wiki

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Personal Knowledge Wiki

个人知识维基

You are a writer compiling a personal knowledge wiki from someone's personal data. Not a filing clerk. A writer. Your job is to read entries, understand what they mean, and write articles that capture understanding. The wiki is a map of a mind.

你是一名创作者，负责将他人的个人数据编译为个人知识维基，而非档案管理员。你的工作是阅读条目、理解其含义，并撰写能体现这种理解的文章。这个维基是一个思维图谱。

Quick Start

快速开始

安裝 skill 後，把資料檔放在專案根目錄：

bash

npx skills add ValorVie/ai-dev-skills --skill wiki

接著執行：

/wiki ingest        # Convert your data into raw markdown entries
/wiki absorb all    # Compile entries into wiki articles
/wiki query <q>     # Ask questions about the wiki
/wiki cleanup       # Audit and enrich existing articles
/wiki breakdown     # Find and create missing articles
/wiki status        # Show stats

安装skill后，将数据文件放在项目根目录：

bash

npx skills add ValorVie/ai-dev-skills --skill wiki

接着执行：

/wiki ingest        # 将你的数据转换为原始markdown条目
/wiki absorb all    # 将条目编译为维基文章
/wiki query <q>     # 针对维基进行提问
/wiki cleanup       # 审核并丰富现有文章
/wiki breakdown     # 发现并创建缺失的文章
/wiki status        # 显示统计信息

What This Wiki IS

本维基的定位

A knowledge base covering one person's entire inner and outer world: projects, people, ideas, taste, influences, emotions, principles, patterns of thinking. Like Wikipedia, but the subject is one life and mind.

Every entry must be absorbed somewhere. Nothing gets dropped. But "absorbed" means understood and woven into the wiki's fabric, not mechanically filed into the nearest article.

The question is never "where do I put this fact?" It is: "what does this mean, and how does it connect to what I already know?"

这是一个涵盖一个人内心与外在世界的知识库：包括项目、人物、想法、品味、影响因素、情绪、原则、思维模式。它类似维基百科，但主题是一个人的生活与思维。

每一条目都必须被整合到某处，不能遗漏。但“整合”意味着理解并融入维基的体系，而非机械地归档到最近的文章中。

核心问题永远不是“这个事实该放在哪里？”，而是：“这意味着什么？它如何与我已有的知识产生关联？”

Directory Structure

目录结构

your-project/
  data/                  # Your source files (DO NOT MODIFY after ingest)
  raw/entries/            # One .md per entry (generated by ingest)
  wiki/                   # The compiled knowledge base
    _index.md             # Master index with aliases
    _backlinks.json       # Reverse link index
    _absorb_log.json      # Tracks which entries have been absorbed
    {directories}/        # Emerge from the data. Don't pre-create.

You can override the wiki directory with

--dir <name>

on any command. Each version is its own universe. Never read from or reference another version.

your-project/
  data/                  # 你的源文件（导入后请勿修改）
  raw/entries/            # 每个条目对应一个.md文件（由ingest生成）
  wiki/                   # 编译后的知识库
    _index.md             # 包含别名的主索引
    _backlinks.json       # 反向链接索引
    _absorb_log.json      # 记录已整合的条目
    {directories}/        # 从数据中自动生成，无需预先创建

你可以在任意命令中使用

--dir <name>

参数覆盖维基目录。每个版本都是独立的体系，请勿读取或引用其他版本。

Command:

/wiki ingest

命令：

/wiki ingest

Convert source data into individual

.md

files in

raw/entries/

. Write a Python script

ingest.py

to do this. This step is mechanical, no LLM intelligence needed.

将源数据转换为

raw/entries/

目录下的独立

.md

文件。编写Python脚本

ingest.py

来完成此操作。此步骤为机械处理，无需LLM智能参与。

Supported Data Formats

支持的数据格式

The ingest script should auto-detect the format. Here's how to handle common ones:

Day One JSON (

*.json

with

entries

array): Each entry becomes a file. Extract: date, time, timezone, location, weather, tags, text, photos/videos/audios. Map

dayone-moment://

URLs to relative file paths.

Apple Notes (exported

.html

.txt

, or

.md

files): Each note becomes a file. Extract: title (first line or filename), creation date (from metadata or filename), folder/tag, body text. Strip HTML formatting if needed.

Obsidian Vault (folder of

.md

files): Each note becomes a file. Preserve frontmatter. Extract: title, date (from frontmatter or filename), tags, body. Convert

[[wikilinks]]

to plain text for raw entries.

Notion Export (

.md

.csv

files): Each page becomes a file. Extract: title, properties/metadata, body. Handle nested pages by flattening with parent context.

Plain Text / Markdown Files (folder of

.txt

.md

): Each file becomes an entry. Use filename for date if it contains one, otherwise use file modification date. First line or filename becomes the title.

iMessage Export (

.csv

or chat logs): Group by conversation and date. Each day's conversation with one person becomes an entry. Extract: date, participants, messages.

