직업 분류
소프트웨어 품질 보증 분석가·테스터
설명
Run the agentic evaluation repo for a target skill. Use when asked to execute repo-defined suites, collect evidence, write per-case results, and produce a short audit report for the target skill. Also supports evaluation modes: AB tests, subjective scoring,…
원문 언어: 영어
업데이트