analyzer
01Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
568 3mo ago A 0 tokens
568Stars on the repository
60Mods indexed here, across every type
3mo agoLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied
comparator
02Agent
Compare two outputs WITHOUT knowing which skill produced them.
568 3mo ago A 0 tokens
grader
03Agent
Evaluate expectations against an execution transcript and outputs.
568 3mo ago A 0 tokens