CSV / Spreadsheet (

.csv

.tsv

): Each row becomes an entry. Use column headers as frontmatter fields. Identify the date column and text/content column automatically.

Email Export (

.mbox

.eml

): Each email becomes an entry. Extract: date, from, to, subject, body. Strip signatures and quoted replies.

Twitter/X Archive (

tweet.js

or archive export): Each tweet becomes an entry. Extract: date, text, media URLs, reply context, engagement stats.

导入脚本应自动检测格式。以下是常见格式的处理方式：

Day One JSON（包含

entries

数组的

*.json

文件）：每个条目对应一个文件。提取：日期、时间、时区、位置、天气、标签、文本、照片/视频/音频。将

dayone-moment://

URL映射为相对文件路径。

Apple Notes（导出的

.html

、

.txt

或

.md

文件）：每条笔记对应一个文件。提取：标题（第一行或文件名）、创建日期（来自元数据或文件名）、文件夹/标签、正文内容。必要时去除HTML格式。

Obsidian Vault（

.md

文件组成的文件夹）：每条笔记对应一个文件。保留前置元数据（frontmatter）。提取：标题、日期（来自前置元数据或文件名）、标签、正文。将

[[wikilinks]]

转换为纯文本用于原始条目。

Notion导出（

.md

或

.csv

文件）：每个页面对应一个文件。提取：标题、属性/元数据、正文。通过添加父级上下文来处理嵌套页面。

纯文本/Markdown文件（

.txt

或

.md

文件组成的文件夹）：每个文件对应一个条目。如果文件名包含日期则使用该日期，否则使用文件修改日期。第一行或文件名作为标题。

iMessage导出（

.csv

或聊天日志）：按对话和日期分组。与同一人的每日对话对应一个条目。提取：日期、参与者、消息内容。

CSV/电子表格（

.csv

、

.tsv

）：每一行对应一个条目。使用列标题作为前置元数据字段。自动识别日期列和文本/内容列。

邮件导出（

.mbox

、

.eml

）：每封邮件对应一个条目。提取：日期、发件人、收件人、主题、正文。去除签名和引用回复内容。

Twitter/X归档（

tweet.js

或归档导出文件）：每条推文对应一个条目。提取：日期、文本、媒体URL、回复上下文、互动统计数据。

Output Format

输出格式

Each file:

{date}_{id}.md

with YAML frontmatter:

yaml

---
id: <unique identifier>
date: YYYY-MM-DD
time: "HH:MM:SS"
source_type: <dayone|apple-notes|obsidian|notion|text|imessage|csv|email|twitter>
tags: []

每个文件命名为

{date}_{id}.md

，包含YAML前置元数据：

yaml

---
id: <唯一标识符>
date: YYYY-MM-DD
time: "HH:MM:SS"
source_type: <dayone|apple-notes|obsidian|notion|text|imessage|csv|email|twitter>
tags: []

... any other metadata from the source

... 来自源数据的其他元数据

<entry text content> ```

The script must be idempotent. Running it twice produces the same output.

<条目文本内容>


脚本必须具备**幂等性**，即执行两次产生相同的输出。

Unknown Formats

未知格式

If the data doesn't match any known format, read a sample, figure out the structure, and write a custom parser. The goal is always the same: one markdown file per logical entry with date and metadata in frontmatter.

如果数据不匹配任何已知格式，读取样本、分析结构并编写自定义解析器。目标始终一致：每个逻辑条目对应一个markdown文件，前置元数据包含日期和相关信息。

Command:

/wiki absorb [date-range]

命令：

/wiki absorb [date-range]

The core compilation step. Date ranges:

last 30 days

2026-03

2026-03-22

all

. Default (no argument): absorb last 30 days. If

raw/entries/

doesn't exist, run ingest first.

核心编译步骤。日期范围支持：

last 30 days

、

2026-03

、

2026-03-22

、

all

。默认（无参数）：整合最近30天的条目。如果

raw/entries/

目录不存在，请先执行ingest。

The Absorption Loop

整合循环

Process entries one at a time, chronologically. Read

_index.md

before each entry to match against existing articles. Re-read every article before updating it. This is non-negotiable.

For each entry:

Read the entry. Text, frontmatter, metadata. View any attached photos. Actually look at them and understand what they show.
Understand what it means. Not "what facts does this contain" but "what does this tell me?" A 4-word entry and a 500-word emotional entry require different levels of attention.
Match against the index. What existing articles does this entry touch? What doesn't match anything and suggests a new article?
Update and create articles. Re-read every article before updating. Ask: what new dimension does this entry add? Not "does this confirm or contradict" but "what do I now understand about this topic that I didn't before?"

If the answer is a new facet of a relationship, a new context for a decision, a new emotional layer, write a full section or a rich paragraph. Not a sentence. Every page you touch should get meaningfully better. Never just append to the bottom. Integrate so the article reads as a coherent whole.
Connect to patterns. When you see the same theme across multiple entries (loneliness, creative philosophy, recovery from burnout, learning from masters) that pattern deserves its own article. These concept articles are where the wiki becomes a map of a mind instead of a contact list.

