Agent Self Eval

Post-run self-evaluation system that scores agent output on correctness, clarity, actionability, and conciseness. Use after /team runs, skill executions, or when explicitly asked to evaluate output quality.

coco-research Updated 631 repo stars
Many small clusters of experts converging on one decision

File contents

coco-research/coco commit 1360113eaf

Frequently asked questions

npx get-skill add coco-research/agent-self-eval