[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ACNHD900HWCGYCRX4P7CNB":3,"skill-same:01M6ACNHD900HWCGYCRX4P7CNB":92},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":24,"linkOnly":25,"markdownContent":26,"markdownBody":27,"frontMatter":28,"refName":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":6,"updatedAt":43,"install":44,"resources":57},"01M6ACNHD900HWCGYCRX4P7CNB","dynamo-interconnect-check",null,"Validate that a Dynamo deployment's NIXL\u002FUCX\u002FNCCL interconnect is ready for disaggregated serving over RDMA\u002FNVLink. Use after recipe-runner brings a deployment up (especially disagg\u002Fmulti-node) to confirm the KV transport is correct; use troubleshoot for diagnosing already-failed pods.","openai\u002Fplugins","openai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F14957082?v=4","01M6AC29YGCR4S2NTJFV0G8B81","OpenAI","01M6AC38CEN570NMR96RNGD2NK",7942,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnvidia\u002Fskills\u002Fdynamo-interconnect-check\u002FSKILL.md",[],[19,20,21,22,23],"dynamo interconnect check","troubleshoot","validate","deployment","validation","2026-11-10 10:12:30",false,"---\nname: dynamo-interconnect-check\ndescription: Validate that a Dynamo deployment's NIXL\u002FUCX\u002FNCCL interconnect is ready for disaggregated serving over RDMA\u002FNVLink. Use after recipe-runner brings a deployment up (especially disagg\u002Fmulti-node) to confirm the KV transport is correct; use troubleshoot for diagnosing already-failed pods.\nlicense: Apache-2.0\nmetadata:\n  author: Dan Gil \u003Cdagil@nvidia.com>\n  tags:\n    - dynamo\n    - nixl\n    - rdma\n    - disagg\n    - validation\n---\n\n# Dynamo Interconnect Check\n\n\u003C!--\nSPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.\nSPDX-License-Identifier: CC-BY-4.0\n-->\n\n## Purpose\n\nConfirm that the transport disaggregated serving depends on actually works. A\ndeployment can pass an endpoint smoke test while disagg is silently wrong: if\nNIXL\u002FUCX cannot reach the peer worker over RDMA or NVLink, KV transfer falls\nback to a slow or broken path. Catch that with read-only checks before trusting\na disagg deployment or its benchmark numbers.\n\nThis skill is read-only. It never mutates the cluster and never prints secrets.\n\n## Prerequisites\n\n- Python 3.10+ on the operator machine.\n- `kubectl exec` access to a worker pod in the target Dynamo deployment.\n- Read access to the recipe directory (`recipes\u002F\u003Cmodel>\u002F\u003Cframework>\u002F\u003Cmode>`).\n- For node-capability checks: tools like `ibstat`, `nvidia-smi`, `lsmod` available in the worker pod image (missing tools are reported as `skipped`, not failures).\n\n## When To Use\n\n- After `dynamo-recipe-runner` deploys a **disagg** or multi-node recipe.\n- Before reporting disagg throughput\u002Flatency, so numbers reflect the real\n  transport.\n- When agg works but disagg is slow, hangs, or returns wrong output and you\n  suspect the fabric rather than the model.\n\nFor diagnosing pods that are already crashing or unschedulable, use\n`dynamo-troubleshoot` first.\n\n## Instructions\n\n### 1. Check Transport Env Vars On The Recipe\n\n```bash\npython3 scripts\u002Fcheck_interconnect.py env recipes\u002F\u003Cmodel>\u002F\u003Cframework>\u002F\u003Cmode>\n```\n\nReports which NIXL\u002FUCX\u002FNCCL transport variables are set and flags\ndisagg-critical ones (e.g. `UCX_TLS`, `UCX_NET_DEVICES`, `NCCL_IB_HCA`) that are\nabsent. Missing here is only a warning — they may be baked into the image — so\nconfirm with the node and NIXL checks. See\n`references\u002Finterconnect-env-vars.md` for what each variable does.\n\n### 2. Check Node Capabilities\n\nLocally on a GPU node, or inside a running worker pod:\n\n```bash\npython3 scripts\u002Fcheck_interconnect.py node \\\n  --namespace \"${NAMESPACE}\" --pod \u003Cworker-pod>\n```\n\nProbes (read-only) for: InfiniBand devices and Active links, GPUDirect RDMA\n(`nvidia_peermem`), GDRCopy, and NVLink in the GPU topology. Missing tools are\nreported as `skipped`, not failures.