wiki-digest

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Wiki Digest — Knowledge Newsletter Generator

Wiki Digest — 知识通讯生成工具

You are generating a human-readable digest of recent wiki activity: what was learned, what was updated, what themes are emerging, and what's worth reviewing. This skill summarizes knowledge, not sources — think of it as a weekly review session, not an ingestion status report.

你需要生成一份可读性强的Wiki近期动态摘要，内容包括新增知识、更新内容、涌现的主题以及值得回顾的内容。该技能聚焦于知识内容的总结，而非数据源——可以将其视为每周复盘会议，而非摄入状态报告。

Before You Start

开始之前

Resolve config — follow the Config Resolution Protocol in
```
llm-wiki/SKILL.md
```
(walk up CWD for
```
.env
```
→
```
~/.obsidian-wiki/config
```
→ prompt setup). This gives
```
OBSIDIAN_VAULT_PATH
```
and
```
OBSIDIAN_LINK_FORMAT
```
.
Parse the period from the user's request:
- "daily" / "today" / "yesterday" → last 24 hours
- "weekly" / "this week" / no argument (default) → last 7 days
- "monthly" / "this month" → last 30 days
- ISO date like "since 2026-05-01" → pages updated since that date
- Explicit number like "last 14 days" → that many days
Read
```
$OBSIDIAN_VAULT_PATH/log.md
```
— last 200 lines — for entries within the period (timestamps are ISO-8601 prefixed lines).
Read
```
$OBSIDIAN_VAULT_PATH/hot.md
```
for current session context.
If
```
$OBSIDIAN_VAULT_PATH/_insights.md
```
exists, read its Anchor Pages table — you'll use it later to identify which new pages became hubs.

解析配置 — 遵循
```
llm-wiki/SKILL.md
```
中的配置解析协议（依次从当前工作目录的
```
.env
```
→
```
~/.obsidian-wiki/config
```
→ 提示设置中查找）。这将获取
```
OBSIDIAN_VAULT_PATH
```
和
```
OBSIDIAN_LINK_FORMAT
```
。
解析用户请求中的时间段：
- "daily" / "today" / "yesterday" → 过去24小时
- "weekly" / "this week" / 无参数（默认） → 过去7天
- "monthly" / "this month" → 过去30天
- ISO格式日期如"since 2026-05-01" → 该日期之后更新的页面
- 明确数字如"last 14 days" → 指定天数
读取
```
$OBSIDIAN_VAULT_PATH/log.md
```
的最后200行，提取时间段内的条目（时间戳为ISO-8601格式开头的行）。
读取
```
$OBSIDIAN_VAULT_PATH/hot.md
```
获取当前会话上下文。
如果
```
$OBSIDIAN_VAULT_PATH/_insights.md
```
存在，读取其锚点页面表格——后续将用于识别哪些新页面成为了核心枢纽。

Step 1: Collect Pages Active in the Period

步骤1：收集时间段内活跃的页面

Glob all

.md

files under

$OBSIDIAN_VAULT_PATH

. Skip special/system files:

index.md

log.md

hot.md

AGENTS.md

_insights.md

Anything under
```
_meta/
```
,
```
_archives/
```
,
```
_raw/
```
Journal digest pages themselves (
```
journal/digest-*.md
```
)

For each remaining page, read its frontmatter:

```
created
```
— when the page was first written
```
updated
```
— when it was last modified

Classify:

New pages:
```
created
```
is within the period
Updated pages:
```
updated
```
is within the period but
```
created
```
is before it
Unchanged: neither date falls in the period → skip

If fewer than 5 pages were active, note it and offer to widen: "Only 3 pages were active in the last 7 days — want a monthly digest instead?" Stop here unless the user says to continue.

For each active page, collect:

title

category

tags

summary

(frontmatter field),

lifecycle

, any

^[ambiguous]

^[inferred]

markers in the body.

遍历

$OBSIDIAN_VAULT_PATH

下所有

.md

文件，跳过特殊/系统文件：

index.md

log.md

hot.md

AGENTS.md

_insights.md

```
_meta/
```
,
```
_archives/
```
,
```
_raw/
```
目录下的所有文件
通讯摘要页面本身（
```
journal/digest-*.md
```
）

对剩余每个页面，读取其前置元数据：

```
created
```
— 页面首次创建时间
```
updated
```
— 页面最后修改时间

分类：

新页面：
```
created
```
时间在时间段内
更新页面：
```
updated
```
时间在时间段内，但
```
created
```
时间早于该时间段
未变更：两个时间均不在时间段内 → 跳过

如果活跃页面少于5个，需告知用户并建议扩大时间段："过去7天内仅3个页面有活动——是否需要生成月度摘要？" 除非用户确认继续，否则停止操作。

对每个活跃页面，收集以下信息：

title

category

tags

summary

（前置元数据字段）,

lifecycle

, 正文中所有

^[ambiguous]

或

^[inferred]

标记。

Step 2: Identify Themes

步骤2：识别主题

From all active pages' tags, tally theme frequency:

For each tag across new + updated pages:
  count how many active pages carry it
Sort descending, take top 5

Step 3: Find Notable New Connections

步骤3：发现重要的新关联

Scan new and updated pages for cross-category wikilinks — links that bridge different knowledge layers. These are the most intellectually interesting outputs of the period.

For each active page, extract all

[[wikilink]]

targets. Classify each link by the target's category prefix. Flag links that cross categories (e.g., a

concepts/

page linking to an

entities/

page, or a

synthesis/

page bridging two topics).

Rank candidates by interestingness:

+3 if the link is across two categories that rarely connect (use
```
_insights.md
```
bridge data if available)
+2 if the target page is a top-10 hub (per
```
_insights.md
```
anchors)
+2 if the link appears in a
```
synthesis/
```
page (deliberate cross-cutting)
+1 if the source page is marked
```
^[inferred]
```
(synthesized connection, not directly stated)

Take the top 3–5 connections. Write each as a plain-English sentence: not just "A → B" but why the connection is interesting.

扫描新页面和更新页面中的跨分类Wiki链接——这些链接连接了不同的知识层级，是本时间段内最具价值的智力产出。

对每个活跃页面，提取所有

[[wikilink]]

目标。根据目标页面的分类前缀对链接进行分类。标记跨分类的链接（例如，

concepts/

页面链接到

entities/

页面，或

synthesis/

页面连接两个不同主题）。

按关联性价值排序候选链接：

+3分：链接连接了两个极少关联的分类（如果有
```
_insights.md
```
中的桥接数据则使用该数据）
+2分：目标页面是前10个核心枢纽（根据
```
_insights.md
```
中的锚点页面）
+2分：链接出现在
```
synthesis/
```
页面中（刻意的跨领域连接）
+1分：源页面标记有
```
^[inferred]
```
（合成的关联，而非直接陈述）

选取前3-5个关联链接。用通俗易懂的句子描述每个链接：不仅要写"A → B"，还要说明该关联为何有价值。

Step 4: Surface Open Threads

步骤4：梳理未完成事项

Scan active pages and

_raw/

for unresolved work:

Drafts: pages with
```
lifecycle: draft
```
or
```
lifecycle: stub
```
Ambiguous claims: count
```
^[ambiguous]
```
markers across all active pages (don't list every one — just the count and which pages have the most)
Unstaged notes: count files in
```
$OBSIDIAN_VAULT_PATH/_raw/
```
(anything here hasn't been promoted)
Taxonomy gaps: tags from Step 2 that aren't in
```
_meta/taxonomy.md
```

扫描活跃页面和

_raw/

目录中的未完成工作：

草稿：标记
```
lifecycle: draft
```
或
```
lifecycle: stub
```
的页面
模糊声明：统计所有活跃页面中
```
^[ambiguous]
```
标记的数量（无需列出每个标记，只需统计总数及标记最多的页面）
未整理笔记：统计
```
$OBSIDIAN_VAULT_PATH/_raw/
```
目录中的文件数量（此处的文件尚未被整理入库）
分类体系缺口：步骤2中未出现在
```
_meta/taxonomy.md
```
中的标签

Step 5: Choose Recommended Re-reads

步骤5：推荐值得重读的页面

From the existing (pre-period) pages, identify 2–3 worth revisiting given this week's new context.

Heuristic: find pre-period pages that share the most tags with the active pages from Step 1. These are foundational pages whose topic was extended this period — the new pages build on them but the user may not have revisited the foundation.

Also include any pre-period page that now has 2+ new incoming links from active pages (it just became more connected — a sign it's load-bearing).

Write each recommendation with a concrete reason: "[[concepts/attention-mechanism]] — your foundational page; three new papers ingested this week all extend it", not just the page title.

从时间段之前已存在的页面中，找出2-3个结合本周新内容值得重读的页面。

判断规则：找出与步骤1中活跃页面共享标签最多的历史页面。这些是基础页面，本周的新内容基于它们扩展，但用户可能尚未回顾这些基础内容。

同时，包含任何新增2条以上来自活跃页面的入链的历史页面（这类页面的关联性增强，已成为核心支撑页面）。

为每个推荐页面提供具体理由："[[concepts/attention-mechanism]] — 你的基础页面；本周摄入的3篇新论文均基于该概念扩展"，而非仅提供页面标题。

Step 6: Generate the Digest

步骤6：生成摘要

Produce a structured, scannable markdown report. The Headlines section is the most important — it should feel like the opening of a good newsletter, synthesizing actual insight rather than listing page names.

