Agent Evaluation Harness

Design an evaluation harness for an LLM agent before shipping it. Use when the user is building or rewriting an agent, deciding ship/no-ship, debugging regressions, or mentions golden sets, eval suites, regression tests, trace-level evals, LLM-as-judge, scoring rubrics, or asks "how do I test this agent?" / "how do I know if my agent got better?".

cobusgreyling Updated 11.8k repo stars
Skills cross-link graph

File contents

cobusgreyling/agent-skills commit d3a39fd783

Frequently asked questions

npx get-skill add cobusgreyling/agent-evaluation-harness