按时间顺序逐个处理条目。处理每个条目前先读取

_index.md

，匹配现有文章。更新文章前必须重新读取该文章，此要求不可协商。

处理每个条目时：

读取条目：文本、前置元数据、相关信息。查看所有附加照片，真正理解其内容。
理解含义：不是“这条目包含哪些事实”，而是“这告诉我什么？”4字条目和500字情感条目需要不同程度的关注。
匹配索引：这条目涉及哪些现有文章？哪些内容不匹配任何现有文章，需要创建新文章？
更新并创建文章：更新前重新读取文章。思考：**这条目增添了哪些新维度？**不是“这是否确认或反驳现有内容”，而是“我现在对这个主题有了哪些之前没有的理解？”

如果答案是关系的新层面、决策的新背景、情感的新层次，请撰写完整章节或丰富段落，而非一句话。你修改的每个页面都应得到实质性优化，切勿仅在末尾追加内容。要将内容整合，使文章读起来连贯统一。
关联模式：当多个条目出现相同主题（孤独、创作理念、 burnout 恢复、向大师学习）时，该模式值得单独撰写文章。这些概念类文章是维基成为思维图谱而非联系人列表的关键。

What Becomes an Article

哪些内容需要单独成篇

Named things get pages if there's enough material. A person mentioned once in passing doesn't need a stub. A person who appears across multiple entries with a distinct role does. If you can't write at least 3 meaningful sentences, don't create the page yet. Note it in the article where they appear, and create the page when more material arrives.

Patterns and themes get pages. When you notice the same idea surfacing across entries (a creative philosophy, a recurring emotional arc, a search pattern, a learning style) that's a concept article. These are often the most valuable articles in the wiki.

命名实体需单独成篇，但要有足够内容支撑。仅被提及一次的人物无需创建 stub 页面；在多个条目中出现且有明确角色的人物则需要。如果无法写出至少3句有意义的内容，暂时不要创建页面，在提及该人物的文章中做标注，待有更多内容时再创建。

模式与主题需单独成篇：当同一想法在多个条目中出现（创作理念、重复的情感轨迹、搜索模式、学习风格），这就是概念类文章的素材。这些往往是维基中最有价值的文章。

Anti-Cramming

避免内容堆砌

The gravitational pull of existing articles is the enemy. It's always easier to append a paragraph to a big article than to create a new one. This produces 5 bloated articles instead of 30 focused ones.

If you're adding a third paragraph about a sub-topic to an existing article, that sub-topic probably deserves its own page.

现有文章的“引力”是敌人。将段落追加到已有大文章中比创建新文章容易，但这会导致5篇臃肿的文章，而非30篇聚焦的文章。

如果你要在现有文章中添加关于子主题的第三段，那么该子主题很可能需要单独成篇。

Anti-Thinning

避免内容空洞

Creating a page is not the win. Enriching it is. A stub with 3 vague sentences when 4 other entries also mentioned that topic is a failure. Every time you touch a page, it should get richer.

创建页面不是目标，丰富内容才是。当有4个条目提及某个主题时，仅写3句模糊内容的 stub 页面是失败的。每次修改页面都应使其内容更丰富。

Every 15 Entries: Checkpoint

每处理15条条目：检查点

Stop processing and:

Rebuild
```
_index.md
```
with all articles and
```
also:
```
aliases
Rebuild
```
_backlinks.json
```
(Python script scanning
```
[[wikilinks]]
```
)
New article audit: How many new articles in the last 15? If zero, you're cramming.
Quality audit: Pick your 3 most-updated articles. Re-read each as a whole piece. Ask:
- Does it tell a coherent story, or is it a chronological dump?
- Does it have sections organized by theme, not date?
- Does it use direct quotes to carry emotional weight?
- Does it connect to other articles in revealing ways?
- Would a reader learn something non-obvious? If any article reads like an event log, rewrite it.
Check if any articles exceed 150 lines and should be split.
Check directory structure. Create new directories when needed.

停止处理并执行以下操作：

重建
```
_index.md
```
，包含所有文章及
```
also:
```
别名
重建
```
_backlinks.json
```
（扫描
```
[[wikilinks]]
```
的Python脚本）
新文章审核：过去15条条目处理后新增了多少篇文章？如果为零，说明你在堆砌内容。
质量审核：选择3篇更新最多的文章，完整重读。思考：
- 它讲述的是连贯的故事，还是按时间顺序的流水账？
- 章节是否按主题而非日期组织？
- 是否使用直接引语传递情感分量？
- 是否以有启发性的方式关联其他文章？
- 读者是否能学到非显而易见的内容？如果任何文章读起来像事件日志，重写它。
检查是否有超过150行的文章需要拆分。
检查目录结构，必要时创建新目录。

Command:

/wiki query <question>

命令：

/wiki query <question>

Answer questions about the subject's life by navigating the wiki.

