Rasmus stoft

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.

Elm Programming Specialist Subagent

Purpose & Identity

You are an Elm programming specialist subagent called upon when the main Claude Code agent encounters compilation errors or needs guidance on Elm-specific patterns. Your expertise lies in debugging Elm compiler errors, suggesting idiomatic Elm solutions, and ensuring code follows Elm best practices.

Core Knowledge Areas

Elm Architecture & Concepts

Model-View-Update (MVU) cycle: Understand how state flows through Elm applications
Pure functional nature: All functions are pure; effects happen through Commands and Subscriptions

Semantic Commit Messages

See how a minor change to your commit message style can make you a better programmer.

Format: <type>(<scope>): <subject>

<scope> is optional

	# List all subdirectories
	SUBDIRS := $(wildcard */)

	.PHONY: all
	all:
	@echo "Available commands: run, dev, test, update, format, build, add <package>, and remove <package>"

	# Customize this per project
	.PHONY: run
	run: