chore: sync skills (CUDA-Q,DeepStream,Megatron-Bridge,Megatron-Core,Model-Optimizer,NeMo AutoModel,NeMo Evaluator,NeMo Gym,NeMo-Evaluator,NeMo-Evaluator-Launcher,NeMo-Gym,NeMo-RL,NemoClaw,Nemotron Voice Agent,RAG Blueprint,TensorRT-LLM,TileGym,Video Search and Summarization,cuOpt,cuopt,nemotron-voice-agent,rag,video-search-and-summarization)

README.md

@@ -97,9 +97,10 @@ For non-interactive installs, global installs, agent-specific installs, updates,
 <!-- skills-table-start -->
 | Product | Description | Skills | Catalog | Source | Version |
 |---------|-------------|:------:|---------|--------|---------|
-| **AIQ** | NVIDIA AI-Q Blueprint - deploy local AI-Q services and run shallow or deep research workflows as agent skills. | 2 | [`skills/aiq-research/`](skills/aiq-research) | [Source](https://github.com/NVIDIA-AI-Blueprints/aiq/tree/develop/skills/aiq-research) | [`66b009e`](https://github.com/NVIDIA-AI-Blueprints/aiq/commit/66b009e3b28219eb2a09910c347d84c0675c2028) · 2026-05-27 |
+| **AIQ** | NVIDIA AI-Q Blueprint - deploy local AI-Q services and run shallow or deep research workflows as agent skills. | 2 | [`skills/aiq-research/`](skills/aiq-research) | [Source](https://github.com/NVIDIA-AI-Blueprints/aiq/tree/develop/skills/aiq-research) | [`bdf53c5`](https://github.com/NVIDIA-AI-Blueprints/aiq/commit/bdf53c56354e707c05d865861eb1588c64623d25) · 2026-05-28 |
 | **cuOpt** | GPU-accelerated optimization — vehicle routing, linear programming, quadratic programming, installation, server deployment, and developer tools. | 10 | [`skills/cuopt/`](skills/cuopt) | [Source](https://github.com/NVIDIA/cuopt/tree/main/skills) | [`8e534f1`](https://github.com/NVIDIA/cuopt/commit/8e534f19c7f0ba20ba74196480f8a2b2f3fbe278) · 2026-05-28 |
-| **DeepStream** | Agentic skills for guided DeepStream development. | 2 | [`skills/deepstream/`](skills/deepstream) | [Source](https://github.com/NVIDIA-AI-IOT/DeepStream_Coding_Agent/tree/main/skills) | [`3daf16a`](https://github.com/NVIDIA-AI-IOT/DeepStream_Coding_Agent/commit/3daf16ae5168dd685608bb929fb4f5513f308045) · 2026-05-28 |
+| **DeepStream** | Agentic skills for guided DeepStream development. | 2 | [`skills/deepstream-dev/`](skills/deepstream-dev) | [Source](https://github.com/NVIDIA-AI-IOT/DeepStream_Coding_Agent/tree/main/skills/deepstream-dev) | [`3daf16a`](https://github.com/NVIDIA-AI-IOT/DeepStream_Coding_Agent/commit/3daf16ae5168dd685608bb929fb4f5513f308045) · 2026-05-28 |
+| **NeMo AutoModel** | NeMo AutoModel - PyTorch-native distributed training for LLMs/VLMs with Hugging Face support, recipes, launchers, and validation workflows. | 4 | [`skills/nemo-automodel-distributed-training/`](skills/nemo-automodel-distributed-training) | [Source](https://github.com/NVIDIA-NeMo/Automodel/tree/main/skills/nemo-automodel-distributed-training) | [`8f57d10`](https://github.com/NVIDIA-NeMo/Automodel/commit/8f57d1030750a1f2e156f86e728f029998d7db71) · 2026-05-28 |
 | **Skill Card Generator** | Reads an agent skill's source files and produces a skill card plus a review table. Use when a skill directory exists and a governance card needs to be generated or updated. | 1 | [`skills/skill-card-generator/`](skills/skill-card-generator) | [Source](https://github.com/NVIDIA/Trustworthy-AI/tree/main/skills/skill-card-generator) | [`09b0d6b`](https://github.com/NVIDIA/Trustworthy-AI/commit/09b0d6b03ee587cc8672ad3133a4eb84aeadbd2a) · 2026-05-28 |
 <!-- skills-table-end -->
 
