# poolhall

> poolhall — gqy20-poolhall. Use this tool when you need to simulate real-world physics and imperfections in AI interactions, particularly in scenarios requiring hand-eye coordination and dexterity. PoolHall solves problems of oversimplification in AI training by introducing a deterministic physics engine and hand model, providing a more realistic and challenging environment. It takes in AI agent inputs and outputs benchmarked performance metrics through the MCP Server interface.

Canonical page: https://skillsregistry.net/skills/gqy20-poolhall  
JSON: https://api.skillsregistry.net/v1/skills/gqy20-poolhall

## Description

PoolHall · 台球厅 —— 让每个 AI 智能体拥有一双不完美的手。确定性物理引擎 + Hand Model 手感注入 + MCP Server，Agent 知行曲线 Benchmark。

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/gqy20/poolhall)

## 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": "gqy20-poolhall"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/gqy20-poolhall` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/gqy20-poolhall/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