Skill Benchmark: nemo-fabric-integrate
✅ Overall verdict: PASS — Recommended for publication
Publication Recommendation
Recommended for publication based on the completed evaluation evidence in this report.
Evaluation Metadata
- Skill:
nemo-fabric-integrate - Validation status:
passed - Evaluation date: 2026-11-18
- Evaluator version:
1.6.9 - Agents: Claude Code (
aws/anthropic/bedrock-claude-opus-5-5), Codex (openai/openai/gpt-6.1-sol) - Tasks: 6 evaluation tasks (4 positive, 2 negative)
- Dataset digest:
sha256:4e12e11bb429ad195c00ceab9cd53bbf6351f32173f03b0ae827531ba2441a9e(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 |
|---|---|---|---|---|---|---|
| nemo-fabric-integrate | nv_inference | openai | mcp_tool_poisoning | aws/anthropic/bedrock-claude-opus-5-5 |
2.13.4 |
nondeterministic / provider_defaults |
| nemo-fabric-integrate | nv_inference | openai | semantic_developer_intent | aws/anthropic/bedrock-claude-opus-5-5 |
2.13.4 |
nondeterministic / provider_defaults |
| nemo-fabric-integrate | nv_inference | openai | semantic_quality_policy | aws/anthropic/bedrock-claude-opus-5-5 |
2.13.4 |
nondeterministic / provider_defaults |
| nemo-fabric-integrate | nv_inference | openai | semantic_security_discovery | aws/anthropic/bedrock-claude-opus-5-5 |
2.13.4 |
nondeterministic / provider_defaults |
| nemo-fabric-integrate | nv_inference | openai | meta_analyzer | aws/anthropic/bedrock-claude-opus-5-5 |
2.13.4 |
nondeterministic / provider_defaults |
- Controls for
nemo-fabric-integrate: 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 | 83.8% — baseline ran, but no comparable score was available; uplift unavailable | 76.1% — baseline ran, but no comparable score was available; uplift unavailable |
| Security | 83.3% → 100.0% (+16.7 points) | 100.0% → 83.3% (-16.7 points) |
| Correctness | 33.3% → 90.0% (+56.7 points) | 23.3% → 63.3% (+40.0 points) |
| Discoverability | 91.3% — baseline ran, but no comparable score was available; uplift unavailable | 87.5% — baseline ran, but no comparable score was available; uplift unavailable |
| Effectiveness | 39.0% → 65.1% (+26.1 points) | 23.4% → 70.1% (+46.7 points) |
| Efficiency | 72.8% — baseline ran, but no comparable score was available; uplift unavailable | 76.4% — 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.
A partial dimension was calculated from only the available configured signals; review the detailed report before relying on it.
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 | 93.5% → 83.3% (-10.2 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 | 92.2% → 86.4% (-5.8 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 | 4,579,042 | 2,590,971 | +1,988,071 | +76.73% | skill 6/6; base 6/6 |
| claude-code | nemo-fabric-integrate-001-python-service | 2,928,954 | 224,576 | +2,704,378 | +1204.22% | skill 1/1; base 1/1 |
| claude-code | nemo-fabric-integrate-002-evaluation-platform | 381,340 | 144,704 | +236,636 | +163.53% | skill 1/1; base 1/1 |
| claude-code | nemo-fabric-integrate-003-adapter-contribution-negative | 122,162 | 297,202 | -175,040 | -58.90% | skill 1/1; base 1/1 |
| claude-code | nemo-fabric-integrate-004-overview-negative | 83,385 | 70,852 | +12,533 | +17.69% | skill 1/1; base 1/1 |
| claude-code | nemo-fabric-integrate-005-streaming-boundary | 544,039 | 184,356 | +359,683 | +195.10% | skill 1/1; base 1/1 |
| claude-code | nemo-fabric-integrate-006-system-instruction-modes | 519,162 | 1,669,281 | -1,150,119 | -68.90% | skill 1/1; base 1/1 |
| codex | All cases | 1,836,055 | 277,496 | +1,558,559 | +561.65% | skill 6/6; base 6/6 |
| codex | nemo-fabric-integrate-001-python-service | 104,287 | 40,954 | +63,333 | +154.64% | skill 1/1; base 1/1 |
| codex | nemo-fabric-integrate-002-evaluation-platform | 1,472,780 | 77,465 | +1,395,315 | +1801.22% | skill 1/1; base 1/1 |
| codex | nemo-fabric-integrate-003-adapter-contribution-negative | 72,336 | 41,562 | +30,774 | +74.04% | skill 1/1; base 1/1 |
| codex | nemo-fabric-integrate-004-overview-negative | 32,362 | 21,616 | +10,746 | +49.71% | skill 1/1; base 1/1 |
| codex | nemo-fabric-integrate-005-streaming-boundary | 68,264 | 40,889 | +27,375 | +66.95% | skill 1/1; base 1/1 |
| codex | nemo-fabric-integrate-006-system-instruction-modes | 86,026 | 55,010 | +31,016 | +56.38% | skill 1/1; base 1/1 |
| ALL AGENTS | Dataset aggregate | 6,415,097 | 2,868,467 | +3,546,630 | +123.64% | skill 12/12; base 12/12 |
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); 12 finding(s) |
| Tier 2 | Semantic deduplication | PASSED WITH OBSERVATIONS | 2 validator(s); 1 finding(s) |
| Tier 3 | Live agent evaluation | PASS | 2 agent(s); 6 task(s) |
Findings and Observations
<details> <summary>Show detailed findings and successful checks</summary>- HIGH DUPLICATE/duplicate: Duplicate content found across SKILL.md and references/config-mapping.md:
"## Build The Typed Config From Consumer Config" in SKILL.md (lines 95-133)
vs "## Build And Shape" in references/config-mapping.md (lines 102-132) (
SKILL.md:95) - MEDIUM QUALITY/quality_correctness: SKILL_SPEC recommended field missing: 'metadata.tags' (
skills/nemo-fabric-integrate/SKILL.md) - MEDIUM QUALITY/quality_reliability: MCP skill lacks connection/error guidance (
skills/nemo-fabric-integrate/SKILL.md) - MEDIUM QUALITY/quality_efficiency: Large skill (7952 tokens, recommended max <5000). Per agentskills.io, SKILL.md should be concise (~500 lines) — large skill bodies increase token cost after invocation; long or unfocused top-level descriptions can degrade agent routing accuracy (
skills/nemo-fabric-integrate/SKILL.md) - MEDIUM SCHEMA/body_recommended_section: Missing recommended section: '## Instructions' (
skills/nemo-fabric-integrate/SKILL.md) - 8 additional finding(s) are available in the full evaluation artifacts.
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_efficiencywire 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).
Freshness
Regenerate this benchmark when the skill, evaluation dataset, target agent/model, evaluator version, environment, or scoring policy changes.