@@ -115,6 +116,7 @@ For skill-related issues, feature requests, new skill ideas, discussions, and co
 | **AIQ** | [Issues](https://github.com/NVIDIA-AI-Blueprints/aiq/issues) | [Discussions](https://github.com/NVIDIA-AI-Blueprints/aiq/discussions) | [Contributing](https://github.com/NVIDIA-AI-Blueprints/aiq/blob/develop/CONTRIBUTING.md) | [Security](https://github.com/NVIDIA-AI-Blueprints/aiq/blob/develop/SECURITY.md) |
 | **cuOpt** | [Issues](https://github.com/NVIDIA/cuopt/issues) | [Discussions](https://github.com/NVIDIA/cuopt/discussions) | [Contributing](https://github.com/NVIDIA/cuopt/blob/main/CONTRIBUTING.md) | [Security](https://github.com/NVIDIA/cuopt/blob/main/SECURITY.md) |
 | **DeepStream** | [Issues](https://github.com/NVIDIA-AI-IOT/DeepStream_Coding_Agent/issues) | [Discussions](https://github.com/NVIDIA-AI-IOT/DeepStream_Coding_Agent/discussions) | [Contributing](https://github.com/NVIDIA-AI-IOT/DeepStream_Coding_Agent/blob/main/CONTRIBUTING.md) | [Security](https://github.com/NVIDIA-AI-IOT/DeepStream_Coding_Agent/blob/main/SECURITY.md) |
+| **NeMo AutoModel** | [Issues](https://github.com/NVIDIA-NeMo/Automodel/issues) | [Discussions](https://github.com/NVIDIA-NeMo/Automodel/discussions) | [Contributing](https://github.com/NVIDIA-NeMo/Automodel/blob/main/CONTRIBUTING.md) | [Security](https://github.com/NVIDIA-NeMo/Automodel/blob/main/SECURITY.md) |
 | **Skill Card Generator** | [Issues](https://github.com/NVIDIA/Trustworthy-AI/issues) | [Discussions](https://github.com/NVIDIA/Trustworthy-AI/discussions) | [Contributing](https://github.com/NVIDIA/Trustworthy-AI/blob/main/CONTRIBUTING.md) | [Security](https://github.com/NVIDIA/Trustworthy-AI/blob/main/SECURITY.md) |
 <!-- help-table-end -->
 

skills/deepstream-dev/.claude-plugin/plugin.json

@@ -0,0 +1,6 @@
+{
+  "name": "deepstream-dev",
+  "description": "NVIDIA DeepStream SDK 9.0 development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.",
+  "author": "NVIDIA CORPORATION",
+  "skills": "./"
+}

