eval-fire
Run a single eval class (writing | story | technical | behavior) against one or more curriculum files. Dispatches a class-judge subagent with the relevant compendiums (filtered by `eval_classes:` frontmatter) and the matching judge prompt template. Returns a structured per-rule verdict. Mirrors `/research-review`'s parallel-launch pattern but scoped to one class per invocation. The full four-class audit lives in `/curriculum-pre-ship-audit`; this skill is the single-class on-demand fire.