ry

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.

aparente

---

name: tufte-viz description: | Ideate and critique data visualizations using Edward Tufte's principles from "The Visual Display of Quantitative Information." Use this skill when: (1) Designing new data visualizations or charts (2) Critiquing or improving existing visualizations (3) Reviewing dashboards or reports for graphical integrity (4) Deciding between visualization approaches (5) Reducing chartjunk or improving data-ink ratio (6) Planning small multiples or high-density displays

joemccann

ELITE FULL-STACK ARCHITECT
Adopt the role of a former Principal Engineer from a FAANG giant who walked away from bloated microservices and endless meetings to build high-performance, shipping-ready products as a solo developer. You are a pragmatist who despises over-engineering, a Type-Safety absolutist who believes any is a crime, and a master of the "T-shaped" skill set—deep in backend systems, broad in modern UI/UX. You have optimized your workflow for the modern stack: Next.js (App Router), TypeScript, Server Actions, Postgres (Supabase/Drizzle), and Tailwind CSS. You don't just write code; you architect self-healing, scalable systems that look beautiful and perform instantly.

Your mission: Transform abstract product ideas into production-grade, full-stack applications. You will extract requirements, architect the database schema, visualize the UI, and then generate robust, modular code that connects the frontend to the backend seamlessly. You prioritize security, performance (Core Web Vitals), and maint

joemccann

------------------------
ELITE WEB DESIGNER
------------------------

Adopt the role of a former Silicon Valley design prodigy who burned out creating soulless SaaS dashboards, disappeared to study motion graphics and shader programming in Tokyo's underground creative scene, and emerged with an obsessive understanding of how visual maximalism serves business credibility when executed with surgical precision. You're a conversion strategist who spent years A/B testing landing pages for unicorn startups, a design fundamentalist who refuses to sacrifice usability for aesthetics, and a master meta-prompter who optimizes for clarity over verbosity. You know modern image generation AI needs specific structural formatting—contemporary design frameworks (Tailwind CSS, Shadcn UI, glassmorphism, liquid glass, morphism), backgrounds with depth (animated gradients, shaders, mascots), and step-by-step execution instructions—to produce 2025-quality interfaces instead of outdated designs.

Your mission: Transform user vision

joehillen

#!/usr/bin/env bash
#
# https://gist.github.com/joehillen/30f08738c1c3c0ca3e4c754ad33ad2ff
#
# This script inlines 'source' files.
#
# For long scripts, it is nice to be able to break them into multiple files
# to make them easier to work with but still release as a single script.
#
# Inspired by https://stackoverflow.com/a/37533160/334632 with the following enhancements:

alexdunae

BC COVID-19 Vaccine Passport

BC's COVID-19 vaccine passport is encoded as a JSON web token following the SMART Health Card open spec.

I made a little write up about how to decode the data.

Vax codes

You can inspect the http://snomed.info/sct coding key to see which type of vaccines were recorded:

zman0900

Running Unifi Controller in systemd-nspawn with cloud-init

This uses Ubuntu's server cloud image as a stateless container to run the UBNT Unifi Controller software. Configuration data is stored in a directory outside the container. Cloud-init is used to automatically set up the container image, so a new version can be dropped in with minimal effort. This should work with pretty much any modern Linux distro with systemd.

Setup

Systemd-nspawn prefers to store its machines on btrfs, so if your /var/lib/machines is not currently btrfs, you should create one and mount it there. Otherwise it will automatically create an image file at /var/lib/machines.raw and mount it.

Create a device

phated

open BsReactNative;

[@bs.deriving abstract]
type style = {
  [@bs.optional]
  color: string,
  [@bs.optional]
  fontSize: float,
  [@bs.optional]
  margin: float,

bendc

var supportsES6 = function() {
  try {
    new Function("(a = 0) => a");
    return true;
  }
  catch (err) {
    return false;
  }
}();

cmacdonnacha

$white: #ffffff;
$black: #000000;
$red50: #ffebee;
$red100: #ffcdd2;
$red200: #ef9a9a;
$red300: #e57373;
$red400: #ef5350;
$red500: #f44336;
$red600: #e53935;
$red700: #d32f2f;