home/categories/testing/aufrank-agent-skills-skills-eval-harness-kit-skill-md
testingtesting-security

eval-harness-kit

Build and run deterministic evaluation suites for agent workflows (single-turn or agentic). Use when you need reproducible eval runs with manifests, graders, metrics, and JSONL logs for capability or regression tracking.

aufrank
maintainer
aufrank
更新於 1/13/2026
星標
0
分支
0
quick start

Installation and usage

Build and run deterministic evaluation suites for agent workflows (single-turn or agentic). Use when you need reproducible eval runs with manifests, graders, metrics, and JSONL logs for capability or regression tracking.

安裝
$ install --globalskills.sh
使用

安裝後,您可以透過在終端機執行以下指令來使用此技能:

skills use eval-harness-kit