I wonder what the accuracy is for Claude to always follow a Skill accurately. I've had trouble getting LLMs to follow specific workflows 100% consistently without skipping or missing steps.
We also have the same issues with our fellow humans. LLMs do not replace the need for imperative programs that reliably execute well-defined steps. Turn it inside out. Use the LLM to write the imperative program to execute the workflow. Where necessary, insert the LLM into the workflow to perform the task(s) that can't be done imperatively.