drawcode

tldr;

This is a structured developer-persona prompt that enforces modular context saving with frontmatter (contexts/context-*.md), isolates code reviews to separate paths, and mandates a strict "Update " prefix syntax for PR summaries.

---

You are an expert AI software engineering collaborator. Your role is to assist with codebase management, context tracking, code reviews, and pull request automation by adhering strictly to the operational guardrails detailed below.

1. Context & Memory Management

• Post-Thread Capture: After completing a thread, extract and summarize the critical architectural patterns, code changes, and workflows. Save these into contexts/context-*.md (updating existing files or creating new ones).

drawcode

Context Manage

Situation: thread solved some things and I no longer need the full context and you don't want to trust compact from a platform that is incentivized to get you to spend -- compact and transfer context your own way where you can see what is included

Ask the thread to create a context prompt to that you want to transfer to a new thread

Simple (works for most things)

"Make me a context prompt that I can use to transfer to another window to resetup context based on all learnings on this so far"

drawcode

title	Unreal Engine Performance Guidelines
author	CodeGameDevCommon
type	skill-file
tags	unreal-engine performance optimization cpu gpu profiling best-practices
version	1.0.0
description	A comprehensive checklist and guide for diagnosing and fixing performance bottlenecks in Unreal Engine, structured for both developers and AI workhorse models.

tldr; Before you optimize anything in Unreal Engine, find out exactly what is slowing you down by using stat unit. Figure out if you are Game Thread (CPU) bound, Draw Thread (CPU) bound, or GPU bound. Once identified, ruthlessly eliminate Blueprint Ticks, leverage Nanite/Instanced Meshes for draw calls, keep shaders green in Shader Complexity mode, and always use Soft References for asset loading to avoid memory bloat. Keep it simple, use built-in tools, and profile often!

drawcode

.NET MAUI High-Performance & Multi-Platform Checklist

🚀 1. Startup & Architecture

• Lazy Service Resolution: Defer instantiation of heavy services to improve initial app responsiveness.

// MauiProgram.cs registration
builder.Services.AddTransient<HeavyService>();
builder.Services.AddTransient<Lazy<IHeavyService>>(p => 
    new Lazy<IHeavyService>(() => p.GetRequiredService<HeavyService>()));

drawcode

# top-most EditorConfig file
root = true

[*]
charset = utf-8
indent_style = space
indent_size = 4
end_of_line = lf
insert_final_newline = true
trim_trailing_whitespace = true

drawcode

Unity Performance Checklist

Table of Contents

• Main Performance Impacts to Games Built on Unity Engine
  • CPU Bottlenecks
  • GPU Bottlenecks
• Memory Bottlenecks

drawcode

#include <iostream>
#include <string>
#include <vector>
#include <regex>
#include <functional>

/// @brief Replaces occurrences of a regular expression pattern in a string with a replacement string.
///
/// @param input The string to search in.
/// @param pattern The regular expression pattern to match.

drawcode

// create basic cplusplus main

#include <iostream>
#include <vector>
#include <string>

using namespace std;

int main()
{

drawcode

/**
 * Different case matchers
 *
 * @see <a href="https://en.wikipedia.org/wiki/Naming_convention_(programming)#Examples_of_multiple-word_identifier_formats">Examples of multiple word identifier formats</
 */
sealed class CaseMatcher(private val regex: Regex) {
    open fun notMatches(source: String?): Boolean {
        return !matches(source)
    }

drawcode

Latency Comparison Numbers (~2012)
----------------------------------
L1 cache reference                           0.5 ns
Branch mispredict                            5   ns
L2 cache reference                           7   ns                      14x L1 cache
Mutex lock/unlock                           25   ns
Main memory reference                      100   ns                      20x L2 cache, 200x L1 cache
Compress 1K bytes with Zippy             3,000   ns        3 us
Send 1K bytes over 1 Gbps network       10,000   ns       10 us
Read 4K randomly from SSD*             150,000   ns      150 us          ~1GB/sec SSD