When you need to judge a solution fairly, this skill brings together multiple independent evaluators. They each review the solution, then debate their findings. The judges argue, defend their points, and adjust their scores. This process repeats until they all agree or reach a set limit. The result is a well-reasoned and balanced evaluation. Three judges work together to reduce bias. They use evidence from the solution to support their arguments. This method is much more reliable than a single person's judgment.
Global
mkdir -p ~/.claude/skills/judge-with-debateProject
mkdir -p .claude/skills/judge-with-debateSource Repository
Find Skillsvercel-labs/skills
Find and install the perfect skill to extend your AI agent
Microsoft Foundrymicrosoft/azure-skills
Build, deploy, and improve AI agents on Microsoft Foundry from start to finish
Azure Aimicrosoft/azure-skills
Search, transcribe, and analyze with Azure AI tools for smarter apps
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Build, deploy, and manage your Copilot SDK apps on Azure with ease
Triagemattpocock/skills
Triage issues with a state machine driven by clear roles and agent briefs
Handoffmattpocock/skills
Hand off your work to another AI agent with a clear summary
Image Editagentspace-so/runcomfy-agent-skills
Smart router picks the best AI model for your image editing needs
Agentspaceagentspace-so/skills
See your AI agent's live folder from any browser instantly