coach-nemoclaw-hermes

Coordinates multi-agent tasks between auditor and executor across isolated sandbox environments.

86|42|Updated May 6, 2026
One-click install
npx skills add https://github.com/NVIDIA/nemoclaw-community --skill coach-nemoclaw-hermes
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: coach-nemoclaw-hermes
Source: https://github.com/NVIDIA/nemoclaw-community/tree/main/examples/demos/field/blender-omniverse-dgx-station/codex-skills/coach-nemoclaw-hermes
Command: npx skills add https://github.com/NVIDIA/nemoclaw-community --skill coach-nemoclaw-hermes

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the challenge of managing complex, multi-agent workflows between a high-level auditor (Codex) and a specialized execution agent (Hermes) within constrained sandbox environments.

Core Features & Use Cases

  • Boundary Management: Enforces strict separation between host-level tasks and sandbox-contained execution to ensure system security.
  • Task Delegation: Enables Codex to delegate specialized Blender, OVRTX, and OVPhysX operations to Hermes while maintaining oversight.
  • Artifact Validation: Provides a structured framework for milestone-based reporting, artifact hashing, and independent verification of generated assets.

Quick Start

Use the coach-nemoclaw-hermes skill to delegate the current Blender rendering task to the Hermes agent while ensuring all output artifacts are validated against the host sandbox.

Frequently Asked Questions about coach-nemoclaw-hermes

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I orchestrate multi-agent workflows for Blender rendering tasks in a sandbox?

To orchestrate multi-agent workflows for Blender rendering tasks in a sandbox, this skill coordinates task delegation between a supervisory auditor and a runtime execution agent. It enforces strict filesystem boundaries to securely manage operations.

What is multi-agent task delegation in isolated sandbox environments?

Multi-agent task delegation in isolated sandbox environments is a coordination process where a supervisory auditor delegates specialized execution tasks to a runtime agent. This mechanism ensures system security by enforcing strict separation between host tasks and sandbox execution.

Can I use this to manage Omniverse and USD-based simulation tasks?

Yes, you can use this skill to manage Omniverse and USD-based simulation tasks. It coordinates complex workflows by delegating specialized Omniverse and PhysX operations to the execution agent while maintaining supervisory oversight.

How do I validate generated artifacts and ensure asset integrity during agent orchestration?

To validate generated artifacts and ensure asset integrity during agent orchestration, this framework provides a structured system for milestone-based reporting and artifact hashing. This enables independent verification of all generated assets.

Does this agent orchestration framework enforce filesystem boundaries for Blender operations?

Yes, this agent orchestration framework enforces strict filesystem boundaries for Blender operations. It ensures strict adherence to boundary rules, maintaining clear separation between host-level tasks and sandbox-contained execution.