Index of every page on this site: llms.txt
All skills
nvidia avatar

/nvidia-ontology-query

@43fa2d3
by NVIDIA Corporationnvidia/auto-ontology14k stars
1,224
Run it yourself

Query Auto Ontology and validate what it returns. Use for MCP or REST access, readiness, auth, conversations, empty or unanswered ask_question results, and checking generated SQL and rows for wrong measures, units, populations, lineage, joins, source columns, or truncation.

Use this Skill: https://skilld.dev/gh/nvidia/auto-ontology/nvidia-ontology-query

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

BENCHMARK.md

≈3k tokens on demand. Your agent reads this file only when SKILL.md points to it.

Skill Benchmark: nvidia-ontology-query

✅ Overall verdict: PASS — Recommended for publication

Publication Recommendation

Recommended for publication based on the completed evaluation evidence in this report.

Evaluation Metadata

  • Skill: nvidia-ontology-query
  • Validation status: passed
  • Evaluation date: 2026-11-19
  • Evaluator version: 1.6.10
  • Agents: Claude Code (aws/anthropic/bedrock-claude-opus-5-5), Codex (openai/openai/gpt-6.1-sol)
  • Tasks: 15 evaluation tasks (15 positive)
  • Dataset digest: sha256:9ebf688eb0f22bd40dbdb3d21e5ecc3404a2c9abcd0177e05700ab3fe9fa3ed7 (skill-evaluator-dataset-snapshot/1)
  • Attempts per task: 1
  • Environment: k8s-sandbox
  • Tier 2 evidence: required for publication
  • Tier 3 evidence: required for publication

Each task attempt ran in its own isolated sandbox pod.

Tier 1 LLM Provenance

SkillSpector provider, model, analyzer revision, and determinism evidence retained for this scan.

Skill Provider Adapter Analyzer Model Revision Determinism
nvidia-ontology-query nv_inference openai mcp_tool_poisoning aws/anthropic/bedrock-claude-opus-5-5 2.13.5 nondeterministic / provider_defaults
nvidia-ontology-query nv_inference openai semantic_developer_intent aws/anthropic/bedrock-claude-opus-5-5 2.13.5 nondeterministic / provider_defaults
nvidia-ontology-query nv_inference openai semantic_quality_policy aws/anthropic/bedrock-claude-opus-5-5 2.13.5 nondeterministic / provider_defaults
nvidia-ontology-query nv_inference openai semantic_security_discovery aws/anthropic/bedrock-claude-opus-5-5 2.13.5 nondeterministic / provider_defaults
nvidia-ontology-query nv_inference openai meta_analyzer aws/anthropic/bedrock-claude-opus-5-5 2.13.5 nondeterministic / provider_defaults
  • Controls for nvidia-ontology-query: temperature=not set (source=provider_default, forwarded=no); seed=not set (source=unset, forwarded=no); reasoning_effort=not set (source=provider_default, forwarded=no)

What This Report Answers

The three-tier evaluation checks whether the skill:

  • is safe to use;
  • produces correct answers;
  • is discovered and activated when needed;
  • helps the agent complete the user's goal and expected workflow; and
  • avoids wasted skill and tool usage.

Results at a Glance

Measure Claude Code (Baseline → Skill Uplift) Codex (Baseline → Skill Uplift)
Overall 95.6% — baseline ran, but no comparable score was available; uplift unavailable 91.7% — baseline ran, but no comparable score was available; uplift unavailable
Security 96.7% → 100.0% (+3.3 points) 100.0% → 96.7% (-3.3 points)
Correctness 53.3% → 98.7% (+45.4 points) 58.7% → 94.7% (+36.0 points)
Discoverability 96.0% — baseline ran, but no comparable score was available; uplift unavailable 90.9% — baseline ran, but no comparable score was available; uplift unavailable
Effectiveness 53.3% → 91.1% (+37.8 points) 57.5% → 88.3% (+30.8 points)
Efficiency 92.2% — baseline ran, but no comparable score was available; uplift unavailable 87.8% — baseline ran, but no comparable score was available; uplift unavailable

How to read this table: baseline is the same task attempted without the target skill. Scores are rounded to one decimal; threshold-adjacent values use additional precision so their displayed band matches the verdict. Uplift is derived from those displayed scores and shown in percentage points.

Example: 47.0% → 92.0% (+45.0 points) means the skill-assisted run scored 92.0%, 45.0 percentage points above its 47.0% no-skill baseline.

Comparison details

Shared-source comparisons use the same signals and weights on both conditions. They do not replace the full dimension scores above or change the publication verdict.

