# medatarun

> medatarun — medatarun-medatarun. Use this tool when you need to create a unified and executable domain model that eliminates ambiguity and ensures accuracy across humans, systems, and AI agents. Medatarun takes in a domain model as input and outputs a shared, executable, and documented model that serves as a single ground truth. It is ideal for use cases where governance overhead, re-work, and approximation hinder productivity, and integrates with git for version control.

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

## Description

Domain models documentation and governance. A live reference for humans, tools and AI agents collaboration on data meaning.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-08-28

## Facts

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

## Source

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

## 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": "medatarun-medatarun"
    }
  }
}
```

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