# judge-mcp

> judge-mcp — mikelninh-judge-mcp. Use this tool when you need to evaluate and refine artifacts against predefined standards, as it scores submissions against rubrics, provides failure explanations, and iterates until a quality threshold is met, accepting git-based inputs and producing scored outputs with actionable feedback. It solves problems of inconsistent quality and manual evaluation, streamlining the review process. Ideal for use in collaborative development and quality control contexts.

Canonical page: https://skillsregistry.net/skills/mikelninh-judge-mcp  
JSON: https://api.skillsregistry.net/v1/skills/mikelninh-judge-mcp

## Description

MCP for MCPs — score artifacts against rubrics, explain failures and iterate until a defined quality threshold.

## Trust

- **Trust score (0–1):** 0.92
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/mikelninh/judge-mcp)

## 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": "mikelninh-judge-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mikelninh-judge-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mikelninh-judge-mcp/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