Often I find LLMs doing multiple steps to achieve some goals (e.g. do certain operations against JIRA or Gitlab), and if the LLM work seems useful, I instruct it to create a tool to achieve the task more directly and revise skill data to make use of the tool.

Granted I've let it mostly vibecode those tools, so they might be garbage. I should perhaps have it do a refactoring round to make more composable tools..