<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Clean-Code on Tobias Theel | Senior Software Engineer</title><link>https://blog.noobygames.de/tags/clean-code/</link><description>Recent content in Clean-Code on Tobias Theel | Senior Software Engineer</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Mon, 20 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.noobygames.de/tags/clean-code/index.xml" rel="self" type="application/rss+xml"/><item><title>The Architecture of Instructions: Mastering GEMINI.md</title><link>https://blog.noobygames.de/blog/gemini-instructions/</link><pubDate>Mon, 20 Apr 2026 00:00:00 +0000</pubDate><guid>https://blog.noobygames.de/blog/gemini-instructions/</guid><description>Introduction In my previous post, we explored how Gemini Code Assist&amp;rsquo;s Agent Mode can handle multi-file refactors. However, an agent is only as good as the instructions it follows. Without guidance, AI might generate code that works but violates your team&amp;rsquo;s architectural standards.
To solve this, Gemini supports a special file: GEMINI.md. Think of this as the &amp;ldquo;System Prompt&amp;rdquo; for your entire repository.
What is GEMINI.md? The GEMINI.md file is a Markdown document placed in your project&amp;rsquo;s root.</description></item></channel></rss>