wiki-capture

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Wiki Capture — Conversation to Wiki Note

Wiki Capture — 对话转Wiki笔记

You are preserving knowledge from the current conversation as a permanent wiki note. The goal is to extract the substance — the knowledge itself — not a summary of what was said.

你需要将当前对话中的知识留存为永久的Wiki笔记。目标是提取核心内容——知识本身，而非对话内容的摘要。

Before You Start

开始之前

Read

~/.obsidian-wiki/config

(preferred) or

.env

(fallback) to get

OBSIDIAN_VAULT_PATH

Read
```
$OBSIDIAN_VAULT_PATH/index.md
```
to understand existing wiki content (avoid duplicates)
Read
```
$OBSIDIAN_VAULT_PATH/hot.md
```
if it exists — it gives context on recent activity

读取

~/.obsidian-wiki/config

（优先）或

.env

（备选）以获取

OBSIDIAN_VAULT_PATH

读取
```
$OBSIDIAN_VAULT_PATH/index.md
```
以了解现有Wiki内容（避免重复）
若
```
$OBSIDIAN_VAULT_PATH/hot.md
```
存在，读取该文件——它提供近期活动的上下文

Step 1: Identify What's Worth Preserving

步骤1：确定值得留存的内容

Scan the conversation. Ask: what knowledge emerged here that would be valuable in 3 months with no memory of this chat?

Worth preserving:

Decisions made and why they were made
Analysis, frameworks, mental models developed
Technical findings, patterns, or procedures
Synthesized understanding of a topic
Clear explanations of a concept that took effort to arrive at
Key facts from an external source discussed in the conversation

Skip:

Logistics, scheduling, pleasantries
Exploratory back-and-forth where no conclusion was reached
Content that's already in the wiki

If nothing material emerged, tell the user and stop.

扫描对话内容，思考：这段对话中产生的哪些知识，在3个月后忘记本次聊天的情况下仍有价值？

值得留存的内容：

已做出的决策及其原因
形成的分析、框架、思维模型
技术发现、模式或流程
对某一主题的综合理解
经过努力得出的对某一概念的清晰解释
对话中讨论的外部来源的关键事实

无需留存的内容：

后勤安排、日程调度、寒暄语
未得出结论的探索性来回讨论
已存在于Wiki中的内容

若未产生有价值的内容，告知用户并停止操作。

Step 2: Classify the Content Type

步骤2：分类内容类型

Assign one of five types — this determines the target folder and tone:

Type	Description	Target folder
`synthesis`	Multi-step analysis or an answer to a specific question that required reasoning	`synthesis/`
`concept`	A definition, framework, or mental model (what a thing is)	`concepts/`
`source`	Summary of an external document, article, or resource discussed	`references/`
`decision`	A strategic, architectural, or design choice and its rationale	`synthesis/`
`session`	A complete discussion summary when the conversation spans multiple topics	`journal/`

If the content clearly belongs to a specific project (detected from context or user mention), place it under

projects/<project-name>/<category>/

instead.

为内容分配以下五种类型之一——这将决定目标文件夹和语气：

类型	描述	目标文件夹
`synthesis`	多步骤分析或需要推理的特定问题的答案	`synthesis/`
`concept`	定义、框架或思维模型（事物的本质）	`concepts/`
`source`	对话中讨论的外部文档、文章或资源的摘要	`references/`
`decision`	战略、架构或设计选择及其理由	`synthesis/`
`session`	涵盖多个主题的完整讨论摘要	`journal/`

若内容明确属于某个特定项目（从上下文或用户提及中识别），则将其放置在

projects/<project-name>/<category>/

路径下。

Step 3: Rewrite as Declarative Knowledge

步骤3：改写为陈述性知识

Do not write a summary of the conversation. Write the knowledge itself, in declarative present tense:

Not: "The user asked about X and Claude explained that..."
Yes: "X works by..."
Not: "We decided to use Y because..."
Yes: "Y is preferred over Z because [reason]. [^[inferred] if the rationale was implied, not stated explicitly]"

Apply provenance markers per

llm-wiki

Extracted — explicitly stated in the conversation (no marker)
Inferred — generalized or synthesized from the conversation →
```
^[inferred]
```
Ambiguous — disputed, uncertain, or contradictory →
```
^[ambiguous]
```

不要写对话摘要。直接写出知识本身，使用陈述性现在时态：

错误示例：“用户询问了X，Claude解释说……”
正确示例：“X的工作原理是……”
错误示例：“我们决定使用Y，因为……”
正确示例：“优先选择Y而非Z，原因是[理由]。^[inferred]（若理由是隐含而非明确陈述的）”

按照

llm-wiki

的规则添加来源标记：

提取 — 对话中明确陈述的内容（无需标记）
推断 — 从对话中归纳或综合得出的内容 →
```
^[inferred]
```
模糊 — 存在争议、不确定或矛盾的内容 →
```
^[ambiguous]
```

Step 4: Generate a Slug and Title

步骤4：生成Slug和标题

Derive a clear, descriptive title from the content. Slugify it:

Lowercase, words separated by hyphens
Max 50 characters
Avoid dates in the slug (the frontmatter has
```
created
```
)

