analyzer
01Agent Claude Code
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
not rated 366
+6 2d ago A 0 tokens
366Stars on the repository
34Mods indexed here, across every type
2d agoLast push, which is what freshness is scored on
customA LICENSE file GitHub cannot name, so bodies are not copied
comparator
02Agent Claude Code
Compare two outputs WITHOUT knowing which skill produced them.
not rated 366
+6 2d ago A 0 tokens
grader
03Agent Claude Code
Evaluate expectations against an execution transcript and outputs.
not rated 366
+6 2d ago A 0 tokens