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: