菜单
Index an atomic note in existing maps of content and find potential connections to related atomic notes.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Given a YouTube URL, fetch its transcript and extract atomic notes into an Obsidian vault. Use when handed a YouTube link to mine for ideas, or asked to "turn this video into atomic notes / atoms".
Create a dated zip backup of the Obsidian vault and rotate old backups on a grandfather-father-son schedule (14 daily, 5 weekly, 12 monthly, 5 yearly). Use when asked to back up the vault, make a snapshot, or run/prune vault backups.
Extract actionable lessons, key insights, emergent todos, and best practices from a note (e.g. a video transcript or article in an Obsidian vault, for example). Use when asked to "extract insights / lessons / takeaways" from a note or document. Outputs bullet lists in chat, or writes them to a markdown file if asked.
Summarize the past week's daily notes, extracting key findings, links, action items, and potential atomic notes, and write the summary into the matching weekly note.
Fetch and summarize a list of URLs (e.g. from OneTab) into Obsidian-friendly markdown with a brief description of each link.
Summarize the current agent session, create an Obsidian note for it, and link it from today's daily note. Use when the user is finished with a session and wants to log what was accomplished.
| name | index-atomic-notes |
| description | Index an atomic note in existing maps of content and find potential connections to related atomic notes. |
Integrate a new atomic note into the knowledge graph by:
Browse the Topics/ folder to understand what maps of content already exist and what subjects they cover.
If the note fits existing topics:
topics propertyIf no suitable topic exists:
Each atomic note should contain a single, focused insight. Cross-links must enhance without diluting.
| Do | Don't |
|---|---|
| Add brief links that provide nuance | Add explanatory text that expands the scope |
| Suggest connections to the user | Modify notes without permission |
| Preserve the original focus | Turn notes into discussion hubs |
If the answer to the last question is "yes", suggest the link to the user instead of adding it.
Good cross-link — adds nuance to existing insight:
Original: "Large language models understand concepts" Addition: "However, [[Performance depends on verifiability]], which means they show stronger capabilities on verifiable tasks."
Bad cross-link — dilutes atomicity:
Original: "AIs are currently trained very broadly" Addition: "This broad training is particularly effective for verifiable tasks because..." Problem: Shifts focus from describing training to explaining task performance.
Given this atomic note:
---
title: The AIs of today are more grown than written
created: 2025-07-05
tags:
- note/atom
category:
- "[[Atoms]]"
---
Steps:
Topics/Artificial Intelligence.mdtopics property:---
title: The AIs of today are more grown than written
created: 2025-07-05
tags:
- note/atom
topics:
- "[[Artificial Intelligence]]"
category:
- "[[Atoms]]"
---