analyzer
01Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
163 29d ago A 0 tokens
original MIT
163Stars on the repository
7Mods indexed here, across every type
29d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
bineval
02Agent
Evaluate a skill artifact with atomic binary yes/no questions, one answer (1/0) per question, each preceded by a written critique grounded in evidence from the skill's own files. Aggregate to per-dimension scores in [0,1]; the orchestrator turns your answers into the overall score and the pass/fail gate.
163 29d ago A 0 tokens
original MIT
comparator
03Agent
Compare two outputs WITHOUT knowing which skill produced them, using binary yes/no questions.
163 29d ago A 0 tokens
original MIT
grader
04Agent
Evaluate expectations against an execution transcript and outputs.
163 29d ago A 0 tokens
original MIT