atomize

/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-*.md files, 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:

1. One concept per note — if an idea has two parts, make two notes
2. 2-5 sentences — express the idea concisely
3. Own words — reformulate, don't copy-paste. The goal is YOUR understanding, not a quote
4. Tags — add 2-4 relevant tags based on content
5. 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:

1. Use Glob to find all existing atomic/*.md files
2. Use Grep to search existing notes for related keywords and concepts
3. If related notes exist, add [[wikilinks]] with a brief explanation of the connection
4. If no related notes exist, that's fine — connections grow over time

File Creation

1. Get today's date via date +%Y-%m-%d (Bash)
2. Create the atomic/ directory if it doesn't exist
3. For each atomic idea, create a file: atomic/YYYY-MM-DD_NNN.md where NNN is a 3-digit sequence number (001, 002, 003...)
4. Check existing files to avoid number collisions