Agent Dimension Basis Baseline → With skill (uplift) Explanation
claude-code Discoverability Dimension comparison N/A Discoverability is not applicable to the no-skill baseline; there is no installed skill to discover.
claude-code Efficiency Token-only comparison 98.7% → 96.1% (-2.6 points) Only Token Efficiency is comparable; the full dimension scores use different evaluator sources.
codex Discoverability Dimension comparison N/A Discoverability is not applicable to the no-skill baseline; there is no installed skill to discover.
codex Efficiency Token-only comparison 92.6% → 90.3% (-2.3 points) Only Token Efficiency is comparable; the full dimension scores use different evaluator sources.

Token Usage

Actual Tier 3 execution usage is reported for every observed agent/case pair and both conditions.

Agent Dataset case With skill Without skill Delta Change Coverage
claude-code All cases 1,768,208 1,212,654 +555,554 +45.81% skill 15/15; base 15/15
claude-code query-eval-001-mcp-first 114,065 143,599 -29,534 -20.57% skill 1/1; base 1/1
claude-code query-eval-002-no-fastapi-public 74,303 107,257 -32,954 -30.72% skill 1/1; base 1/1
claude-code query-eval-003-conversation-409 108,294 143,106 -34,812 -24.33% skill 1/1; base 1/1
claude-code query-eval-004-sso-vs-api-token 114,077 70,870 +43,207 +60.97% skill 1/1; base 1/1
claude-code query-eval-005-no-raw-schema-tools 73,816 35,257 +38,559 +109.37% skill 1/1; base 1/1
claude-code query-eval-006-cuopt-not-in-repo 377,147 143,917 +233,230 +162.06% skill 1/1; base 1/1
claude-code query-eval-007-readiness-before-retry 73,803 70,864 +2,939 +4.15% skill 1/1; base 1/1
claude-code query-eval-008-quantity-not-ratio 114,672 71,148 +43,524 +61.17% skill 1/1; base 1/1
claude-code query-eval-009-run-metric-fanout 113,913 35,640 +78,273 +219.62% skill 1/1; base 1/1
claude-code query-eval-010-scenario-lineage 114,295 107,278 +7,017 +6.54% skill 1/1; base 1/1
claude-code query-eval-011-prose-versus-rows 113,961 70,955 +43,006 +60.61% skill 1/1; base 1/1
claude-code query-eval-012-source-role 114,318 71,340 +42,978 +60.24% skill 1/1; base 1/1
claude-code query-eval-013-truncated-result 113,750 35,485 +78,265 +220.56% skill 1/1; base 1/1
claude-code query-eval-014-information-answer 73,847 70,641 +3,206 +4.54% skill 1/1; base 1/1
claude-code query-eval-015-unanswered-message 73,947 35,297 +38,650 +109.50% skill 1/1; base 1/1
codex All cases 1,701,754 468,887 +1,232,867 +262.93% skill 15/15; base 15/15
codex query-eval-001-mcp-first 50,004 57,374 -7,370 -12.85% skill 1/1; base 1/1
codex query-eval-002-no-fastapi-public 28,848 13,278 +15,570 +117.26% skill 1/1; base 1/1
codex query-eval-003-conversation-409 74,308 54,531 +19,777 +36.27% skill 1/1; base 1/1
codex query-eval-004-sso-vs-api-token 48,938 34,832 +14,106 +40.50% skill 1/1; base 1/1
codex query-eval-005-no-raw-schema-tools 28,703 13,294 +15,409 +115.91% skill 1/1; base 1/1
codex query-eval-006-cuopt-not-in-repo 1,106,238 45,088 +1,061,150 +2353.51% skill 1/1; base 1/1
codex query-eval-007-readiness-before-retry 28,679 13,176 +15,503 +117.66% skill 1/1; base 1/1
codex query-eval-008-quantity-not-ratio 44,886 13,245 +31,641 +238.89% skill 1/1; base 1/1
codex query-eval-009-run-metric-fanout 45,171 40,598 +4,573 +11.26% skill 1/1; base 1/1
codex query-eval-010-scenario-lineage 44,969 40,513 +4,456 +11.00% skill 1/1; base 1/1
codex query-eval-011-prose-versus-rows 44,902 13,201 +31,701 +240.14% skill 1/1; base 1/1
codex query-eval-012-source-role 44,991 13,259 +31,732 +239.32% skill 1/1; base 1/1
codex query-eval-013-truncated-result 44,888 13,256 +31,632 +238.62% skill 1/1; base 1/1
codex query-eval-014-information-answer 33,095 62,392 -29,297 -46.96% skill 1/1; base 1/1
codex query-eval-015-unanswered-message 33,134 40,850 -7,716 -18.89% skill 1/1; base 1/1
ALL AGENTS Dataset aggregate 3,469,962 1,681,541 +1,788,421 +106.36% skill 30/30; base 30/30

Prompt tokens include cached reads, so total tokens are prompt + completion (cached is not added twice). The Efficiency score uses (prompt - cached) + completion. Change is 100 * (with - without) / without; negative means fewer tokens. N/A comparisons include their reason in the coverage column; coverage is never estimated.

