Have you ever written a detailed prompt and still gotten an answer that missed the point? A few small habits can make it harder for an AI agent to understand what you want. Let’s look at why that happens and how to make your prompts work more clearly for you.

Reading agent logs by hand is slow, and the raw event files are far too big to paste into a chat. VS Code and GitHub Copilot CLI ship built-in skills that do the reading for you. In this post, you’ll learn how both work, why the log folder is deliberately hard for the agent to reach, and what makes selective access such a clever design choice.

If you’ve built custom Copilot agents, skills, and MCP servers, you may know some of the benefits of using plugins to distribute this content. You may also know how quickly the setup starts to become complicated across AI harnesses. The new Agent Plugins specification gives you a portable core for shared skills and servers while keeping client-specific features in a cleaner, separate namespace. In this post, I walk through the new layout and show how to keep your reusable AI tooling portable without giving up the features that make each client worth using.