When you run multiple AI agents on the same task, you need a fair way to pick the best one. This tool scores and ranks every agent result. You can use a metric like execution time or accuracy. Or you can use an LLM judge that reads the outputs and decides the winner.
If your top agents are very close, a hybrid mode first checks the numbers then uses the LLM to break ties. After ranking, you can merge the winning agent into your project with one command.
Add Eval skill to your workflow
Global
mkdir -p ~/.claude/skills/evalProject
mkdir -p .claude/skills/evalSource Repository
More AI & Agent Building Claude Code Skills
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