\n\n### 3. Validate NIXL Reachability\n\n```bash\npython3 scripts\u002Fcheck_interconnect.py nixl \\\n  --namespace \"${NAMESPACE}\" --pod \u003Cworker-pod>\n```\n\nLooks for NIXL test tooling in the pod and surfaces the exact next step to run a\npairwise prefill↔decode transfer test. A full cross-pod transfer test requires\ntwo scheduled GPU pods on the fabric.\n\n## Available Scripts\n\n| Script | Purpose | Arguments |\n|---|---|---|\n| `scripts\u002Fcheck_interconnect.py env` | Inspect NIXL\u002FUCX\u002FNCCL env vars on a recipe | positional recipe path |\n| `scripts\u002Fcheck_interconnect.py node` | Probe InfiniBand, GPUDirect RDMA, GDRCopy, NVLink on a node or pod | `--namespace`, `--pod` |\n| `scripts\u002Fcheck_interconnect.py nixl` | Surface NIXL transfer-test readiness for a pod | `--namespace`, `--pod` |\n\nInvoke via the agentskills.io `run_script()` protocol:\n\n```python\nrun_script(\"scripts\u002Fcheck_interconnect.py\", args=[\"env\", \"recipes\u002Fqwen3-coder-480b\u002Fsglang\u002Fdisagg\"])\nrun_script(\"scripts\u002Fcheck_interconnect.py\", args=[\"node\", \"--namespace\", \"dynamo-demo\", \"--pod\", \"qwen-worker-0\"])\n```\n\n## Examples\n\nVerify a disagg recipe's transport env shape before deploy:\n\n```bash\npython3 scripts\u002Fcheck_interconnect.py env recipes\u002Fqwen3-coder-480b\u002Fsglang\u002Fdisagg\n```\n\nAfter deploy, validate a worker pod's fabric:\n\n```bash\npython3 scripts\u002Fcheck_interconnect.py node \\\n  --namespace dynamo-demo --pod qwen-worker-0\npython3 scripts\u002Fcheck_interconnect.py nixl \\\n  --namespace dynamo-demo --pod qwen-worker-0\n```\n\nEquivalent through the agent protocol:\n\n```python\nrun_script(\"scripts\u002Fcheck_interconnect.py\", args=[\"nixl\", \"--namespace\", \"dynamo-demo\", \"--pod\", \"qwen-worker-0\"])\n```\n\n## Output Contract\n\nEach check returns `ok` \u002F `warn` \u002F `fail` \u002F `skipped` with a one-line detail,\nplus a rolled-up verdict on disagg transport readiness. Report:\n\n- transport env vars present vs. disagg-critical ones missing\n- RDMA \u002F GPUDirect \u002F NVLink capability status\n- whether NIXL reachability was validated, and the next command if not\n- a clear statement of whether disagg can be trusted, or what to fix first\n\n## Limitations\n\n- Read-only fabric probe; does not run a full pairwise NIXL transfer (requires two scheduled GPU pods and the in-pod NIXL test tools).\n- `skipped` results for missing tools (`ibstat`, `nvidia-smi`, `lsmod`) are inconclusive, not a pass.\n- Env-var check inspects the recipe text; values injected at runtime via initContainers or operator-applied envs are not detected.\n- Single-node agg deployments do not exercise the transport — this skill is for disagg \u002F multi-node validation.\n\n## Troubleshooting\n\n| Symptom | Likely cause | Next step |\n|---|---|---|\n| `env` reports all critical vars missing | Vars baked into image or injected by operator | Run the `node` check inside the worker pod to verify actual env |\n| `node` reports no Active IB link | Fabric down or HCA not provisioned to the node | Contact cluster admin; verify `kubectl describe node` shows `nvidia.com\u002Fgpu` and IB labels |\n| `nvidia_peermem` missing | GPUDirect RDMA module not loaded | Ask cluster admin to load `nvidia-peermem`; without it, NIXL falls back to staged copies |\n| `nixl` finds no test tools | Worker image lacks NIXL test harness | Use a NIXL-enabled image or run the standalone transfer test from a debug pod |\n\n## Benchmark\n\nSee `BENCHMARK.md` for the NVCARPS-EVAL performance report (auto-generated by the NVSkills CI pipeline). To refresh, re-run `\u002Fnvskills-ci` on an upstream PR touching this skill.\n\n## References\n\n- `references\u002Finterconnect-env-vars.md` — NIXL\u002FUCX\u002FNCCL env var catalog and IB\n  capability checklist.\n- Use `scripts\u002Fcheck_interconnect.py` for all read-only checks.\n","# Dynamo Interconnect Check\n\n\u003C!--\nSPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.