llm-as-judge

3 plugins use this word, from 2 publishers.

mizan-evalbyghchinoy
Run Mizan evaluations from an agent: score a single response or compare two responses against a metric template via the…
2 skills
eval-ladderbyjrichlen
Design and audit an agent system's eval ladder — the cheapest rung that catches each regression, the blind spot beside…
1 skill
mizan-mcpbyghchinoy
Expose the Mizan eval engine to agents and MCP clients as callable tools via the `mizan mcp` server. Registers a local…
1 skill