archetypeai/agent-skills / skills/atai-newton-omega-nvidia-nemotron
atai-newton-omega-nvidia-nemotron
VerifiedPair Archetype AI's Omega encoder (`OmegaEncoder::omega_embeddings_1_4` over `/query`) with NVIDIA Nemotron on NVIDIA's hosted API (`integrate.api.nvidia.com`) — Omega + client-side KNN decide what state a sensor window is in, Nemotron explains it in operator language. Use this skill when the user wants an LLM to turn Omega/KNN verdicts into fault briefs, suggested operator actions, or alert summaries with NVIDIA Nemotron. Covers the "Omega senses, Nemotron explains" split (Nemotron gets verdicts + window statistics, never embeddings), NVIDIA key types and model retirement, turning Nemotron 3's reasoning off, JSON-only prompts with validation, peer/baseline comparison, caching, and two worked demos (SWaT operator suggestions, wind-turbine fault briefs). For the Omega call itself see `atai-newton-omega-model`; for data prep see `atai-newton-omega-model-data-prep`. Do NOT use for Newton's own text reasoning (that's `atai-newton-fusion-model`).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 13.5 KB |
| references/.env.example | other | 518 B |
| references/_common.py | script | 13.4 KB |
| references/check_nemotron.py | script | 3.9 KB |
| references/explain_knn.py | script | 4.8 KB |
| references/requirements.txt | manifest | 207 B |
| references/sample_data/README.md | markdown | 1.8 KB |
| references/sample_data/bearing_degraded.csv | other | 70.3 KB |
| references/sample_data/bearing_healthy.csv | other | 68.5 KB |
| references/sample_data/bearing_incoming.csv | other | 17.8 KB |
| tests/test_references.py | script | 9.7 KB |
references/requirements.txt
View on GitHub# Runtime dependencies for the reference scripts.
# pip install -r requirements.txt
# Nemotron calls use the standard library (urllib) — no OpenAI SDK needed.
archetypeai>=26.11.11.0
python-dotenv
numpy
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |