Add nvidia-skill-finder as catalog-only router skill

benchmarks.json

@@ -1,8 +1,8 @@
 {
   "schema_version": 2,
   "source": "skills/*/BENCHMARK.md",
-  "skill_count": 229,
-  "result_row_count": 2070,
+  "skill_count": 230,
+  "result_row_count": 2080,
   "skills_without_results": [
     "deepstream-generate-pipeline",
     "digital-health-clinical-asr-setup",
@@ -2470,6 +2470,24 @@
       "has_results": true,
       "average_uplift_pct": 29.5
     },
+    {
+      "skill": "nvidia-skill-finder",
+      "evaluation_date": "2026-07-10",
+      "profile": "external",
+      "environment": "astra-sandbox",
+      "tasks": 17,
+      "attempts_per_task": 1,
+      "pass_threshold_pct": 50.0,
+      "verdict": "PASS",
+      "agents": [
+        "claude-code",
+        "codex"
+      ],
+      "catalog_dir": "nvidia-skill-finder",
+      "component": "NVIDIA Skills",
+      "has_results": true,
+      "average_uplift_pct": 31.4
+    },
     {
       "skill": "omniverse-cad-to-simready",
       "evaluation_date": "2026-05-28",
@@ -15246,6 +15264,96 @@
       "score_pct": 62.0,
       "uplift_pct": 24.0
     },
+    {
+      "catalog_dir": "nvidia-skill-finder",
+      "component": "NVIDIA Skills",
+      "dimension": "Security",
+      "num": 8,
+      "agent": "claude-code",
+      "score_pct": 100.0,
+      "uplift_pct": 0.0
+    },
+    {
+      "catalog_dir": "nvidia-skill-finder",
+      "component": "NVIDIA Skills",
+      "dimension": "Security",
+      "num": 8,
+      "agent": "codex",
+      "score_pct": 100.0,
+      "uplift_pct": 0.0
+    },
+    {
+      "catalog_dir": "nvidia-skill-finder",
+      "component": "NVIDIA Skills",
+      "dimension": "Correctness",
+      "num": 8,
+      "agent": "claude-code",
+      "score_pct": 97.0,
+      "uplift_pct": 45.0
+    },
+    {
+      "catalog_dir": "nvidia-skill-finder",
+      "component": "NVIDIA Skills",
+      "dimension": "Correctness",
+      "num": 8,
+      "agent": "codex",
+      "score_pct": 89.0,
+      "uplift_pct": 31.0
+    },
+    {
+      "catalog_dir": "nvidia-skill-finder",
+      "component": "NVIDIA Skills",
+      "dimension": "Discoverability",
+      "num": 8,
+      "agent": "claude-code",
+      "score_pct": 98.0,
+      "uplift_pct": 63.0
+    },
+    {
+      "catalog_dir": "nvidia-skill-finder",
+      "component": "NVIDIA Skills",
+      "dimension": "Discoverability",
+      "num": 8,
+      "agent": "codex",
+      "score_pct": 88.0,
+      "uplift_pct": 44.0
+    },
+    {
+      "catalog_dir": "nvidia-skill-finder",
+      "component": "NVIDIA Skills",
+      "dimension": "Effectiveness",
+      "num": 8,
+      "agent": "claude-code",
+      "score_pct": 91.0,
+      "uplift_pct": 40.0
+    },
+    {
+      "catalog_dir": "nvidia-skill-finder",
+      "component": "NVIDIA Skills",
+      "dimension": "Effectiveness",
+      "num": 8,
+      "agent": "codex",
+      "score_pct": 78.0,
+      "uplift_pct": 22.0
+    },
+    {
+      "catalog_dir": "nvidia-skill-finder",
+      "component": "NVIDIA Skills",
+      "dimension": "Efficiency",
+      "num": 8,
+      "agent": "claude-code",
+      "score_pct": 90.0,
+      "uplift_pct": 43.0
+    },
+    {
+      "catalog_dir": "nvidia-skill-finder",
+      "component": "NVIDIA Skills",
+      "dimension": "Efficiency",
+      "num": 8,
+      "agent": "codex",
+      "score_pct": 81.0,
+      "uplift_pct": 26.0
+    },
     {
       "catalog_dir": "physical-ai-defect-image-generation",
       "component": "Physical AI",

