artemgetmann

🧠 How to Save Context Tokens When Using Claude Code

This is a personal reference workflow for minimizing token usage while maintaining project continuity across Claude Code (Sonnet 4 with file access).

---

✅ Setup: Populate CLAUDE.md

Claude loads CLAUDE.md automatically at session start.

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.

tandpfun

name

extract-clothing-cutouts

description

Extract high-quality, deduplicated transparent ecommerce clothing cutouts from a folder of photographs where people wear one or more garments. Use when Codex must find outfit or model photos, identify unique clothing across images, create focused references, reconstruct complete garments with Imagegen, remove a solid chroma background into RGBA PNGs, and output only the finished clothing images into a new folder under the current working directory.

Extract Clothing Cutouts

Turn photographs of worn clothing into source-faithful standalone catalog PNGs. Treat each result as a reconstruction from visible evidence, not literal segmentation whenever the wearer or another layer occludes part of the garment.

Start by asking for two paths

ZergsLaw

---
name: safe-skill-install
description: >-
  Use ALWAYS when installing a new agent skill — via `npx skills add`, cloning a repo, a zip,
  or a local folder. Before installing, the skill MUST be scanned with security scanners
  (NVIDIA SkillSpector, optionally Perplexity Bumblebee) and installed only per the scanner's
  verdict. Never install a skill that has not passed the scan.
---

# Safe skill install

ZergsLaw

---
name: grill-me
description: Builds a complete task brief before any code is written. Interrogates the user to fill goal, scope, constraints and acceptance criteria, then produces TASK_BRIEF.md from the embedded template. Use when the user gives a raw or vague task intention, says "grill me", asks for a task brief or spec, or makes an underspecified feature request like "add support for X".
---

# Grill Me - build a task brief through interrogation

## Overview
Turn a raw intention into a complete TASK_BRIEF.md through a short, structured
interrogation. The brief transfers responsibility for understanding the task

paulfranco

Interview Questions

Node.js

Q1: What do you mean by Asynchronous API? ☆☆

Answer: All APIs of Node.js library are aynchronous that is non-blocking. It essentially means a Node.js based server never waits for a API to return data. Server moves to next API after calling it and a notification mechanism of Events of Node.js helps server to get response from the previous API call.

Source: tutorialspoint.com

ImagineGamingPlay

# Put this code in shell
npm init -y && npm i --save-dev node@16 && npm config set prefix=$(pwd)/node_modules/node && export PATH=$(pwd)/node_modules/node/bin:$PATH