judge-with-debate
judge-with-debate
Key benefits:
- Structured evaluation - Meta-judge produces tailored rubrics and criteria before judging begins
- Multiple perspectives - Three independent judges reduce individual bias
- Evidence-based debate - Judges defend positions with specific evidence from the solution and evaluation specification
- Iterative refinement - Up to 3 debate rounds drive convergence on accurate scores
- Shared specification - Meta-judge runs once; all judges across all rounds share the same evaluation specification
Pattern: Debate-Based Evaluation
More from neolabhq/context-engineering-kit
sdd:plan
Refine, parallelize, and verify a draft task specification into a fully planned implementation-ready task
550sdd:implement
Implement a task with automated LLM-as-Judge verification for critical steps
525customaize-agent:prompt-engineering
Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.
512code-review:review-local-changes
Comprehensive review of local uncommitted changes using specialized agents with code improvement suggestions
511sdd:brainstorm
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
509sdd:add-task
creates draft task file in .specs/tasks/draft/ with original user intent
503