atomize
Skill19 starsChanged 8 months agoMITView on GitHub
Atomize any content into your Zettelkasten vault. Accepts text, file paths, or URLs. Extracts atomic ideas, finds connections to existing notes, and saves to your vault.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- sergeeey/Claude-cod-top-2026their own version, first seen May 13, 2026
- blueOctopusAI/intel-hubtheir own version, first seen Feb 15, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- sergeeey/Claude-cod-top-2026★ 9same name
- blueOctopusAI/intel-hub★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- cos-reviewSkill
- daily-logSkill
- linkedin-research-postSkill
- ai-personal-os-onboardingSkill
- slide-inspectorSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
17 rules. About 0 are common, 10 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈10
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Ask ONE question using AskUserQuestion:
- Distinctive: line 26
Pasted text: Use it directly
- Distinctive: line 27
File path: Read the file
- Distinctive: line 28
Describe an idea: Use their description
- Very specific: line 29
Daily logs: Read all notes/daily-log-*.md files, extract Highlight and Blocker sections (ignore Vitals metrics — energy/focus/mood are …
- Very specific: line 50
Use Glob to find all existing atomic/*.md files
- Very specific: line 51
Use Grep to search existing notes for related keywords and concepts
- Very specific: line 52
If related notes exist, add [[wikilinks]] with a brief explanation of the connection
- Distinctive: line 53
If no related notes exist, that's fine — connections grow over time
- Very specific: line 58
Create the atomic/ directory if it doesn't exist
- Distinctive: line 60
Check existing files to avoid number collisions
- Distinctive: line 100
If this is their first time using /atomize and they have fewer than 3 atomic notes total, add:
- Very specific: line 106
If atomic/ has 0 existing notes: skip connection search, just create the notes and mention "No existing notes to connect to yet — your …
- Distinctive: line 107
If input is very short (1 sentence): create just 1 atomic note, that's fine
- Distinctive: line 108
If input is very long (full article): extract the 5-7 most important ideas, not everything
- Distinctive: line 109
If a daily log has "Nothing major" as blocker: skip it, no knowledge there
- Distinctive: line 111
Do NOT turn this into a long conversation.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/atomize — Knowledge Atomizer
Turn any content into connected atomic notes in your Zettelkasten vault.
Input Flow
Ask ONE question using AskUserQuestion:
Question 1: What to atomize?
- Question: "What do you want to atomize?"
- Options:
["Paste text here", "Give a file path", "Describe an idea", "Atomize my recent daily logs"] - Accept whatever they provide.
Based on their choice:
- Pasted text: Use it directly
- File path: Read the file
- Describe an idea: Use their description
- Daily logs: Read all
notes/daily-log-*.mdfiles, extract Highlight and Blocker sections (ignore Vitals metrics — energy/focus/mood are data, not knowledge)
Extraction Rules
From the input, extract atomic ideas following these rules:
- One concept per note — if an idea has two parts, make two notes
- 2-5 sentences — express the idea concisely
- Own words — reformulate, don't copy-paste. The goal is YOUR understanding, not a quote
- Tags — add 2-4 relevant tags based on content
- Source attribution — note where the idea came from
Typically extract 2-5 atomic notes from a paragraph or article excerpt. For daily logs, focus on:
- Ideas hidden in Highlight entries (things learned, realized, discovered)
- Patterns in Blocker entries (recurring problems = knowledge)
- Any insights that weren't fully developed
Connection Discovery
For EACH extracted idea:
- Use
Globto find all existingatomic/*.mdfiles - Use
Grepto search existing notes for related keywords and concepts - If related notes exist, add
[[wikilinks]]with a brief explanation of the connection - If no related notes exist, that's fine — connections grow over time
File Creation
- Get today's date via
date +%Y-%m-%d(Bash) - Create the
atomic/directory if it doesn't exist - For each atomic idea, create a file:
atomic/YYYY-MM-DD_NNN.mdwhere NNN is a 3-digit sequence number (001, 002, 003...) - Check existing files to avoid number collisions
File Template
---
id: YYYY-MM-DD_NNN
title: "[Descriptive title]"
date: YYYY-MM-DD
source: "[Where the idea came from]"
tags: [tag1, tag2]
---
# [Title]
[2-5 sentences expressing the idea in your own words]
## Connections
- [[related-note-id]] — [Why this connects]
## Source Context
[Brief: who said it, where you read it, what prompted the thought]
---
*Created via /atomize*After Saving
Print a summary:
Atomized! X notes created, Y connections found to existing notes.
New notes:
- atomic/YYYY-MM-DD_001.md — "[title]"
- atomic/YYYY-MM-DD_002.md — "[title]" → connected to [[existing-note]]
- atomic/YYYY-MM-DD_003.md — "[title]"
If this is their first time using /atomize and they have fewer than 3 atomic notes total, add:
Tip: The more notes you add, the more connections appear. Try /atomize daily with one article, conversation, or idea.
Edge Cases
- If
atomic/has 0 existing notes: skip connection search, just create the notes and mention "No existing notes to connect to yet — your graph starts here!" - If input is very short (1 sentence): create just 1 atomic note, that's fine
- If input is very long (full article): extract the 5-7 most important ideas, not everything
- If a daily log has "Nothing major" as blocker: skip it, no knowledge there
Do NOT turn this into a long conversation. Extract, create, summarize. The whole interaction should take under 3 minutes after the user provides input.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

