Use when auditing an existing agent skill (SKILL.md) to find where it leans on LLM judgment for work that could be deterministic, and to emit runnable promptfoo assertions that validate the deterministic parts. Covers two axes — offloading AI steps to code, and constraining AI output format. Triggers for "/determinize-skill PATH", "make this skill more deterministic", "audit a skill for determinism", "where can this skill be deterministic".
