Introduction

Written by the author, AI-editedAI-generated, author-verified How this module was made

Heads up... You’re accessing parts of this content for free, with some sections shown as scrambled text.

Heads up... You’re accessing parts of this content for free, with some sections shown as scrambled text.

Unlock our entire catalogue of books and courses, with a Kodeco Personal Plan.

Unlock now

In the last lesson you put the Tokens Dashboard through a proper review with two prompts, sorted out what was worth fixing, and applied the changes. You have ten files updated and a clean build.

But think about what happens next time you ask Claude Agent to write something new for this project. It has no memory of any of that. The standards you established, the review process you built up. None of it carries over. Every new session starts fresh.

So instead of fixing the same things over and over, this lesson shows you how to write them down once in a way Claude Agent actually reads and follows.

By the end of this lesson, you’ll be able to:

  • Explain the difference between a CLAUDE.md rule and a skill, and when to use each.
  • Add coding standards to CLAUDE.md so they apply automatically to future code generations.
  • Create a reusable review skill that runs a structured pull request style review on demand.
  • Verify that rules and skills are working without mentioning them in the prompt.
See forum comments
Download course materials from Github
Previous: Quiz: Using AI to Improve the Review Next: Teaching the AI to Improve