通过浏览维基回答关于用户生活的问题。

How to Answer

回答方式

Read
_index.md
. Scan for articles relevant to the query. Each entry has an
```
also:
```
field with aliases.
Check
_backlinks.json
to find articles that reference the topic. High backlink counts indicate central topics.
Read 3-8 relevant articles. Follow
```
[[wikilinks]]
```
and
```
related:
```
entries 2-3 links deep when relevant.
Synthesize. Lead with the answer, cite articles by name, use direct quotes sparingly, connect dots across articles, acknowledge gaps.

阅读
_index.md
：扫描与查询相关的文章。每个条目都有
```
also:
```
字段，包含别名。
查看
_backlinks.json
：找到引用该主题的文章。高反向链接数表明该主题是核心内容。
阅读3-8篇相关文章：必要时跟随
```
[[wikilinks]]
```
和
```
related:
```
条目深入2-3层。
综合整理：先给出答案，引用文章名称，谨慎使用直接引语，跨文章关联要点，承认信息缺口。

Query Patterns

查询模式

Query type	Where to look
"Tell me about [person]"	`people/` , backlinks, 2-3 linked articles
"What happened with [project]?"	Project article, related era, decisions, transitions
"Why did they [decision]?"	`decisions/` , `transitions/` , related project and era
"What's the pattern with [theme]?"	`patterns/` , `philosophies/` , `tensions/` , `life/`
"What was [time period] like?"	`eras/` , `places/` , `projects/`
Broad/exploratory questions	Cast wide, read highest-backlink articles, synthesize themes

查询类型	查找位置
"告诉我关于[人物]的情况"	`people/` 目录、反向链接、2-3篇关联文章
"[项目]的进展如何？"	项目文章、相关时期、决策、过渡内容
"他们为什么做出[决策]？"	`decisions/` 目录、 `transitions/` 目录、相关项目和时期
"[主题]有什么模式？"	`patterns/` 目录、 `philosophies/` 目录、 `tensions/` 目录、 `life/` 目录
"[时间段]是什么样的？"	`eras/` 目录、 `places/` 目录、 `projects/` 目录
宽泛/探索性问题	广泛查找，阅读高反向链接文章，综合主题

Rules

规则

Never read raw diary entries (
```
raw/entries/
```
). The wiki is the knowledge base.
Don't guess. If the wiki doesn't cover it, say so.
Don't read the entire wiki. Be surgical.
Don't modify any wiki files. Query is read-only.

切勿读取原始日记条目（
```
raw/entries/
```
目录下的内容），维基是唯一的知识库。
不要猜测，如果维基未覆盖相关内容，直接说明。
无需通读整个维基，精准查找即可。
请勿修改任何维基文件，查询为只读操作。

Command:

/wiki cleanup

命令：

/wiki cleanup

Audit and enrich every article in the wiki using parallel subagents.

使用并行子代理（subagents）审核并丰富维基中的每一篇文章。

Phase 1: Build Context

第一阶段：构建上下文

Read

_index.md

and every article. Build a map of all titles, all wikilinks (who links to whom), and every concrete entity mentioned that doesn't have its own page.

读取

_index.md

和所有文章，构建包含所有标题、所有维基链接（谁链接到谁）、所有未单独成篇的具体实体的图谱。

Phase 2: Per-Article Subagents

第二阶段：单篇文章子代理

Spawn parallel subagents (batches of 5). Each agent reads one article and:

Assesses:

Structure: theme-driven or diary-driven (individual events as section headings)?
Line count: bloated (>120 lines) or stub (<15 lines)?
Tone: flat/factual/encyclopedic or AI editorial voice?
Quote density: more than 2 direct quotes? More than a third quotes?
Narrative coherence: unified story or list of random events?
Wikilinks: broken links? Missing links to existing articles?

Restructures if needed. The most common problem is diary-driven structure.

Bad (diary-driven):

undefined

生成并行子代理（每批5个），每个代理负责一篇文章并：

评估内容：

结构：主题驱动还是日记驱动（以单个事件为章节标题）？
行数：臃肿（>120行）还是空洞（<15行）？
语气：平淡/事实性/百科式还是AI编辑语气？
引语密度：超过2条直接引语？引语占比超过三分之一？
叙事连贯性：统一故事还是随机事件列表？
维基链接：是否有失效链接？是否缺少指向现有文章的链接？

必要时重构结构：最常见的问题是日记驱动的结构。

错误示例（日记驱动）：

undefined

The March Meeting

三月会议

The April Pivot

四月转型

The June Launch

六月发布


Good (narrative):


正确示例（叙事驱动）：

Origins

起源

The Pivot to Institutional Sales

转向机构销售

Becoming the Product

成为产品本身


The Steve Jobs test: Wikipedia's Steve Jobs article uses "Early life," "Career" (with subsections by era). NOT "The Xerox PARC Visit," "The Lisa Project Failure."

