Isaac sim

Skill a5c-ai/babysitter/library/specializations/robotics-simulation/skills/isaac-sim

Specialized skill for NVIDIA Isaac Sim photorealistic simulation and synthetic data generationFrom its SKILL.md

Install

npx -y skills add a5c-ai/babysitter --skill isaac-sim

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

1.7 KB, 284 tokens by cl100k_base, as published. Nobody here has run it

NVIDIA Isaac Sim Skill

Overview

Expert skill for NVIDIA Isaac Sim photorealistic simulation, Omniverse integration, and synthetic data generation using Replicator.

Capabilities

Import and convert URDF to USD format
Create photorealistic environments with RTX ray tracing
Configure PhysX physics simulation
Implement Replicator synthetic data generation
Apply domain randomization (lighting, textures, poses)
Generate ground truth annotations (segmentation, depth, bounding boxes)
Configure ROS/ROS2 bridge for Isaac Sim
Set up multi-GPU distributed simulation
Create Isaac Sim extensions and workflows
Export datasets in standard formats (COCO, KITTI)

Target Processes

isaac-sim-photorealistic.js
synthetic-data-pipeline.js
digital-twin-development.js
rl-robot-control.js

Dependencies

NVIDIA Isaac Sim
Omniverse
NVIDIA GPU with RTX
USD/USDA libraries

Usage Context

This skill is invoked when processes require photorealistic simulation environments, synthetic data generation with domain randomization, or high-fidelity physics simulation using NVIDIA's simulation stack.

Output Artifacts

USD scene files
Replicator configuration scripts
Synthetic datasets (images, annotations, ground truth)
Domain randomization configurations
ROS bridge configurations

What ships with it: 1 file

828 B alongside SKILL.md

README.md828 B