多
What is it?
使用多代理辩论和 LLM-as-Judge 模式的多视角评审系统，包含 3 个专业评判者、辩论轮次和共识构建。
How to use it?
安装技能后通过命令调用，3 个专业评判代理从不同视角评审，经多轮辩论达成共识结论。
Key Features
- 3 个专业评判者多视角审查
- 多代理辩论模式
- LLM-as-Judge 评估
- 迭代辩论轮次机制
- 共识构建和结论综合
Related Skills
More from AI & MLAgent Evaluation Framework
Comprehensive Claude Code agent evaluation framework with multi-dimensional scoring, LLM-as-Judge mode, and research-backed performance variance analysis
433NeoLabHQ
AI & ML
Developer Tools
Execute and Judge Loop
Single-task execution with LLM-as-Judge verification in an iterative loop, supporting auto-retry and strict orchestrator role separation
433NeoLabHQ
AI & ML
Developer Tools
LLM-as-Judge Evaluator
Standalone LLM-as-Judge evaluation tool with context isolation, Chain-of-Thought scoring, multi-dimensional weighted rubric, and evidence-backed assessments
433NeoLabHQ
AI & ML
Developer Tools