The trick is to "just use it", BUT every few weeks grab the logs (you do keep them, right?) and have a session with the model to find out if there are any repeated patterns.
If you find any, consider making them into skills or /commands or maybe even add them to AGENTS.md.
Which logs do you use for that?
I would assume those in ~/.claude/projects/**/*.jsonl. They contain full conversation history, including the tool calls that were made, how man tokens were consumed, etc
Claude has a built-in /insights feature for this, but you can replicate it with any other tool that keeps the session logs on disk.