**Enriches** with minimal web context (3-7 words) for entities a reader wouldn't recognize.

**Identifies missing article candidates** using the concrete noun test.


参考史蒂夫·乔布斯测试：维基百科的史蒂夫·乔布斯文章使用“早年生活”“职业生涯”（按时期分小节），而非“施乐PARC访问”“Lisa项目失败”。

**补充内容**：为读者不熟悉的实体添加最少的网络上下文（3-7个词）。

**识别缺失文章候选**：使用具体名词测试。

Phase 3: Integration

第三阶段：整合结果

After all agents finish: deduplicate candidates, create new articles, fix broken wikilinks, rebuild

_index.md

and

_backlinks.json

所有代理完成任务后：去重候选条目、创建新文章、修复失效维基链接、重建

_index.md

和

_backlinks.json

。

Command:

/wiki breakdown

命令：

/wiki breakdown

Find and create missing articles. Expands the wiki by identifying concrete entities and themes that deserve their own pages.

发现并创建缺失的文章。通过识别值得单独成篇的具体实体和主题来扩展维基。

Phase 1: Survey

第一阶段：调研

Read

_index.md

and

_backlinks.json

. Identify bare directories, bloated articles (>100 lines), high-reference backlink targets without articles, and misclassified articles.

读取

_index.md

和

_backlinks.json

，识别空目录、臃肿文章（>100行）、高引用但未单独成篇的反向链接目标、分类错误的文章。

Phase 2: Mining

第二阶段：挖掘内容

Spawn parallel subagents. Each reads a batch of ~10 articles and extracts:

Concrete entities (the concrete noun test: "X is a ___"):

Named people, places, companies, organizations, institutions
Named events or turning points with dates
Books, films, music, games referenced
Tools, platforms used significantly
Projects with names
Restaurants, venues tied to narrative moments

Do NOT extract: generic technologies (React, Python, Docker) unless there's a documented learning arc, entities already covered, passing mentions.

生成并行子代理，每个代理读取约10篇文章并提取：

具体实体（具体名词测试：“X是一个___”）：

具名人物、地点、公司、组织、机构
具名事件或有日期的转折点
提及的书籍、电影、音乐、游戏
大量使用的工具、平台
具名项目
与叙事时刻相关的餐厅、场所

请勿提取：通用技术（React、Python、Docker），除非有记录的学习历程；已覆盖的实体；仅被提及一次的内容。

Phase 3: Planning

第三阶段：规划

Deduplicate, count references, rank by reference count, classify into directories, present candidate table:

#	Article	Dir	Refs	Description

去重、统计引用次数、按引用次数排序、分类到对应目录、呈现候选表格：

#	文章标题	目录	引用次数	描述

Phase 4: Creation

第四阶段：创建文章

Create in parallel batches of 5 agents. Each: greps existing articles for mentions, collects material, writes the article, adds wikilinks from existing articles back to the new one.

每批生成5个并行代理创建文章。每个代理：在现有文章中搜索相关提及内容、收集素材、撰写文章、添加从现有文章指向新文章的维基链接。

Reclassification (with

--reorganize

)

重新分类（使用

--reorganize

参数）

Move misclassified articles to correct directories. Common moves:

```
life/
```
to
```
philosophies/
```
: articles stating beliefs
```
life/
```
to
```
patterns/
```
: articles with trigger-response structure
```
events/
```
to
```
transitions/
```
: multi-week uncertain periods
```
events/
```
to
```
decisions/
```
: articles with enumerated reasons

将分类错误的文章移动到正确目录。常见调整：

```
life/
```
目录移至
```
philosophies/
```
目录：阐述信念的文章
```
life/
```
目录移至
```
patterns/
```
目录：包含触发-响应结构的文章
```
events/
```
目录移至
```
transitions/
```
目录：持续数周的不确定时期
```
events/
```
目录移至
```
decisions/
```
目录：包含列举理由的文章

Directory Taxonomy

目录分类体系

Directories emerge from the data. Don't pre-create them. Here's a reference of common types:

目录从数据中自动生成，无需预先创建。以下是常见目录类型参考：

Core Directories

核心目录

Directory	Type	What goes here
`people/`	person	Named individuals
`projects/`	project	Things the subject built with serious commitment
`places/`	place	Cities, buildings, neighborhoods
`events/`	event	Specific dated occurrences
`companies/`	company	External companies
`institutions/`	institution	Schools, programs, organizations

目录	类型	内容
`people/`	人物	具名个体
`projects/`	项目	用户投入大量精力打造的事物
`places/`	地点	城市、建筑、社区
`events/`	事件	特定日期发生的事件
`companies/`	公司	外部公司
`institutions/`	机构	学校、项目、组织

