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

karpathy

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.

dabit3

import Anthropic from "@anthropic-ai/sdk";
import { Pool } from "pg";

const anthropic = new Anthropic();

// dn connection - Claude never sees this
const db = new Pool({
  host: "your-database-host.com",
  port: 5432,
  database: "sales_db",

vincentkoc

description	Build high-impact documentation grounded in best practices
argument-hint	TYPE=<tutorial|how-to|reference|explanation>

Use this when drafting or overhauling docs. It works for net-new guides, branch-specific updates, or sweeping improvements. Pass TYPE if you already know the Diataxis bucket.

1. Define intent & success

• Audience: skill level, prerequisites, and the “job to be done.”
• Outcome: what readers can do immediately after (e.g., “deploy first webhook”).

intellectronica

Meeting Notes and Transcript with Gemini

1. Record the meeting (I use Apple's Voice Memos app, but any audio recoreder will do).
2. Paste or upload the recording into Gemini (either the Gemini app or AI Studio).
3. Paste the prompt.
4. Fill in the RECEIPIENTS at the end.
5. Use Gemini 2.5 Flash for good enough, Gemini 2.5 Pro for superb.
6. Get detailed meeting notes and diarised transcript.

---

intellectronica

<style-guide>

</style-guide>


<structure-model>

</structure-model>

intellectronica

My Guiding Principles for You, My AI Coach/Therapist

This document outlines how I expect you to operate as my life and business coach, therapist, and accountability partner. My goal is a collaborative relationship that is direct, challenging, and results-oriented.

1. Communication Style: Direct & Focused

• Be Extremely Direct: I want straightforward, unambiguous communication. Get straight to the point. No beating around the bush. If you see an issue, name it.
• Challenge Me: Don't shy away from challenging my assumptions, my excuses, or my perspectives. I expect "tough love." Push me to be better.
• No Abstract Fluff: Focus on the concrete and the practical. Avoid vague concepts or overly philosophical discussions unless they directly lead to an actionable insight for a specific situation.
• Concise Responses: Your replies should be succinct and targeted. Deliver the core message without unnecessary elaboration. Think bullet points or short paragraphs over essays. I don

hamelsmu

Question: Should I avoid using RAG for my AI application after reading that "RAG is dead" for coding agents?

Many developers are confused about when and how to use RAG after reading articles claiming "RAG is dead." Understanding what RAG actually means versus the narrow marketing definitions will help you make better architectural decisions for your AI applications.

Answer: The viral article claiming RAG is dead specifically argues against using naive vector database retrieval for autonomous coding agents, not RAG as a whole. This is a crucial distinction that many developers miss due to misleading marketing.

RAG simply means Retrieval-Augmented Generation - using retrieval to provide relevant context that improves your model's output. The core principle remains essential: your LLM needs the right context to generate accurate answers. The question isn't whether to use retrieval, but how to retrieve effectively.

For coding

mattppal

Frontend Security

	Security Measure	Description
☐	Use HTTPS everywhere	Prevents basic eavesdropping and man-in-the-middle attacks
☐	Input validation and sanitization	Prevents XSS attacks by validating all user inputs
☐	Don't store sensitive data in the browser	No secrets in localStorage or client-side code
☐	CSRF protection	Implement anti-CSRF tokens for forms and state-changing requests
☐	Never expose API keys in frontend	API credentials should always remain server-side

intellectronica

Migrating a v0.dev Project to GitHub and Vercel (Step-by-Step Guide)

Researched and generated by ChatGPT Deep Research

---

Overview: Vercel’s v0.dev is an AI-based tool that helps you generate a Next.js project via a chat interface. Once you’ve created an app with v0 and even deployed it on Vercel, you may want to move the code into a GitHub repository for version control and continuous deployment. This guide will walk you through exporting your v0 project’s files, pushing them to a new GitHub repo, linking that repo to Vercel for automatic deployments, and ensuring you can still use v0 for future development. We’ll also cover configuration tips and best practices along the way.

1. Exporting Project Files from v0