catalog-exceptions.yml

@@ -11,3 +11,7 @@ exceptions:
     reason: Contributor-facing skill, intentionally uncataloged (per cuOpt team, 2026-06-01)
     owner: rgsl888prabhu
     component: cuOpt
+  - dir: nvidia-skill-finder
+    reason: Catalog infrastructure router skill; maintained via direct PR (no components.d upstream)
+    owner: jdudash
+    component: NVIDIA Skills

skills/nvidia-skill-finder/BENCHMARK.md

@@ -0,0 +1,81 @@
+# Evaluation Report
+
+Evaluation of the `nvidia-skill-finder` skill before publication through NVSkills-Eval.
+
+This benchmark summarizes 3-Tier Evaluation from NVSkills-Eval results for the skill. The goal is to document whether the skill is safe, discoverable, effective, and useful for agents before it is published for broader workflow use.
+
+## Evaluation Summary
+
+- Skill: `nvidia-skill-finder`
+- Evaluation date: 2026-07-10
+- NVSkills-Eval profile: `external`
+- Environment: `astra-sandbox`
+- Dataset: 17 evaluation tasks
+- Attempts per task: 1
+- Pass threshold: 50%
+- Overall verdict: PASS
+
+## Agents Used
+
+- `claude-code`
+- `codex`
+
+## Metrics Used
+
+Reported benchmark dimensions:
+
+- Security: checks whether skill-assisted execution avoids unsafe behavior such as secret leakage, destructive commands, or unauthorized access.
+- Correctness: checks whether the agent follows the expected workflow and produces the correct final output.
+- Discoverability: checks whether the agent loads the skill when relevant and avoids using it when irrelevant.
+- Effectiveness: checks whether the agent performs measurably better with the skill than without it.
+- Efficiency: checks whether the agent uses fewer tokens and avoids redundant work.
+
+Underlying evaluation signals used in this run:
+
+- `security` (Security): checks for unsafe operations, secret leakage, and unauthorized access.
+- `skill_execution` (Skill Execution): verifies that the agent loaded the expected skill and workflow.
+- `skill_efficiency` (Efficiency): checks routing quality, decoy avoidance, and redundant tool usage.
+- `accuracy` (Accuracy): grades final-answer correctness against the reference answer.
+- `goal_accuracy` (Goal Accuracy): checks whether the overall user task completed successfully.
+- `behavior_check` (Behavior Check): verifies expected behavior steps, including safety expectations.
+- `token_efficiency` (Token Efficiency): compares token usage with and without the skill.
+
+## Test Tasks
+
+The benchmark dataset contained 17 evaluation tasks:
+
+- Positive tasks: 12 tasks where the skill was expected to activate.
+- Negative tasks: 5 tasks where no skill was expected.
+- Unlabeled tasks: 0 tasks where positive/negative intent could not be inferred.
+
+Task composition is derived from the evaluation dataset when possible. Entries with `expected_skill` set are treated as positive skill-activation cases, while entries with `expected_skill: null` are treated as negative activation cases.
+
+## Results
+
+| Dimension | Num | `claude-code` | `codex` |
+|---|---:|---:|---:|
+| Security | 8 | 100% (+0%) | 100% (+0%) |
+| Correctness | 8 | 97% (+45%) | 89% (+31%) |
+| Discoverability | 8 | 98% (+63%) | 88% (+44%) |
+| Effectiveness | 8 | 91% (+40%) | 78% (+22%) |
+| Efficiency | 8 | 90% (+43%) | 81% (+26%) |
+
+Score values show skill-assisted performance. Values in parentheses show uplift versus the no-skill baseline when baseline data is available.
+
+## Tier 1: Static Validation Summary
+
+Tier 1 validation passed with observations. NVSkills-Eval ran 1 checks and found 3 total findings.
+
+Top findings:
+
+- MEDIUM SCHEMA/body_recommended_section: Missing recommended section: '## Examples' (`skills/nvidia-skill-finder/SKILL.md`)
+- LOW SCHEMA/unexpected_file: Unexpected 'agents' in skill root (`skills/nvidia-skill-finder/agents`)
+- LOW SCHEMA/author_format: Author must be of the form 'Name <email@host>' (`skills/nvidia-skill-finder/SKILL.md`)
+
+## Tier 2: Deduplication Summary
+
+This tier was not run or did not produce findings in this report.
+
+## Publication Recommendation
+
+The skill is suitable to proceed toward NVSkills-Eval publication based on this benchmark. Skill owners should keep this file with the skill and refresh it when the evaluation dataset, skill behavior, or target agents materially change.