# groundtruth-geo

> groundtruth-geo — sulmusic2-star-groundtruth-geo. Use this tool when you need to verify the accuracy of US property facts, such as parcel boundaries and ownership information, to identify and correct errors in machine learning models. The groundtruth-geo tool provides a deterministic and reproducible benchmark, allowing you to grade and evaluate model performance on specific questions. It is particularly useful when working with frontier models that require precise and reliable data to improve their accuracy.

Canonical page: https://skillsregistry.net/skills/sulmusic2-star-groundtruth-geo  
JSON: https://api.skillsregistry.net/v1/skills/sulmusic2-star-groundtruth-geo

## Description

Deterministic, government-cited, reproducible benchmark of parcel-precise US property facts — on the exact questions frontier models fail. Benchmark + grader + MCP server.

## Trust

- **Trust score (0–1):** 0.87
- **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/sulmusic2-star/groundtruth-geo)

## 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": "sulmusic2-star-groundtruth-geo"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sulmusic2-star-groundtruth-geo` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sulmusic2-star-groundtruth-geo/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