Back to Details

wiki-new

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Personal Wiki — Onboarding Wizard

个人维基——搭建向导

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将充当图书管理员——读取原始资料，将其编译为结构化的互联维基，并长期维护。

Wizard Flow

向导流程

Guide the user through these 3 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3个步骤。每次只提出一个问题。每个步骤都有合理的默认值——用户可以接受默认值或提供自定义值。

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 CLAUDE.md config.
提问：
“您想给知识库起什么名字？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。该名称将成为文件夹名称以及CLAUDE.md配置文件中的标题。

Step 2: Vault Location

步骤2：Vault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：
“我应该在哪里创建它？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 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 CLAUDE.md config.
提问：
“这个知识库是关于什么的？这有助于我描述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”
接受任意自由文本。使用该内容为CLAUDE.md配置文件编写一行领域描述。

Post-Wizard: Scaffold the Vault

向导完成后：搭建Vault结构

After collecting all answers, execute these steps in order:
收集所有答案后，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.
运行入职脚本，传入完整的vault路径：
bash <skill-directory>/scripts/onboarding.sh <vault-path>
这将创建所有目录以及初始的
wiki/index.md
和
wiki/log.md
文件。

2. Generate CLAUDE.md

2. 生成CLAUDE.md

Read the template from 
<skill-directory>/references/agent-configs/claude-code.md
.
Replace the placeholders:
  • {{VAULT_NAME}}
    → the vault name from Step 1
  • {{DOMAIN_DESCRIPTION}}
    → a one-line description derived from Step 3
  • {{WIKI_SCHEMA}}
    → read 
    <skill-directory>/references/wiki-schema.md
    and insert everything from 
    ## Architecture
    onward
Write the generated CLAUDE.md to the vault root.
从
<skill-directory>/references/agent-configs/claude-code.md
读取模板。
替换占位符：
  • {{VAULT_NAME}}
    → 步骤1中的vault名称
  • {{DOMAIN_DESCRIPTION}}
    → 从步骤3衍生的一行描述
  • {{WIKI_SCHEMA}}
    → 读取
    <skill-directory>/references/wiki-schema.md
    并插入从
    ## Architecture
    开始的所有内容
将生成的CLAUDE.md写入vault根目录。

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 initialized

Created vault "{{VAULT_NAME}}" for {{DOMAIN_DESCRIPTION}}.
undefined
Created vault "{{VAULT_NAME}}" for {{DOMAIN_DESCRIPTION}}.
undefined

4. Print summary

4. 打印摘要

Show the user:
  1. What was created — directory tree and CLAUDE.md
  2. 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
  3. How to start — open the vault folder in Obsidian, clip an article to 
    raw/
    , then run 
    /wiki-ingest
向用户展示：
  1. 已创建内容——目录树和CLAUDE.md
  2. 必要的下一步——安装Obsidian Web Clipper浏览器扩展：
    安装Obsidian Web Clipper，轻松将网页文章保存到您的vault中： https://chromewebstore.google.com/detail/obsidian-web-clipper/cnjifjpddelmedmihgijeibhnjfabmlf
  3. 启动方式——在Obsidian中打开vault文件夹，将文章剪辑到
    raw/
    目录，然后运行
    /wiki-ingest

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 CLAUDE.md config)
  • agent-configs/claude-code.md
    — CLAUDE.md template
这些文件随本skill捆绑提供，位于
<skill-directory>/references/
：
  • wiki-schema.md
    ——标准维基规则（CLAUDE.md配置文件的单一事实来源）
  • agent-configs/claude-code.md
    ——CLAUDE.md模板

Next Steps

后续步骤

After setup is complete, the user's workflow is:
  1. Clip articles to 
    raw/
    using the Obsidian Web Clipper
  2. Ingest sources with 
    /wiki-ingest
    — processes raw files into wiki pages
  3. Ask questions with 
    /wiki-query
    — searches and synthesizes from the wiki
  4. Health-check with 
    /wiki-lint
    — run after every 10 ingests or monthly
  5. Discover connections with 
    /wiki-explore
    — find cross-domain patterns
  6. Get inspired with 
    /wiki-spark
    — generate creative prompts from your wiki
设置完成后，用户的工作流程如下：
  1. 剪辑文章——使用Obsidian Web Clipper将文章保存到
    raw/
    目录
  2. 导入资料——使用
    /wiki-ingest
    将原始文件处理为维基页面
  3. 提问——使用
    /wiki-query
    从维基中搜索并整合信息
  4. 健康检查——每导入10次或每月运行一次
    /wiki-lint
  5. 发现关联——使用
    /wiki-explore
    查找跨领域模式
  6. 获取灵感——使用
    /wiki-spark
    从您的维基生成创意提示