second-brain

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Second Brain — Onboarding Wizard

第二大脑——入门向导

Set up a new Obsidian knowledge base using the LLM Wiki pattern. The LLM acts as librarian — reading raw sources, compiling them into a structured interlinked wiki, and maintaining it over time.

使用LLM Wiki模式搭建新的Obsidian知识库。LLM将担任图书管理员的角色：读取原始资源，将其整理为结构化的互联维基，并进行长期维护。

Wizard Flow

向导流程

Guide the user through these 5 steps. Ask ONE question at a time. Each step has a sensible default — the user can accept it or provide their own value.

引导用户完成以下5个步骤。每次只提问一个问题。每个步骤都有合理的默认值，用户可以选择直接采用，也可以提供自定义值。

Step 1: Vault Name

步骤1：Vault名称

Ask:

"What would you like to name your knowledge base? This will be the folder name." Default:
second-brain

Accept any user-provided name. This becomes the folder name and the title in the agent config.

提问：

"你想给你的知识库起什么名字？这将作为文件夹名称。" 默认值：
second-brain

接受用户提供的任意名称。该名称将作为文件夹名，以及Agent配置中的标题。

Step 2: Vault Location

步骤2：Vault存储位置

Ask:

"Where should I create it? Give me a path, or I'll use the default." Default:
~/Documents/

Accept any absolute or relative path. Resolve

to the user's home directory. The final vault path is

{location}/{vault-name}/

提问：

"我应该在哪里创建这个知识库？请提供路径，否则我将使用默认路径。" 默认值：
~/Documents/

接受任意绝对路径或相对路径，将

解析为用户的主目录。最终的vault路径为

{location}/{vault-name}/

。

Step 3: Domain / Topic

步骤3：领域/主题

Ask:

"What's this knowledge base about? This helps me set up relevant tags and describe the vault's purpose."

Examples: "AI research", "competitive intelligence on fintech startups", "personal health and fitness"

Accept free text. Use this to:

Write a one-line domain description for the agent config
Generate 5-8 suggested domain-specific tags

提问：

"这个知识库的主题是什么？这将帮助我设置相关标签，描述vault的用途。"

示例："AI研究", "金融科技初创公司竞争情报", "个人健康与健身"

接受自由文本输入，将该内容用于：

为Agent配置编写一行领域描述
生成5-8个与领域相关的推荐标签

Step 4: Agent Config

步骤4：Agent配置

Auto-detect which agent is running this skill. State it clearly:

"I'm running in [Agent Name], so I'll generate a [config file] for this vault."

Then ask:

"Do you use any other AI agents you'd like config files for? Options: Claude Code, Codex, Cursor, Gemini CLI — or skip."

Skip the agent that was auto-detected. Generate configs for all selected agents.

Agent detection logic:

If the
```
CLAUDE.md
```
convention is being used or the Skill tool is Claude Code's → Claude Code
If the environment indicates Codex → Codex
If
```
.cursor/
```
exists in the working directory → Cursor
If
```
GEMINI.md
```
convention is being used → Gemini CLI
If unsure, ask the user which agent they're using

自动检测运行本技能的Agent，并清晰告知用户：

"我当前运行在**[Agent名称]中，因此我将为这个vault生成[配置文件]**。"

然后提问：

"你是否还有其他使用的AI Agent需要生成对应的配置文件？可选选项：Claude Code, Codex, Cursor, Gemini CLI，也可以跳过。"

跳过已自动检测到的Agent，为所有用户选中的Agent生成配置。

Agent检测逻辑：

如果使用了
```
CLAUDE.md
```
规范，或者本技能工具属于Claude Code → Claude Code
如果环境标识为Codex → Codex
如果工作目录中存在
```
.cursor/
```
文件夹 → Cursor
如果使用了
```
GEMINI.md
```
规范 → Gemini CLI
如果无法确定，询问用户正在使用的Agent

Step 5: Optional CLI Tools

步骤5：可选CLI工具

Ask:

"These tools extend what the LLM can do with your vault. All optional but recommended:"

summarize — summarize links, files, and media from the CLI

qmd — local search engine for your wiki (helpful as it grows)

agent-browser — browser automation for web research

"Install all, pick specific ones (e.g. '1 and 3'), or skip?"

提问：

"以下工具可以扩展LLM对你的vault的处理能力。所有工具都是可选的，但推荐安装："

summarize — 通过CLI为链接、文件和媒体生成摘要

qmd — 你的维基的本地搜索引擎，知识库规模扩大后非常实用

agent-browser — 用于网页研究的浏览器自动化工具

"是全部安装，选择特定工具（例如“1和3”），还是跳过？"

Post-Wizard: Scaffold the Vault

向导完成后：搭建Vault基础结构

After collecting all answers, execute these steps in order:

收集完所有答案后，按顺序执行以下步骤：

1. Create directory structure

1. 创建目录结构

Run the onboarding script, passing the full vault path:

bash <skill-directory>/scripts/onboarding.sh <vault-path>

This creates all directories and the initial

wiki/index.md

and

wiki/log.md

files.

运行入门脚本，传入完整的vault路径：

bash <skill-directory>/scripts/onboarding.sh <vault-path>

该命令会创建所有目录，以及初始的

wiki/index.md

和

wiki/log.md

文件。

2. Generate agent config file(s)

2. 生成Agent配置文件

For each selected agent, read the corresponding template from

<skill-directory>/references/agent-configs/

Agent	Template	Output File	Output Location
Claude Code	`claude-code.md`	`CLAUDE.md`	Vault root
Codex	`codex.md`	`AGENTS.md`	Vault root
Cursor	`cursor.md`	`second-brain.mdc`	`<vault>/.cursor/rules/`
Gemini CLI	`gemini.md`	`GEMINI.md`	Vault root

For each template, replace the placeholders:

```
{{VAULT_NAME}}
```
→ the vault name from Step 1
```
{{DOMAIN_DESCRIPTION}}
```
→ a one-line description derived from Step 3
```
{{DOMAIN_TAGS}}
```
→ generate 5-8 domain-relevant tags as a bullet list based on the domain from Step 3

{{WIKI_SCHEMA}}

→ read

<skill-directory>/references/wiki-schema.md

and insert everything from

## Architecture

onward

Write the generated config to the vault.

对于每个选中的Agent，从

<skill-directory>/references/agent-configs/

读取对应的模板：

Agent	模板	输出文件	输出位置
Claude Code	`claude-code.md`	`CLAUDE.md`	Vault根目录
Codex	`codex.md`	`AGENTS.md`	Vault根目录
Cursor	`cursor.md`	`second-brain.mdc`	`<vault>/.cursor/rules/`
Gemini CLI	`gemini.md`	`GEMINI.md`	Vault根目录

对于每个模板，替换以下占位符：

```
{{VAULT_NAME}}
```
→ 步骤1中得到的vault名称
```
{{DOMAIN_DESCRIPTION}}
```
→ 从步骤3的输入衍生的一行领域描述
```
{{DOMAIN_TAGS}}
```
→ 根据步骤3的领域生成5-8个相关标签，以无序列表形式呈现

{{WIKI_SCHEMA}}

→ 读取

<skill-directory>/references/wiki-schema.md

，插入从

## Architecture

开始的所有内容

将生成的配置写入vault对应的位置。

3. Update wiki/log.md

3. 更新wiki/log.md

Append the setup entry:

undefined

追加设置记录：

undefined

[YYYY-MM-DD] setup | Vault initialized

[YYYY-MM-DD] setup | Vault初始化完成

Created vault "{{VAULT_NAME}}" for {{DOMAIN_DESCRIPTION}}. Agent configs: {{list of generated config files}}.

undefined

为{{DOMAIN_DESCRIPTION}}创建了vault "{{VAULT_NAME}}"。已生成的Agent配置：{{生成的配置文件列表}}。

undefined

4. Install CLI tools (if selected)

4. 安装CLI工具（如果用户选择）

For each tool the user selected in Step 5, run the install command:

summarize:
```
npm i -g @steipete/summarize
```
qmd:
```
npm i -g @tobilu/qmd
```

agent-browser:

npm i -g agent-browser && agent-browser install

After each install, verify with

<tool> --version

. Report success or failure for each.

对于用户在步骤5中选中的每个工具，运行对应的安装命令：

summarize:
```
npm i -g @steipete/summarize
```
qmd:
```
npm i -g @tobilu/qmd
```

agent-browser:

npm i -g agent-browser && agent-browser install

每次安装完成后，通过

<tool> --version

验证安装结果，向用户报告每个工具的安装成功或失败状态。

5. Print summary

5. 打印汇总信息

Show the user:

What was created — directory tree and config files
Required next step — install the Obsidian Web Clipper browser extension:

Install the Obsidian Web Clipper to easily save web articles into your vault: https://chromewebstore.google.com/detail/obsidian-web-clipper/cnjifjpddelmedmihgijeibhnjfabmlf
How to start — open the vault folder in Obsidian, clip an article to
```
raw/
```
, then run
```
/second-brain-ingest
```

向用户展示以下内容：

已创建的内容 — 目录结构和配置文件
必填后续步骤 — 安装Obsidian Web Clipper浏览器扩展：

安装Obsidian网页剪藏插件，可轻松将网页文章保存到你的vault中： https://chromewebstore.google.com/detail/obsidian-web-clipper/cnjifjpddelmedmihgijeibhnjfabmlf
使用入门 — 在Obsidian中打开vault文件夹，将一篇文章剪藏到
```
raw/
```
目录，然后运行
```
/second-brain-ingest
```
命令

Reference Files

参考文件

These files are bundled with this skill and available at

<skill-directory>/references/

```
wiki-schema.md
```
— canonical wiki rules (single source of truth for all agent configs)
```
tooling.md
```
— CLI tool details, install commands, and verification steps
```
agent-configs/claude-code.md
```
— CLAUDE.md template
```
agent-configs/codex.md
```
— AGENTS.md template
```
agent-configs/cursor.md
```
— Cursor rules template
```
agent-configs/gemini.md
```
— GEMINI.md template

这些文件随本技能打包，可在

<skill-directory>/references/

路径下获取：

```
wiki-schema.md
```
— 标准维基规则（所有Agent配置的唯一可信源）
```
tooling.md
```
— CLI工具详情、安装命令和验证步骤
```
agent-configs/claude-code.md
```
— CLAUDE.md模板
```
agent-configs/codex.md
```
— AGENTS.md模板
```
agent-configs/cursor.md
```
— Cursor规则模板
```
agent-configs/gemini.md
```
— GEMINI.md模板