4 posts tagged with "AI"

Today I learned Claude Code has hooks! These let you automatically run commands when certain events happen. I'm using this to auto-fix RuboCop violations every time Claude edits a Ruby file, and it's making my development flow so much smoother.

Today I discovered that Claude Code's slash commands can execute bash commands before running, capturing their output as context. This is making me so excited! When you have a bunch of commands to run, Claude is not always reliable for running the all, or running them in the right order.

I started working on the Octoprint gem back in March 2022. The goal was simple: create a Ruby wrapper around the Octoprint REST API so I could interact with multiple 3D printer servers for another project.

Simple, but incredibly boring.

The work was pure drudgery: read an API endpoint's documentation, create classes for models and errors, write tests, document everything, repeat. I implemented just what I needed and then... let it sit. For years. Untouched except for the occasional Dependabot update.

I was getting bored writing the CLAUDE.md file for my Ruby project. The usual drill: "Use RSpec for testing. Use Rubocop for linting." You know the type: bullet points that technically cover the basics but somehow miss the mark.

So I handed it off to Claude with a simple request: "Can you document conventions and commonly agreed-on best practices for this Rails project?"

What came back surprised me. Claude didn't just reformat my scattered notes; it completely restructured them. My lazy bullet points became a comprehensive guide with clear sections, context, and actionable details. The output felt more... intentional. Like it was designed to actually help someone succeed, not just check a documentation box.

But then, I realized Claude had essentially shown me how to write for its own "neurons."

That moment got me thinking. If Claude could improve my documentation, could it improve my prompts?