ghchinoy/mizan-eval
v0.1.0Apache-2.0
Run Mizan evaluations from an agent: score a single response or compare two responses against a metric template via the mizan CLI, reasoning over the -o json result. Use when you need to evaluate an asset/response against guidance and explain the verdict.
What this package declares
The file a client reads when it loads this plugin, exactly as this revision carries it.
plugin.json
{
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
"name": "mizan-eval",
"version": "0.1.0",
"description": "Run Mizan evaluations from an agent: score a single response or compare two responses against a metric template via the mizan CLI, reasoning over the -o json result. Use when you need to evaluate an asset/response against guidance and explain the verdict.",
"author": {
"name": "ghchinoy",
"url": "https://github.com/ghchinoy"
},
"homepage": "https://github.com/ghchinoy/mizan/tree/main/plugins/mizan-eval",
"repository": "https://github.com/ghchinoy/mizan",
"license": "Apache-2.0",
"keywords": [
"mizan",
"evaluation",
"llm-as-judge",
"pairwise",
"rubric",
"vertex-ai",
"gen-ai-evaluation",
"cli"
]
}