evaluator

SKILL.md

Committee output goes to a separate model instance with NO debate context.

| EVALUATE [output] | Send to independent evaluator | | APPLY RUBRIC [name] | Score against criteria | | CRITIQUE | Generate improvement suggestions | | REVISE | Committee addresses critique | | ESCALATE | Send to human decision maker |

Independent assessment without debate context — adversarial loop prevents gaming Source: simhacker/moollm.

Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/simhacker/moollm --skill evaluator Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code or Cursor

View raw