analyzer
01Agent Claude CodeCursor
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
not rated 10 7mo ago A 0 tokens
copy · 95% BSD-3-Clause
10Stars on the repository
65Mods indexed here, across every type
7mo agoLast push, which is what freshness is scored on
BSD-3-ClauseLicence, which decides whether bodies are shown
comparator
02Agent Claude CodeCursor
Compare two outputs WITHOUT knowing which skill produced them.
not rated 10 7mo ago A 0 tokens
copy · 92% BSD-3-Clause
grader
03Agent Claude CodeCursor
Evaluate expectations against an execution transcript and outputs.
not rated 10 7mo ago A 0 tokens
copy · 98% BSD-3-Clause