skill
직업 분류
설명
업데이트
evaluator
소프트웨어 품질 보증 분석가·테스터
Grade a benchmark submission against the hidden reference answers and rubrics, producing per-question and overall scores out of 10. Use when asked to evaluate, score, or grade a submission under submissions/.
2026-07-09
test-taker
소프트웨어 개발자
Take the LLM-agent capability benchmark - create a submission folder named <llm>+<harness> and answer all three questions (offline dashboard, CSV analysis, architecture design). Use when asked to take the test, sit the benchmark, or generate a benchmark submission.
2026-07-09