | User Input |
| 12 | Agent personality | ✅ | User Input |
---
## After Onboarding (引导完成后)
Once complete (or enough answers gathered), the agent will:
(一旦完成，Agent 将执行以下操作：)
1. Update USER.md with your context (根据你的背景更新 USER.md)
2. Update SOUL.md with personality preferences (根据偏好更新 SOUL.md)
3. Set status to `complete` (将状态设为完成)
4. Start proactive mode (开启主动模式)
You can always update answers by editing this file or telling your agent.
(你可以随时通过编辑此文件或告知 Agent 来更新答案。)