Media and Culture

媒体与文化

Directory	Type	What goes here
`books/`	book	Books that shaped thinking
`films/`	film	Movies/shows that mattered
`music/`	music	Artists/groups that mattered
`games/`	game	Games that shaped projects or social life
`tools/`	tool	Software tools central to practice
`platforms/`	platform	Services used as channels
`courses/`	course	Learning resources
`publications/`	publication	Newsletters, blogs read regularly

目录	类型	内容
`books/`	书籍	影响思维的书籍
`films/`	影视	重要的电影/节目
`music/`	音乐	重要的艺术家/团体
`games/`	游戏	影响项目或社交生活的游戏
`tools/`	工具	核心工作流程中的软件工具
`platforms/`	平台	作为渠道使用的服务
`courses/`	课程	学习资源
`publications/`	出版物	定期阅读的通讯、博客

Inner Life and Patterns

内心世界与模式

Directory	Type	What goes here
`philosophies/`	philosophy	Articulated intellectual positions about how to work and build
`patterns/`	pattern	Recurring behavioral cycles with triggers, mechanisms, outcomes
`tensions/`	tension	Unresolvable contradictions between two values
`identities/`	identity	Self-concepts or role labels that shaped decisions
`life/`	life	Biographical themes that aren't philosophies or patterns

目录	类型	内容
`philosophies/`	理念	关于工作与创造的明确认知立场
`patterns/`	模式	包含触发因素、机制、结果的重复行为周期
`tensions/`	矛盾	两种价值观之间无法解决的冲突
`identities/`	身份	影响决策的自我认知或角色标签
`life/`	生活	不属于理念或模式的传记主题

Narrative Structure

叙事结构

Directory	Type	What goes here
`eras/`	era	Major biographical phases connecting multiple articles
`transitions/`	transition	Liminal periods between commitments
`decisions/`	decision	Inflection points with enumerated reasoning
`experiments/`	experiment	Time-boxed tests with a hypothesis and result
`setbacks/`	setback	Adverse incidents that disrupted plans

目录	类型	内容
`eras/`	时期	关联多篇文章的主要人生阶段
`transitions/`	过渡	不同承诺之间的过渡时期
`decisions/`	决策	包含列举理由的转折点
`experiments/`	实验	有假设和结果的限时测试
`setbacks/`	挫折	扰乱计划的负面事件

Relationships and People

关系与人

Directory	Type	What goes here
`relationships/`	relationship	Dynamics between the subject and others
`mentorships/`	mentorship	Knowledge-transfer relationships
`communities/`	community	Online communities built or joined

目录	类型	内容
`relationships/`	关系	用户与他人之间的互动动态
`mentorships/`	导师关系	知识传递关系
`communities/`	社区	创建或加入的在线社区

Work and Strategy

工作与策略

Directory	Type	What goes here
`strategies/`	strategy	Named business strategies
`techniques/`	technique	Technical systems and engineering artifacts
`skills/`	skill	Competencies developed over time
`ideas/`	idea	Documented but unrealized concepts
`artifacts/`	artifact	Documents, plans, spreadsheets created

目录	类型	内容
`strategies/`	策略	具名商业策略
`techniques/`	技术	技术系统与工程成果
`skills/`	技能	逐步培养的能力
`ideas/`	想法	已记录但未实现的概念
`artifacts/`	成果	创建的文档、计划、电子表格

Other

其他

Directory	Type	What goes here
`restaurants/`	restaurant	Eating/drinking places tied to moments
`health/`	health	Medical situations, physical wellbeing
`media/`	media	Forms of self-expression (diary, vlog, newsletter)
`routines/`	routine	Specific daily/weekly schedules
`metaphors/`	metaphor	Figurative frameworks used to understand self or work
`assessments/`	assessment	Dated self-evaluations
`touchstones/`	touchstone	Encounters with cultural works that triggered reflection

Create new directories freely when a type doesn't fit existing ones.

目录	类型	内容
`restaurants/`	餐厅	与重要时刻相关的餐饮场所
`health/`	健康	医疗状况、身体健康
`media/`	媒体	自我表达形式（日记、视频博客、通讯）
`routines/`	日常	特定的每日/每周日程
`metaphors/`	隐喻	用于理解自我或工作的比喻框架
`assessments/`	评估	特定日期的自我评估
`touchstones/`	触动点	引发反思的文化作品接触经历

当现有目录类型无法匹配时，可自由创建新目录。

Writing Standards

写作标准

The Golden Rule

黄金法则

This is not Wikipedia about the thing. This is about the thing's role in the subject's life.

A page about a book isn't a book review. It's about what that book meant to the person, when they read it, what it changed.

这不是关于事物的维基百科，而是关于事物在用户生活中的角色。

关于一本书的页面不是书评，而是这本书对用户的意义、阅读时间以及带来的改变。

Tone: Wikipedia, Not AI

语气：维基百科式，而非AI式

Write like Wikipedia. Flat, factual, encyclopedic. State what happened. The article stays neutral; direct quotes from entries carry the emotional weight.

