Agent skill · nvidia
nvidia-ontology-query
Query Auto Ontology and validate generated SQL, rows, and answers. Use for MCP or REST access, readiness, authentication, conversations, and grounded questions.
What it needs
About 3k tokens when loaded.
What this skill does
<!-- SPDX-FileCopyrightText: Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. SPDX-License-Identifier: Apache-2.0 --> Auto Ontology grounded queries Purpose Query the current Auto Ontology implementation from an agent without prescribing a harness, SDK, or LangGraph template. Typed workflow artifacts, statuses, gates, and handoffs are in runtime-contract.yaml. Prerequisites Use a running Auto Ontology deployment and an authenticated MCP or REST client. If Auto Ontology is not running, use nvidia-ontology-setup first. Limitations This skill reads and validates answers. It does not expose FastAPI directly, write semantic definitions, publish governed results, or provide a raw-schema browser. Hand mutations and publication to nvidia-ontology-management. Instructions 1. Call readiness before asking a question. 2. Discover terms and confirm answerability through the semantic layer. 3. Ask through MCP, or use the authenticated Next.js REST gateway as fallback. 4. Validate material intent, SQL, rows, truncation, and prose before presenting a claim-bearing answer. Prefer MCP for reads When the harness speaks MCP, use it. The handshake tool list is the live source of truth (mcp/autoontologymcp/tools.py). Do not copy a tool table into the session; if the handshake and this skill disagree, trust the handshake. Sequence (the server also advertises this so models do not jump straight to askquestion): 1. checkreadiness — compiled semantic layer and a live DB connection. 2. searchterms — what the nouns mean here. 3. checkanswerable — cheap coverage check. 4. askquestion — full text-to-SQL; tens of seconds; answer + SQL + rows (capped at 100 rows, with rowcount / truncated). 5. For a claim-bearing answer, validate material intent, generated SQL, returned rows, truncation, and prose using query-validation.md. Everything on MCP reads. There is no MCP tool for raw databases, schemas, or columns on purpose. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills nvidia/nvidia-ontology-query