Ask HN: What makes someone good at using Claude Code?

I am building Promptster - an AI fluency platform that helps level up engineering organizations. Engineering managers invite their teammates and Promptster analyzes the engineers work with ai coding tools (claude code, codex, cursor, copilot). The manager receives a team-aggregate dashboard where they can roll-out certain practices / skill to their whole team. Each IC receives their own dashboard where they can see their fluency statistics, skill usage, context management, and a DORA dashboard.

We have an open-source rubric that tries to answer, what are best practices for Claude Code (and AI coding agents in-general), would love to hear thoughts and feedback on it. The question is a bit abstract, but I tried my best to figure out practices that I use myself and the top minds agree on.

https://github.com/promptster-ai/rubric