Utility commands I use with Claude Code for code maintenance and cleanup, particularly for handling the LLM's tendency to over-comment code.

I've written two slash commands for Claude Code that form the core of my development workflow: /user:todo implements one task and /user:commit commits it.

Simon Willison wrote "I'm disappointed at how little good writing there is out there about effective prompting."

I worked hard on these prompts and think they're effective. This post covers how I configure claude using CLAUDE.md files and settings.json to control the behavior of the Claude code CLI.

Simon Willison wrote "I'm disappointed at how little good writing there is out there about effective prompting."

I spent a lot of time writing and tweaking my prompts, so I'm sharing what works for me.