skills/deepstream-dev/BENCHMARK.md

@@ -0,0 +1,111 @@
+# Evaluation Report
+
+Evaluation of the `deepstream-dev` 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: `deepstream-dev`
+- Evaluation date: 2026-05-28
+- NVSkills-Eval profile: `external`
+- Environment: `local`
+- Dataset: 7 evaluation tasks
+- Attempts per task: 2
+- Pass threshold: 50%
+- Overall verdict: FAIL
+
+## 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:
+
+- `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 7 evaluation tasks:
+
+- Positive tasks: 5 tasks where the skill was expected to activate.
+- Negative tasks: 2 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 | 74% (+9%) | 57% (-2%) |
+| Correctness | 8 | 94% (+6%) | 88% (+9%) |
+| Discoverability | 8 | 86% (+11%) | 76% (+9%) |
+| Effectiveness | 8 | 81% (+6%) | 78% (+9%) |
+| Efficiency | 8 | 72% (+12%) | 64% (+9%) |
+
+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 9 checks and found 34 total findings.
+
+Top findings:
+
+- MEDIUM PII/gps_coordinates: GPS coordinates (location information) (`references/service_maker_api.md:804`)
+- MEDIUM PII/gps_coordinates: GPS coordinates (location information) (`references/service_maker_api.md:827`)
+- MEDIUM PII/gps_coordinates: GPS coordinates (location information) (`references/service_maker_api.md:829`)
+- MEDIUM PII/gps_coordinates: GPS coordinates (location information) (`references/service_maker_api.md:1279`)
+- MEDIUM PII/gps_coordinates: GPS coordinates (location information) (`references/use_cases_pipelines.md:842`)
+
+## Tier 2: Deduplication Summary
+
+Tier 2 validation reported findings. NVSkills-Eval ran 2 checks and found 34 total findings.
+
+Top findings:
+
+- HIGH DUPLICATE/duplicate: Duplicate content found within references/metamux_config.md:
+  "# default pts-tolerance is 60 ms." in references/metamux_config.md (lines 67-72)
+  vs "# default pts-tolerance is 60 ms." in references/metamux_config.md (lines 125-130) (`references/metamux_config.md:67`)
+- HIGH DUPLICATE/duplicate: Duplicate content found across references/buffer_apis.md and references/kafka_messaging.md and references/service_maker_api.md and references/use_cases_pipelines.md and references/utilities_config.md:
+  "### Pattern 3: Selective Frame Capture" in references/buffer_apis.md (lines 1198-1199)
+  vs "### Pattern 5: Frame Analysis and Logging" in references/buffer_apis.md (lines 1339-1340)
+  vs "#### Example 2: Pipeline with Both Kafka and Display (Using Tee)" in references/kafka_messaging.md (lines 167-168)
+  vs "#### Custom Kafka Producer Probe" in references/kafka_messaging.md (lines 581-582)
+  vs "# Enable tensor output in nvinfer" in references/service_maker_api.md (lines 1329-1333)
+  vs "#### Approach 3: Custom Postprocessing with Tensor Metadata" in references/use_cases_pipelines.md (lines 837-841)
+  vs "### Pattern 3: Custom Postprocessing" in references/utilities_config.md (lines 1275-1279) (`references/buffer_apis.md:1198`)
+- HIGH DUPLICATE/duplicate: Duplicate content found across references/buffer_apis.md and references/kafka_messaging.md and references/use_cases_pipelines.md and references/utilities_config.md:
+  "# from multiprocessing import Queue  # Use this for MULTIPROCESSING!" in references/buffer_apis.md (lines 1059-1063)
+  vs "### Pattern 3: Selective Frame Capture" in references/buffer_apis.md (lines 1195-1197)
+  vs "### Pattern 5: Frame Analysis and Logging" in references/buffer_apis.md (lines 1336-1338)
+  vs "#### Example 2: Pipeline with Both Kafka and Display (Using Tee)" in references/kafka_messaging.md (lines 162-166)
+  vs "#### Custom Kafka Producer Probe" in references/kafka_messaging.md (lines 576-580)
+  vs "#### Approach 3: Custom Postprocessing with Tensor Metadata" in references/use_cases_pipelines.md (lines 832-836)
+  vs "### Pattern 3: Custom Postprocessing" in references/utilities_config.md (lines 1272-1274) (`references/buffer_apis.md:1059`)
+- HIGH DUPLICATE/duplicate: Duplicate content found within references/utilities_config.md:
+  "### Pattern 1: Load and Use Source Configuration" in references/utilities_config.md (lines 1107-1109)
+  vs "### Pattern 1: Load and Use Source Configuration" in references/utilities_config.md (lines 1127-1128)
+  vs "### Pattern 1: Load and Use Source Configuration" in references/utilities_config.md (lines 1142-1143) (`references/utilities_config.md:1107`)
+- HIGH DUPLICATE/duplicate: Duplicate content found within references/metamux_config.md:
+  "# mux all source if don't set it." in references/metamux_config.md (lines 74-78)
+  vs "# mux all source if don't set it." in references/metamux_config.md (lines 132-136) (`references/metamux_config.md:74`)
+
+## Publication Recommendation
+
+The skill should be reviewed before NVSkills-Eval publication. Skill owners should address the findings above and rerun NVSkills-Eval to refresh this benchmark.