atai-newton-omega-nvidia-nemotron
Installation
SKILL.md
Newton Omega × NVIDIA Nemotron — Omega senses, Nemotron explains
Omega turns sensor windows into embeddings; a client-side KNN turns those into a verdict (healthy / fault, normal / attack, …). That verdict is accurate but mute. This skill adds NVIDIA Nemotron as the explanation layer: when Omega flags something, Nemotron reads the verdict and plain window statistics and writes what an operator needs — what changed, the likely cause, what to check.
sensor window ──► scale ──► Omega /query (one per channel) ──► KNN vs n-shot library ──► verdict + votes
│
window stats (+ healthy baseline or peer) ─────────────────────────┤
▼
NVIDIA Nemotron (chat/completions, JSON only)
│
validate ──► cache ──► UI
When to Apply
- An Omega + KNN pipeline already produces verdicts and you want operator-facing text: fault briefs, suggested actions, alert summaries.
- The user specifically wants NVIDIA Nemotron (hosted on build.nvidia.com) as the reasoning model.