# grandjury

> grandjury — humanjudge-grandjury. Use this tool when you need to evaluate AI models with human judgment, leveraging 25,000+ blind reviews from verified reviewers to assess performance across various benchmarks. It provides a Python SDK interface for seamless integration, accepting AI model inputs and outputting human evaluation results. Ideal for use cases requiring objective, human-in-the-loop validation of AI model performance.

Canonical page: https://skillsregistry.net/skills/humanjudge-grandjury  
JSON: https://api.skillsregistry.net/v1/skills/humanjudge-grandjury

## Description

Pluralistic human evaluation infrastructure for AI in production

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** other
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](https://github.com/humanjudge/grandjury)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "humanjudge-grandjury"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/humanjudge-grandjury` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/humanjudge-grandjury/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt