Walter H. Roman whroman

Simple Markdown Zettelkasten

(Simple Markdown Zettelkasten, or SMZ for giggles.)

As I've lurked productivity twitter, I've noticed that a lot of the digital Zettelkasten[^1] systems that I've seen fall into two categories: ones using markdown plain text files, and ones using a dedicated tool like Roam/Notion. Systems using markdown files can differ wildly given the eccentricities of the particular user, and their favorite text editor.

After some research, here is what I believe to be the most compatible markdown format for plain-text Zettelkasten files.

tags: #notes, #productivity

Default shortcuts

Scrolling

Action	Shortcut
Scroll line up	ctrl+shift+up (also ⌥+⌘+⇞ and ⌘+↑ on macOS)
Scroll line down	ctrl+shift+down (also ⌥+⌘+⇟ and ⌘+↓ on macOS)
Scroll page up	ctrl+shift+page_up (also ⌘+⇞ on macOS)
Scroll page down	ctrl+shift+page_down (also ⌘+⇟ on macOS)

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

	// Update globs depending on your framework
	---
	name: tailwind_v4
	description: Guide for using Tailwind CSS v4 instead of v3.x
	globs: ["*/.{js,ts,jsx,tsx,mdx,css}"]
	tags:
	- tailwind
	- css
	---