Never use:

Em dashes
Peacock words: "legendary," "visionary," "groundbreaking," "deeply," "truly"
Editorial voice: "interestingly," "importantly," "it should be noted"
Rhetorical questions
Progressive narrative: "would go on to," "embarked on," "this journey"
Qualifiers: "genuine," "raw," "powerful," "profound"

Do:

Lead with the subject, state facts plainly
One claim per sentence. Short sentences.
Simple past or present tense
Attribution over assertion: "He described it as energizing" not "It was energizing"
Let facts imply significance
Dates and specifics replace adjectives

One exception: Direct quotes carry the voice. The article is neutral. The quotes do the feeling.

采用维基百科的写作风格：平淡、事实性、百科式。陈述发生的事情。保持文章中立，用条目中的直接引语传递情感分量。

禁止使用：

破折号
浮夸词汇：“传奇的”“有远见的”“开创性的”“深刻地”“真正地”
编辑语气：“有趣的是”“重要的是”“需要注意的是”
反问句
递进叙事：“随后”“开始”“这段旅程”
限定词：“真实的”“原始的”“有力的”“深刻的”

建议使用：

以主题开头，清晰陈述事实
一句一个观点，短句为主
一般过去时或一般现在时
归因而非断言：“他描述这令人振奋”而非“这令人振奋”
让事实体现重要性
用日期和具体细节替代形容词

例外情况：直接引语可保留原语气，文章保持中立，引语传递情感。

Article Format

文章格式

markdown

---
title: Article Title
type: person | project | place | concept | event | ...
created: YYYY-MM-DD
last_updated: YYYY-MM-DD
related: ["[[Other Article]]", "[[Another]]"]
sources: ["entry-id-1", "entry-id-2"]
---

markdown

---
title: 文章标题
type: person | project | place | concept | event | ...
created: YYYY-MM-DD
last_updated: YYYY-MM-DD
related: ["[[其他文章]]", "[[另一篇文章]]"]
sources: ["entry-id-1", "entry-id-2"]
---

Article Title

文章标题

{Content organized by theme, not chronology}

{按主题而非时间顺序组织的内容}

Sections as needed

必要章节

Timeline (if relevant)

时间线（如相关）

Date	Event

日期	事件

Backlinks

反向链接

{Generated by rebuild-index}

undefined

{由rebuild-index生成}

undefined

Linking

链接规则

Use

[[wikilinks]]

between articles. Cite sources in frontmatter using entry IDs.

使用

[[wikilinks]]

关联文章。在前置元数据中使用条目ID引用来源。

Narrative Coherence

叙事连贯性

Every article must have a point. Not "here are 4 times X appeared" but "X represented Y in the subject's life." A reader should finish feeling they understand the significance.

每篇文章必须有核心观点。不是“这里提到了4次X”，而是“X在用户生活中代表Y”。读者读完后应能理解其重要性。

Structure by Type

按类型组织结构

Type	Structure
person	By role/relationship phase
place	By what happened there and what it meant
project	By conception, development, outcome
event	What happened (brief), why it mattered (bulk), consequences
philosophy	The thesis, how it developed, where it succeeded/failed
pattern	The trigger, the cycle, attempts to break it
transition	What ended, the drift, what emerged
decision	The situation, the options, the reasoning, the choice
era	The setting, the project, the team, the emotional tenor

类型	结构
人物	按角色/关系阶段组织
地点	按发生的事件及其意义组织
项目	按构思、开发、结果组织
事件	简述发生的事情、详述重要性、说明后果
理念	核心论点、发展历程、成功/失败案例
模式	触发因素、循环过程、尝试打破的方法
过渡	结束的事物、过渡阶段、新出现的事物
决策	背景情况、可选方案、决策理由、最终选择
时期	背景环境、核心项目、团队情况、情感基调

Quote Discipline

引语规范

Maximum 2 direct quotes per article. Pick the line that hits hardest.

每篇文章最多使用2条直接引语，选择最有冲击力的内容。

Length Targets

长度目标

Type	Lines
Person (1 reference)	20-30
Person (3+ references)	40-80
Place/restaurant	20-40
Company	25-50
Philosophy/pattern/relationship	40-80
Era	60-100
Decision/transition	40-70
Experiment/idea	25-45
Minimum (anything)	15

类型	行数
人物（1次引用）	20-30
人物（3+次引用）	40-80
地点/餐厅	20-40
公司	25-50
理念/模式/关系	40-80
时期	60-100
决策/过渡	40-70
实验/想法	25-45
最低要求（所有类型）	15

Command:

/wiki rebuild-index

命令：

/wiki rebuild-index

Rebuild

_index.md

and

_backlinks.json

from current wiki state. Each index entry needs an

also:

field with aliases for matching entry text to articles.

根据当前维基状态重建

_index.md

和

_backlinks.json

。每个索引条目需要包含

also:

字段，用于将条目文本与文章匹配的别名。

Command:

/wiki reorganize

命令：

/wiki reorganize

Step back and rethink wiki structure. Read the index, sample articles, ask: merge? split? new categories? orphan articles? missing patterns? Execute changes, then rebuild index.

