Discover gists

Claude-SPARC Automated Development System For Claude Code

Overview

The SPARC Automated Development System (claude-sparc.sh) is a comprehensive, agentic workflow for automated software development using the SPARC methodology (Specification, Pseudocode, Architecture, Refinement, Completion). This system leverages Claude Code's built-in tools for parallel task orchestration, comprehensive research, and Test-Driven Development.

Features

Comprehensive Research Phase: Automated web research using parallel batch operations
Full SPARC Methodology: Complete implementation of all 5 SPARC phases

Learning LLMs in 2025

So you know how the transformer works, and you know basic ML/DL, and you want to learn more about LLMs. One way to go is looking into the various "algorithmic" stuff (optimization algorithms, RL, DPO, etc). Lot's of materials on that. But the interesting stuff is (in my opinion at least) not there.

This is an attempt to collect a list of academic (or academic-like) materials that explore LLMs from other directions, and focus on the non-ML-algorithmic aspects.

Courses

David Chiang's Theory of Neural Networks course.
This is not primarily LLMs, but does have substantial section on Transformers. Formal/Theory. More of a book than a course.

Phison PS2251-xx USB flash drive controller mode configuration

Overview

Phison based flash drives have various modes that dictate how they operate;

as a regular flash drive (mode 3)
as a dual-volume flash drive (mode 7)
as a single volume flash drive + cdrom (mode 21)

Complete Recent Discord Quest

Note

This does not works in browser for non-video, non-activity quests! For stream/play quests use the desktop app!

Note

When doing stream quests, you need at least 1 other account in the vc!

How to use this script:

Accept a quest under Discover -> Quests

Cursor's Memory Bank

I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read ALL memory bank files at the start of EVERY task - this is not optional.

Memory Bank Structure

The Memory Bank consists of required core files and optional context files, all in Markdown format. Files build upon each other in a clear hierarchy:

flowchart TD

health

wellnessfx - Improve health, fitness, wellness through blood tests, doctors, nutrition

driphydration - Drip Hydration Mobile IV Therapy | NAD, Dehydration, Hangover, Flu, Myers Cocktail

elysiumhealth - Breakthroughs in aging research are no longer a myth of science fiction but scientific fact. Elysium makes first-of-their-kind health products and technologies backed by partnerships with institutions at the forefront of aging research.

obasan - Obasan Mattress

	/**
	"by/composed by": https://x.com/bandinopla
	Based on article by Roman Liutikov: https://romanliutikov.com/blog/ps1-style-graphics-in-threejs
	Modifications done with DeepSeek: https://chat.deepseek.com/
	*/
	import * as THREE from 'three';

	export class PS1Material extends THREE.ShaderMaterial {
	constructor({ map, color }: { map: THREE.Texture, color:THREE.ColorRepresentation }) {
	super({

	#!/bin/sh

	# show_wifi_clients.sh
	# Shows MAC, IP address and any hostname info for all connected wifi devices
	# modification based on https://openwrt.org/faq/how_to_get_a_list_of_connected_clients

	echo "# All connected wifi devices, with IP address,"
	echo "# hostname (if available), and MAC address."

	printf "%-15s %-15s %15s\n" "IP address" "Host" "MAC"