从内容中提炼清晰、描述性的标题。将标题转换为slug格式：

小写，单词用连字符分隔
最多50个字符
slug中避免使用日期（frontmatter中有
```
created
```
字段）

Step 5: Write the Wiki Note

步骤5：撰写Wiki笔记

Create the file at the target path with required frontmatter:

yaml

---
title: >-
  <Title>
category: <synthesis|concepts|references|journal|skills>
tags: [<2-5 domain tags from taxonomy>]
sources:
  - conversation:<ISO-date>
created: <ISO-8601 timestamp>
updated: <ISO-8601 timestamp>
summary: >-
  <1-2 sentences, ≤200 chars, answering "what knowledge does this page hold?">
provenance:
  extracted: 0.X
  inferred: 0.X
  ambiguous: 0.X
---

Body structure by type:

synthesis / decision:

markdown

undefined

在目标路径创建文件，并包含必填的frontmatter：

yaml

---
title: >-
  <Title>
category: <synthesis|concepts|references|journal|skills>
tags: [<2-5 domain tags from taxonomy>]
sources:
  - conversation:<ISO-date>
created: <ISO-8601 timestamp>
updated: <ISO-8601 timestamp>
summary: >-
  <1-2句话，≤200字符，回答“此页面包含哪些知识？”>
provenance:
  extracted: 0.X
  inferred: 0.X
  ambiguous: 0.X
---

按类型划分的正文结构：

synthesis / decision:

markdown

undefined

Title

Context

背景

<促使内容产生的原因——要解决的问题或疑问>

Finding / Decision

结论 / 决策

<核心知识或结论>

Reasoning

推理过程

<为什么会得出此结论或做出此选择>

Implications

影响

<由此产生的结果——需要关注的事项、后续步骤、权衡因素>

Title

<用清晰的一句话定义概念。>

What It Is

定义

<对概念的解释>

How It Works

工作原理

<机制或结构>

When to Use

适用场景

<Applicability, conditions, trade-offs>

<适用性、条件、权衡因素>

Title

Source: <title or URL>

来源：<标题或URL>

What It Covers

内容概述

<该来源的主题>

Key Points

要点

<带有来源标记的要点列表>

Open Questions

未解决问题

<来源提出但未解答的问题——若无则省略>

Title

Session captured: <date>

对话记录时间：<date>

Topics Covered

讨论主题

<简要列表>

Key Takeaways

关键要点

<对话中产生的3-5个最重要的内容>

Decisions Made

已做出的决策

<明确的决策及其理由>

Open Questions

未解决问题

<仍未明确的事项>

Step 6: Update Tracking Files

步骤6：更新跟踪文件

index.md
— Add the new page under its category section.

log.md
— Append:

- [TIMESTAMP] CAPTURE type=<type> page="<path>" title="<title>"

hot.md
— Update Recent Activity with what was just captured. Update Key Takeaways if the note introduced something worth flagging. Update

updated

timestamp.

index.md
— 在对应的类别下添加新页面。

log.md
— 添加以下内容：

- [TIMESTAMP] CAPTURE type=<type> page="<path>" title="<title>"

hot.md
— 在“近期活动”部分更新刚刚记录的内容。若笔记引入了值得标记的内容，更新“关键要点”部分。更新

updated

时间戳。

Step 7: Confirm to User

步骤7：向用户确认

Report the saved path and title:

Saved to: projects/<name>/synthesis/<slug>.md
Title: <Title>
Type: synthesis

告知用户保存的路径和标题：

已保存至：projects/<name>/synthesis/<slug>.md
标题：<Title>
类型：synthesis

Quality Checklist

质量检查清单

Content rewritten as declarative knowledge (not a chat transcript)
Type classified correctly; target path is in the right folder
Frontmatter complete with title, category, tags, sources, summary, provenance
At least 2 wikilinks to existing pages
```
index.md
```
,
```
log.md
```
, and
```
hot.md
```
updated
Confirmed save path to user

内容已改写为陈述性知识（而非聊天记录）
类型分类正确；目标路径位于正确文件夹
Frontmatter完整，包含标题、类别、标签、来源、摘要、来源标记
至少包含2个指向现有页面的wikilinks
```
index.md
```
、
```
log.md
```
和
```
hot.md
```
已更新
已向用户确认保存路径

wiki-capture

Original

Translation

Wiki Capture — Conversation to Wiki Note

Wiki Capture — 对话转Wiki笔记

Before You Start

开始之前

Step 1: Identify What's Worth Preserving

步骤1：确定值得留存的内容

Step 2: Classify the Content Type

步骤2：分类内容类型

Step 3: Rewrite as Declarative Knowledge

步骤3：改写为陈述性知识

Step 4: Generate a Slug and Title

步骤4：生成Slug和标题

Step 5: Write the Wiki Note

步骤5：撰写Wiki笔记

Title

Title

Context

背景

Finding / Decision

结论 / 决策

Reasoning

推理过程

Implications

影响

Related

相关链接

Title

Title

What It Is

定义

How It Works

工作原理

When to Use

适用场景

Related

相关链接

Title

Title

What It Covers

内容概述

Key Points

要点

Open Questions

未解决问题

Related

相关链接

Title

Title

Topics Covered

讨论主题

Key Takeaways

关键要点

Decisions Made

已做出的决策

Open Questions

未解决问题

Related

相关链接

Step 6: Update Tracking Files

步骤6：更新跟踪文件

Step 7: Confirm to User

步骤7：向用户确认

Quality Checklist

质量检查清单