Skill Store 33

Judge

Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation

by neolabhq

The skill

Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation

This skill's licence does not allow redistribution, so the store does not show its text. Read it at the source.

Use this skill

Connect your agent to the Skill Store MCP server and ask for it by ref: neolabhq/judge-67409136764.

Markdown version

Details

Publisher
neolabhq
Category
AI & Agents › Agent evaluation
Updated
2026-08-26

References

More from neolabhq

  • Actualize Reconcile the project's FPF state with recent repository changes
  • Add Task creates draft task file in .specs/tasks/draft/ with original user intent
  • Agent Evaluation Evaluate and improve Claude Code commands, skills, and agents.
  • Analyse Problem Comprehensive A3 one-page problem analysis with root cause and action plan

Related skills

  • Do And Judge Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry…
  • The Jury Use when a question, decision, plan, tradeoff, or claim needs a rigorous verdict and one perspect…
  • Do Competitively Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, mu…
  • Evaluation Builds evaluation frameworks for agent systems, including LLM-as-judge design.
  • Judge With Debate Evaluate solutions through multi-round debate between independent judges until consensus