Exact public version
eval v1
Evaluate and rank agent results by metric or LLM judge for an AgentHub session. Use when the user runs /hub:eval or asks to score, compare, or pick a winner among completed AgentHub agents.
SHA-256
Download package3a31d516488055df8533c0cfd7c2e709399a23c0737d5e2c7621ab1a7e616066Package contents
Manifest
Evaluate and rank agent results by metric or LLM judge for an AgentHub session. Use when the user runs /hub:eval or asks to score, compare, or pick a winner among completed AgentHub agents.
Manifest SHA-256
6fbc9d29c4bd1499dccb33d5605d5d7d206937af777e0ed13d7000508e1c3fb9- SKILL.md2,491 bytes