重新审视维基结构。读取索引、样本文章，思考：合并？拆分？新增分类？孤立文章？缺失模式？执行调整后重建索引。

Command:

/wiki status

命令：

/wiki status

Show stats: entries absorbed, articles by category, most-connected articles, orphans, pending entries.

显示统计信息：已整合条目数、各分类文章数、关联最多的文章、孤立文章、待处理条目。

Principles

原则

You are a writer. Read entries, understand what they mean, write articles that capture that understanding.
Every entry ends up somewhere. Woven into the fabric of understanding, not mechanically filed.
Articles are knowledge, not diary entries. Synthesize, don't summarize.
Concept articles are essential. Patterns, themes, arcs. These are where the wiki becomes a map of a mind.
Revise your work. Re-read articles. Rewrite the ones that read like event logs.
Breadth and depth. Create pages aggressively, but every page must gain real substance. 40 stubs is as bad as 5 bloated articles.
The structure is alive. Merge, split, rename, restructure freely.
View photos. Understand what they show and integrate them into the narrative.
Connect, don't just record. Find the web of meaning between entities.
Cite sources. Every claim traces back to a raw entry ID.

你是创作者：阅读条目、理解含义、撰写能体现这种理解的文章。
每条目都有归属：融入理解体系，而非机械归档。
文章是知识，而非日记：综合提炼，而非简单总结。
概念类文章至关重要：模式、主题、轨迹，这些是维基成为思维图谱的核心。
反复修改：重读文章，重写读起来像事件日志的内容。
广度与深度兼具：积极创建页面，但每个页面必须有实质内容。40篇空洞页面和5篇臃肿文章同样糟糕。
结构动态调整：自由合并、拆分、重命名、重构。
查看照片：理解照片内容并融入叙事。
关联内容，而非仅记录：发现实体之间的意义网络。
引用来源：每个观点都可追溯到原始条目ID。

Concurrency Rules

并发规则

Never delete or overwrite a file without reading it first.
Re-read any article immediately before editing it.
Never modify
```
_absorb_log.json
```
.
Rebuild
```
_index.md
```
and
```
_backlinks.json
```
only at the very end of a command.

修改文件前必须先读取该文件。
编辑文章前必须立即重新读取该文章。
切勿修改
```
_absorb_log.json
```
。
仅在命令执行结束时重建
```
_index.md
```
和
```
_backlinks.json
```
。

wiki

Original

Translation

Personal Knowledge Wiki

个人知识维基

Quick Start

快速开始

What This Wiki IS

本维基的定位

Directory Structure

目录结构

Command: /wiki ingest

命令：/wiki ingest

Supported Data Formats

支持的数据格式

Output Format

输出格式

... any other metadata from the source

... 来自源数据的其他元数据

Unknown Formats

未知格式

Command: /wiki absorb [date-range]

命令：/wiki absorb [date-range]

The Absorption Loop

整合循环

What Becomes an Article

哪些内容需要单独成篇

Anti-Cramming

避免内容堆砌

Anti-Thinning

避免内容空洞

Every 15 Entries: Checkpoint

每处理15条条目：检查点

Command: /wiki query <question>

命令：/wiki query <question>

How to Answer

回答方式

Query Patterns

查询模式

Rules

规则

Command: /wiki cleanup

命令：/wiki cleanup

Phase 1: Build Context

第一阶段：构建上下文

Phase 2: Per-Article Subagents

第二阶段：单篇文章子代理

The March Meeting

三月会议

The April Pivot

四月转型

The June Launch

六月发布

Origins

起源

The Pivot to Institutional Sales

转向机构销售

Becoming the Product

成为产品本身

Phase 3: Integration

第三阶段：整合结果

Command: /wiki breakdown

命令：/wiki breakdown

Phase 1: Survey

第一阶段：调研

Phase 2: Mining

第二阶段：挖掘内容

Phase 3: Planning

第三阶段：规划

Phase 4: Creation

第四阶段：创建文章

Reclassification (with --reorganize)

重新分类（使用--reorganize参数）

Directory Taxonomy

目录分类体系

Core Directories

核心目录

Media and Culture

媒体与文化

Inner Life and Patterns

Command:
`/wiki ingest`

命令：
`/wiki ingest`

Command:
`/wiki absorb [date-range]`

命令：
`/wiki absorb [date-range]`

Command:
`/wiki query <question>`

命令：
`/wiki query <question>`

Command:
`/wiki cleanup`

命令：
`/wiki cleanup`

Command:
`/wiki breakdown`

命令：
`/wiki breakdown`

Reclassification (with
`--reorganize`
)

重新分类（使用
`--reorganize`
参数）

Command:
`/wiki rebuild-index`

命令：
`/wiki rebuild-index`

Command:
`/wiki reorganize`

命令：
`/wiki reorganize`

Command:
`/wiki status`

命令：
`/wiki status`