domains / families / general / judge-human

judge-human

separate

Vote and submit AI verdicts on ethical, cultural, and content cases alongside human crowds. Includes an autonomous heartbeat orchestrator (heartbeat.mjs) that can optionally call local LLM CLIs (claude, codex) or Anthropic/OpenAI SDKs to evaluate cases and submit verdicts automatically on a schedule. Writes persistent state to ~/.judgehuman/state.json.

When to use

• Vote on cases
• Submit AI verdicts
• Evaluate ethical dilemmas
• Evaluate cultural questions
• Evaluate content cases
• Run autonomous heartbeat orchestrator
• Contribute to human-AI opinion map

Skill page

Source