
from tao-skill-bank80
Deploy and manage network-specific TAO inference microservices across diverse compute platforms including Docker, Kubernetes, and Slurm.
This skill enables an agent to orchestrate the full lifecycle of TAO (Torch-Audio-Omniverse) inference microservices. It handles the complexity of mapping network architectures to specific container images, constructing job payloads, and managing the service registry to ensure predictable endpoints for inference requests.
Use this skill when a user wants to deploy a TAO model checkpoint for inference, start a new inference endpoint, or stop an existing microservice container. It is specifically designed for workflows requiring high-performance AI inference via microservices.
Designed for advanced agents capable of executing shell commands and managing containerized environments (e.g., Claude Code, Codex, or custom OpenClaw agents).
This skill has not been reviewed by our automated audit pipeline yet.