Great Rules In, Great Results Out
An investment in writing great rules for your AI tools will be repaid many times over.

I’ve written recently about how Cursor, the AI IDE, isn’t just great for code—it’s a superb copywriting tool as well.
As part of my recent implementation of the Astro static site generator, I wanted to improve the instructions I give Cursor when I start writing a new post. What I need is a scaffolding consisting of a directory for the post, a skeleton content Markdown file, and subdirectories for related items: images, social media posts, and AI chat transcripts (in case I want to highlight an AI conversation). This process changed a bit when I migrated from Hugo to Astro and I so I updated and refined my related Cursor rule.
All I had to do was give Cursor the rule as @ context, and then make a very simple request.
Here’s the full transcript of my interaction with Cursor:
AI Conversation Transcript: Cursor
8/28/2025 at 08:25:44 CDTNote that the interaction consisted of a single, simple request, and Cursor doing all the work. That’s the way, uh-huh uh-huh, I like it, uh-huh uh-huh …
But how did Cursor know what to do? That astro-mdx-content-authoring
rules file is 287 lines long, and carefully explains everything about authoring content files within my new Astro environment, including this scaffolding process.
Creating that rules file took some work—though these days I have Claude Code write most of my Cursor rules. Still, I there was work involved in thinking through what was needed and in continuing to refine the rule as my Astro setup evolved and new ideas came to mind.
But the payback is high: a laborious process reduced to a single, simple request.
Invest in your AI rules, and thou shalt be repaid.