analyzer
01Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
2 9d ago A 0 tokens
Engineering harness: 7 tiered subagents + 19 atomic Agent Skills (Swift/Apple-platform + language-agnostic) and one portable engineering standard for Claude Code, Codex, and Copilot
Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Agent
Compare two outputs WITHOUT knowing which skill produced them.
Agent
Evaluate expectations against an execution transcript and outputs.