\nSPDX-License-Identifier: CC-BY-4.0\n-->\n\n## Purpose\n\nConfirm that the transport disaggregated serving depends on actually works. A\ndeployment can pass an endpoint smoke test while disagg is silently wrong: if\nNIXL\u002FUCX cannot reach the peer worker over RDMA or NVLink, KV transfer falls\nback to a slow or broken path. Catch that with read-only checks before trusting\na disagg deployment or its benchmark numbers.\n\nThis skill is read-only. It never mutates the cluster and never prints secrets.\n\n## Prerequisites\n\n- Python 3.10+ on the operator machine.\n- `kubectl exec` access to a worker pod in the target Dynamo deployment.\n- Read access to the recipe directory (`recipes\u002F\u003Cmodel>\u002F\u003Cframework>\u002F\u003Cmode>`).\n- For node-capability checks: tools like `ibstat`, `nvidia-smi`, `lsmod` available in the worker pod image (missing tools are reported as `skipped`, not failures).\n\n## When To Use\n\n- After `dynamo-recipe-runner` deploys a **disagg** or multi-node recipe.\n- Before reporting disagg throughput\u002Flatency, so numbers reflect the real\n  transport.\n- When agg works but disagg is slow, hangs, or returns wrong output and you\n  suspect the fabric rather than the model.\n\nFor diagnosing pods that are already crashing or unschedulable, use\n`dynamo-troubleshoot` first.\n\n## Instructions\n\n### 1. Check Transport Env Vars On The Recipe\n\n```bash\npython3 scripts\u002Fcheck_interconnect.py env recipes\u002F\u003Cmodel>\u002F\u003Cframework>\u002F\u003Cmode>\n```\n\nReports which NIXL\u002FUCX\u002FNCCL transport variables are set and flags\ndisagg-critical ones (e.g. `UCX_TLS`, `UCX_NET_DEVICES`, `NCCL_IB_HCA`) that are\nabsent. Missing here is only a warning — they may be baked into the image — so\nconfirm with the node and NIXL checks. See\n`references\u002Finterconnect-env-vars.md` for what each variable does.\n\n### 2. Check Node Capabilities\n\nLocally on a GPU node, or inside a running worker pod:\n\n```bash\npython3 scripts\u002Fcheck_interconnect.py node \\\n  --namespace \"${NAMESPACE}\" --pod \u003Cworker-pod>\n```\n\nProbes (read-only) for: InfiniBand devices and Active links, GPUDirect RDMA\n(`nvidia_peermem`), GDRCopy, and NVLink in the GPU topology. Missing tools are\nreported as `skipped`, not failures.\n\n### 3. Validate NIXL Reachability\n\n```bash\npython3 scripts\u002Fcheck_interconnect.py nixl \\\n  --namespace \"${NAMESPACE}\" --pod \u003Cworker-pod>\n```\n\nLooks for NIXL test tooling in the pod and surfaces the exact next step to run a\npairwise prefill↔decode transfer test. A full cross-pod transfer test requires\ntwo scheduled GPU pods on the fabric.\n\n## Available Scripts\n\n| Script | Purpose | Arguments |\n|---|---|---|\n| `scripts\u002Fcheck_interconnect.py env` | Inspect NIXL\u002FUCX\u002FNCCL env vars on a recipe | positional recipe path |\n| `scripts\u002Fcheck_interconnect.py node` | Probe InfiniBand, GPUDirect RDMA, GDRCopy, NVLink on a node or pod | `--namespace`, `--pod` |\n| `scripts\u002Fcheck_interconnect.py nixl` | Surface NIXL transfer-test readiness for a pod | `--namespace`, `--pod` |\n\nInvoke via the agentskills.io `run_script()` protocol:\n\n```python\nrun_script(\"scripts\u002Fcheck_interconnect.py\", args=[\"env\", \"recipes\u002Fqwen3-coder-480b\u002Fsglang\u002Fdisagg\"])\nrun_script(\"scripts\u002Fcheck_interconnect.py\", args=[\"node\", \"--namespace\", \"dynamo-demo\", \"--pod\", \"qwen-worker-0\"])\n```\n\n## Examples\n\nVerify a disagg recipe's transport env shape before deploy:\n\n```bash\npython3 scripts\u002Fcheck_interconnect.py env recipes\u002Fqwen3-coder-480b\u002Fsglang\u002Fdisagg\n```\n\nAfter deploy, validate a worker pod's fabric:\n\n```bash\npython3 scripts\u002Fcheck_interconnect.py node \\\n  --namespace dynamo-demo --pod qwen-worker-0\npython3 scripts\u002Fcheck_interconnect.py nixl \\\n  --namespace dynamo-demo --pod qwen-worker-0\n```\n\nEquivalent through the agent protocol:\n\n```python\nrun_script(\"scripts\u002Fcheck_interconnect.py\", args=[\"nixl\", \"--namespace\", \"dynamo-demo\", \"--pod\", \"qwen-worker-0\"])\n```\n\n## Output Contract\n\nEach check returns `ok` \u002F `warn` \u002F `fail` \u002F `skipped` with a one-line detail,\nplus a rolled-up verdict on disagg transport readiness. Report:\n\n- transport env vars present vs. disagg-critical ones missing\n- RDMA \u002F GPUDirect \u002F NVLink capability status\n- whether NIXL reachability was validated, and the next command if not\n- a clear statement of whether disagg can be trusted, or what to fix first\n\n## Limitations\n\n- Read-only fabric probe; does not run a full pairwise NIXL transfer (requires two scheduled GPU pods and the in-pod NIXL test tools).