tongsim

🥈Silver

TongSIM is a high-fidelity platform for training and testing embodied agents using Unreal Engine and Python SDK. It benefits operations teams by enabling realistic simulations for agent development. It connects to workflows involving agent training, testing, and deployment.

16290Updated 1mo ago

Intermediate30min to implementautomation

Saves ~240 min per use

Quick InstallView Source

git clone https://github.com/bigai-ai/tongsim.git

Works with:

Claude

Overview

About This Skill

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/bigai-ai/tongsim

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Create a training scenario for a robotic agent in a [WAREHOUSE] environment. The agent should be able to navigate through [NUMBER] aisles, identify [NUMBER] types of products, and place them in the correct [LOCATION] based on [CRITERIA]. Include potential obstacles and how the agent should handle them.

Example Output

# Training Scenario for Warehouse Robotic Agent

## Environment
- **Warehouse Layout**: 10 aisles, each 50 meters long
- **Products**: 50 types, varying in size and weight
- **Locations**: 3 designated zones (Heavy, Fragile, Standard)

## Tasks
1. **Navigation**: Agent must traverse all aisles without collision
2. **Identification**: Agent must correctly identify products using [CRITERIA]
3. **Placement**: Agent must place products in correct zone based on [CRITERIA]

## Obstacles
- **Moving Obstacles**: Forklifts and human workers
- **Static Obstacles**: Pallets and boxes on the floor
- **Handling**: Agent must reroute or pause if obstacle is encountered

## Success Metrics
- **Accuracy**: 95% or higher in product identification and placement
- **Efficiency**: Complete all tasks within 2 hours
- **Safety**: No collisions or damages reported