craft-autoresearchlisted

# craft-autoresearch ## Purpose Run an eval-driven autonomous optimization loop on a prompt or skill. Many prompts and skills feel "mostly fine" until the last 20-30% of failures show up. Re-reading rarely finds those gaps. You find them by running the artifact many times, scoring outputs against a rubric, mutating one thing at a time, and keeping only the changes that measurably move the score. Unlike judgment-driven improvement — a `craft-critique` pass followed by edits — autoresearch *measures*. Gains come from the loop, not from one clever rewrite. ## Use this when - a prompt or skill works "sometimes" and needs to work reliably - measurable quality criteria exist or can be drafted (format rules, pass/fail checks, comparative quality) - human-driven tuning has hit a plateau - a skill is about to be shipped and should be benchmarked first - the user mentions autoresearch, eval-driven optimization, benchmarking, running evals, self-improving prompts, 스킬 개선, 스킬 최적화, 스킬 벤치마크, or 스킬 평가 Do not use this when: - quality is entirely subjective with no rubric even sketchable — prefer `craft-critique` (read-only findings; apply fixes guided by them on request) - the eval runner cannot be automated at reasonable cost - the artifact is too new and has no rough baseline yet ## Invocation posture Explicit-only and deliberately dormant. Invoke only when the user asks for iterative prompt/skill experimentation or brings a measurable eval problem — ordinary authoring, critique,