# newhorse

> newhorse — xcrong-newhorse. Use this tool when you need to design, develop, and evaluate AI agents in a competitive environment, solving problems such as optimizing agent performance and comparing different AI models. The NewHorse platform takes in AI agent designs and outputs performance metrics and rankings, providing a standardized interface for testing and validation. It is ideal for use cases where AI agent development and comparison are crucial, such as research, innovation, and education.

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

## Description

NewHorse AI Agent Competition Platform.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-05-21

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** instructions
- **Runtime environment:** llm
- **Category:** ai-ml
- **Updated:** 2026-09-13

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/xcrong-newhorse)

## 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": "xcrong-newhorse"
    }
  }
}
```

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