Apply the link format from

llm-wiki/SKILL.md

(Link Format section) using

OBSIDIAN_LINK_FORMAT

. Default is

[[wikilink]]

markdown

undefined

生成结构化、易于浏览的Markdown报告。其中“头条”部分最为重要——应像优质通讯的开篇一样，提炼实际洞见，而非仅罗列页面名称。

使用

llm-wiki/SKILL.md

（链接格式部分）中指定的链接格式，结合

OBSIDIAN_LINK_FORMAT

。默认格式为

[[wikilink]]

。

markdown

undefined

Wiki Digest — [Period Label]

Wiki Digest — [时间段标签]

[N new pages · M updated pages · period: YYYY-MM-DD to YYYY-MM-DD]

[N个新页面 · M个更新页面 · 时间段：YYYY-MM-DD 至 YYYY-MM-DD]

Headlines

头条

[Concrete insight #1 — synthesize the actual knowledge, not just "learned about X"]
[Concrete insight #2]
[Concrete insight #3]

[具体洞见1 — 提炼实际知识，而非仅说“学习了X”]
[具体洞见2]
[具体洞见3]

New Knowledge

新增知识

New pages ([count])

新页面 ([数量])

Page	Category	Summary
[[concepts/foo]]	concept	One-sentence summary from frontmatter
[[entities/bar]]	entity	One-sentence summary

页面	分类	摘要
[[concepts/foo]]	concept	来自前置元数据的一句话摘要
[[entities/bar]]	entity	一句话摘要

Notable updates ([count])

重要更新 ([数量])

Page	What changed
[[skills/react-hooks]]	Added patterns for useCallback with async effects

(If no updates, omit this subsection.)

页面	更新内容
[[skills/react-hooks]]	添加了useCallback结合异步副作用的模式

(若无更新内容，省略此小节。)

Emerging Themes

涌现主题

#[tag] ([N pages]) — [One sentence on why this topic was active]
#[tag] ([N pages]) — [...]
#[NEW TAG] ([N pages]) ⭐ New vocabulary — not yet in taxonomy

Most active category: [category/] ([N pages added or updated])

#[tag] ([N个页面]) — [一句话说明该主题活跃的原因]
#[tag] ([N个页面]) — [...]
#[NEW TAG] ([N个页面]) ⭐ 新增词汇 — 尚未加入分类体系

最活跃分类：[category/] ([N个页面被新增或更新])

Key Connections Made

建立的核心关联

[[concepts/A]] → [[entities/B]] — [Plain-English reason this connection is interesting]
[[synthesis/X]] created — bridges [[concepts/Y]] and [[concepts/Z]] for the first time
(up to 5 connections)

[[concepts/A]] → [[entities/B]] — [通俗易懂的语言说明该关联为何有价值]
[[synthesis/X]] 已创建 — 首次连接[[concepts/Y]]和[[concepts/Z]]
(最多列出5个关联)

Open Threads

未完成事项

Drafts to compile ([count]): [[concepts/foo]], [[concepts/bar]] — still in draft lifecycle
Ambiguous claims: [N]
```
^[ambiguous]
```
markers across [M] pages — run
```
/wiki-synthesize
```
to resolve
Unstaged notes: [N] files in
```
_raw/
```
— run
```
/wiki-ingest _raw/
```
to promote them
Taxonomy gaps: Tags
```
#newtag1
```
,
```
#newtag2
```
used but not in taxonomy — run
```
/tag-taxonomy
```

(Omit any subsection where count is 0.)

待整理草稿 ([数量])：[[concepts/foo]]、[[concepts/bar]] — 仍处于草稿阶段
模糊声明：[N]个
```
^[ambiguous]
```
标记分布在[M]个页面中 — 运行
```
/wiki-synthesize
```
来解决
未整理笔记：[N]个文件在
```
_raw/
```
目录中 — 运行
```
/wiki-ingest _raw/
```
来整理入库
分类体系缺口：使用了标签
```
#newtag1
```
、
```
#newtag2
```
但未加入分类体系 — 运行
```
/tag-taxonomy
```

(若某小节数量为0，省略该小节。)

Recommended Re-reads

Step 7: Output & Optionally Save

步骤7：输出并可选保存

Default (chat output): Print the digest directly. At the end, ask: "Want me to save this as
journal/digest-YYYY-MM-DD.md
?"

If user prefixed with "save" or "write" (e.g.,

/wiki-digest save

or "generate and save my weekly digest"):

Write to

$OBSIDIAN_VAULT_PATH/journal/digest-YYYY-MM-DD.md

(weekly/monthly) or

journal/digest-YYYY-MM-DD-daily.md

(daily)

Add frontmatter:

yaml

---
title: "Wiki Digest — [Period Label]"
category: journal
tags: [digest, meta/review]
sources: []
created: TIMESTAMP
updated: TIMESTAMP
summary: "Weekly knowledge digest: [N new, M updated pages]. Top themes: [tag1], [tag2]."
---

Update
```
index.md
```
with the new entry under Journal
Do not add to
```
.manifest.json
```
(digests aren't source ingestions)

Either way, append to

log.md

- [TIMESTAMP] DIGEST period="7d" new_pages=N updated_pages=M themes=T connections=C saved=false

默认（聊天输出）：直接打印摘要。在末尾询问： “是否需要将此摘要保存为
journal/digest-YYYY-MM-DD.md
？”

如果用户前缀包含“save”或“write”（例如：

/wiki-digest save

或“生成并保存我的每周摘要”）：

将内容写入

$OBSIDIAN_VAULT_PATH/journal/digest-YYYY-MM-DD.md

（周/月度）或

journal/digest-YYYY-MM-DD-daily.md

（日度）

添加前置元数据：