Know who speaks before the skill runs > TL;DR: Always define a clear role at the top of every skill file so you know whose perspective drives the execution. Common Mistake ❌ You write a skill full of rules but assign no role. The AI starts execut...

Everyone is talking about Loop Engineering. Apparently, you don't need to program anymore. > TL;DR: Loop Engineering is the hottest AI workflow pattern of 2026. But it hides a dirty secret. The Tweet That Started It All https://x.com/2063697162748...

Brushing Over Real Problems > TL;DR: You write tests that touch every line but verify nothing, creating false confidence in a broken system. Problems 😔 False confidence Hidden production defectshttps://coderlegion.com/6337/we-need-to-stop-the-bug...

Comments are dead. Tests are alive > TL;DR: Take your comment, compact it, and name your functions. > Now test it and remove the comments. Problems Addressed 😔 Maintainability Readability Related Code Smells 💨 https://coderlegion.com/8106/code-...

Don't let the AI grade its own homework. > TL;DR: Spawn a fresh subagent after every task to check your rules, because the AI that did the work can't audit itself. Common Mistake ❌ You write a detailed AGENTS.mdhttps://coderlegion.com/13150/ai-cod...

You have a big algorithmic method. Let's break it. > TL;DR: Long methods are bad. Move them and break them. Problems Addressed 😔 Lack of Testability Accidental Complexity Testing Private Methodshttps://maximilianocontieri.com/code-smell-112-test...

Cap the size before the agent writes a single line. > TL;DR: Tell your AI to split work into small reviewable pull requests before it writes any code. Common Mistake ❌ You ask your AI agent to build a feature. The agent opens a 2,000-line pull re...

Make the AI Work Inside Boundaries, Not Outside Them > TL;DR: Install your harness before prompting: the structure you set up first is what turns an impulsive AI into a safe, steerable collaborator. Common Mistake ❌ You open a fresh chat and type ...

Stop shipping code you can't explain. > TL;DR: Merging code you don't understand creates comprehension debt that compounds until your team can no longer maintain it. Common Mistake ❌ You ask the AI to implement a feature. The code looks clean. T...

Build a Persistent Memory Layer Your AI Can Actually Use > TL;DR: Use Obsidian with Markdown notes, YAML metadata, and direct AI file access to build a Second Brain with LLMs that gives your tools persistent project context. Common Mistake ❌ You p...

State your reasons before your prompt and the AI will solve the right problem. > TL;DR: Tell the AI your reason before your request to get solutions that match your real constraints. Common Mistake ❌ You send commands to the AI without context. "...

Talk twice as fast as you type, and create richer prompts with less effort. > TL;DR: Dictate your prompts instead of typing them to speak twice as fast and give more context. Common Mistake ❌ You write detailed prompts by hand, word by word, stayi...

When you have a lot of data to analyze, Ask for a tool, not a summary. > TL;DR: Ask the AI to write a program that analyzes your data instead of pasting all your data into the prompt. Common Mistake ❌ You have 50 complex JSON files. You paste the...

Your PR descriptions are training data for your future self, and for every agent after you. > TL;DR: Improve the AI tools, rules, skills, and workflows you use in every pull request so your team and future agents can learn, reproduce, and improve on...

Don't let your most important instructions drown in context noise > TL;DR: Bury critical rules and AI models ignore them. Use explicit markers to force compliance. Common Mistake ❌ You write a long skillhttps://coderlegion.com/10515/ai-coding-tip-...

Don't turn collaborators into permanent roommates > TL;DR: You should avoid storing stateless utility classes as instance variables initialized with new. Problems Hardcoded dependencies Testing difficulties High couplinghttps://coderlegion.com...

Context is precious. Don't waste it. > TL;DR: Split your AGENTS.md into layered files so your AI loads only the rules that matter for the code you touch. Common Mistake ❌ You put a single massive AGENTS.md , CLAUDE.md , GEMINI.md at your project r...

Refactorings are amazing to grow and improve our code > TL;DR: Let's start addressing our code smells I have been writing a series on Code Smells for a long time. https://coderlegion.com/10942/how-to-find-the-stinky-parts-of-your-code There are a...

Forget about data structures, DTOs, POJOs, and anemic objects. > TL;DR: Avoid external manipulation Problems Addressed Encapsulation Violation Anemichttps://coderlegion.com/7246/code-smell-01-anemic-models Models Related Code Smells https://c...

Structure your skills so the AI loads only the files it needs. Split complexity across modular files and use keywords to trigger conditional loading. > TL;DR: You reduce token usage when you trigger conditional loading instead of loading all files a...