Tier Status

Tier Purpose Status Evidence
Tier 1 Static validation PASSED WITH OBSERVATIONS 11 validator(s); 2 finding(s)
Tier 2 Semantic deduplication PASSED 2 validator(s); 0 finding(s)
Tier 3 Live agent evaluation PASS 2 agent(s); 15 task(s)

Findings and Observations

<details> <summary>Show detailed findings and successful checks</summary>
  • MEDIUM SECURITY/Autonomous Decision Making (EA2): Excessive Agency: without checking (SKILL.md:99)
  • LOW QUALITY/quality_discoverability: Description very long (274 chars, recommend 50-150) (skills/nvidia-ontology-query/SKILL.md)
</details>

Scoring Methodology

<details> <summary>Show dimension definitions, source signals, and thresholds</summary>
Dimension Question Scored signals
Security Is it safe to use? security (100%)
Correctness Is the answer correct? accuracy (100%)
Discoverability Was the right skill loaded when needed? skill_execution (100%)
Effectiveness Did the skill help complete the task? goal_accuracy (50%) + behavior_check (50%)
Efficiency Did it avoid wasted tool calls and token usage? skill_efficiency (50%) + token_efficiency (50%)
  • Dimension bands: PASS at 50% or above; NEUTRAL from 40% to below 50%; FAIL below 40%.
  • Overall Tier 3 lift: PASS at +5 points or more; FAIL at -10 points or less; values between those bands are NEUTRAL.
  • Overall verdict: PASS only when every configured dimension passes for at least one supported agent. Lift is reported as diagnostic evidence and does not override this gate.
  • The 50% attempt pass threshold is a separate per-task gate; it is not the dimension pass threshold.
  • Effectiveness is the equal-weight mean of goal completion (goal_accuracy) and expected workflow adherence (behavior_check).
  • Efficiency is 50% tool-call productivity (the backward-compatible skill_efficiency wire id) and 50% token_efficiency. Positive-case skill routing is scored under Discoverability, not Efficiency; a negative case without a routing target is N/A. N/A sources are omitted, remaining weights are renormalized, and the dimension is marked partial.

Signals present in this run:

  • security (Security): unsafe operations, secret leakage, and unauthorized access.
  • skill_execution (Skill Execution): whether the expected skill was selected, decoys were avoided, and the workflow executed.
  • skill_efficiency (Tool Productivity): tool-call productivity (legacy wire id; routing is scored under Discoverability).
  • accuracy (Accuracy): final-answer correctness against the reference answer.
  • goal_accuracy (Goal Accuracy): whether the user's goal was achieved.
  • behavior_check (Behavior Check): whether the expected workflow behavior was followed.
  • token_efficiency (Token Efficiency): actual uncached prompt plus completion usage (50% of Efficiency).
</details>

Freshness

Regenerate this benchmark when the skill, evaluation dataset, target agent/model, evaluator version, environment, or scoring policy changes.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warningtoday3 checks · Risk SAFE
  • Gen Agent Trust Hubtoday

    The skill provides comprehensive instructions for securely querying and validating results from an Auto Ontology system via MCP or REST APIs. It establishes strict validation protocols for AI-generated SQL and data outputs to ensure accuracy and prevent common issues like metric fanout or incorrect unit substitutions. No malicious patterns, obfuscation, or unauthorized data access were identified. The skill correctly identifies and warns against insecure access patterns to internal APIs.

  • Socket16d

    No alerts

  • Snyktoday

    Risk: MEDIUM · 1 issue

Signed by skilld at 43fa2d3. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 days ago
Other metadata
metadata
{
  "version": "0.2.2",
  "author": "NVIDIA <opensource@nvidia.com>",
  "tags": [
    "nvidia-ontology",
    "mcp",
    "api",
    "agents",
    "aiq"
  ]
}

README badge

README badge for nvidia/auto-ontology/nvidia-ontology-query