\n- `skipped` results for missing tools (`ibstat`, `nvidia-smi`, `lsmod`) are inconclusive, not a pass.\n- Env-var check inspects the recipe text; values injected at runtime via initContainers or operator-applied envs are not detected.\n- Single-node agg deployments do not exercise the transport — this skill is for disagg \u002F multi-node validation.\n\n## Troubleshooting\n\n| Symptom | Likely cause | Next step |\n|---|---|---|\n| `env` reports all critical vars missing | Vars baked into image or injected by operator | Run the `node` check inside the worker pod to verify actual env |\n| `node` reports no Active IB link | Fabric down or HCA not provisioned to the node | Contact cluster admin; verify `kubectl describe node` shows `nvidia.com\u002Fgpu` and IB labels |\n| `nvidia_peermem` missing | GPUDirect RDMA module not loaded | Ask cluster admin to load `nvidia-peermem`; without it, NIXL falls back to staged copies |\n| `nixl` finds no test tools | Worker image lacks NIXL test harness | Use a NIXL-enabled image or run the standalone transfer test from a debug pod |\n\n## Benchmark\n\nSee `BENCHMARK.md` for the NVCARPS-EVAL performance report (auto-generated by the NVSkills CI pipeline). To refresh, re-run `\u002Fnvskills-ci` on an upstream PR touching this skill.\n\n## References\n\n- `references\u002Finterconnect-env-vars.md` — NIXL\u002FUCX\u002FNCCL env var catalog and IB\n  capability checklist.\n- Use `scripts\u002Fcheck_interconnect.py` for all read-only checks.\n",{"name":5,"license":15,"metadata":29,"description":7},{"tags":30,"author":35},[31,32,33,34,23],"dynamo","nixl","rdma","disagg","Dan Gil \u003Cdagil@nvidia.com>","main","0722921d5542fc593105c27bd52630babd8b8c2a","plugins\u002Fnvidia\u002Fskills\u002Fdynamo-interconnect-check",1025,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","https:\u002F\u002Fgithub.com\u002Fopenai","https:\u002F\u002Fopenai.com\u002F","2026-11-14 08:11:13",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add openai\u002Fplugins --skill dynamo-interconnect-check",{"tool":50,"command":51},"bunx","bunx skills add openai\u002Fplugins --skill dynamo-interconnect-check",{"tool":53,"command":54},"pnpm","pnpm dlx skills add openai\u002Fplugins --skill dynamo-interconnect-check","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnvidia\u002Fskills\u002Fdynamo-interconnect-check\u002FSKILL.md",true,[58,64,68,72,76,82,86],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"agents\u002Fopenai.yaml","REFERENCE","参考文档",365,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnvidia\u002Fskills\u002Fdynamo-interconnect-check\u002Fagents\u002Fopenai.yaml",{"path":65,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":66,"sourceHtmlUrl":67},"BENCHMARK.md",2924,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnvidia\u002Fskills\u002Fdynamo-interconnect-check\u002FBENCHMARK.md",{"path":69,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":70,"sourceHtmlUrl":71},"evals\u002Fevals.json",3203,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnvidia\u002Fskills\u002Fdynamo-interconnect-check\u002Fevals\u002Fevals.json",{"path":73,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Finterconnect-env-vars.md",3580,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnvidia\u002Fskills\u002Fdynamo-interconnect-check\u002Freferences\u002Finterconnect-env-vars.md",{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"scripts\u002Fcheck_interconnect.py","SCRIPT","脚本",13099,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnvidia\u002Fskills\u002Fdynamo-interconnect-check\u002Fscripts\u002Fcheck_interconnect.py",{"path":83,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":84,"sourceHtmlUrl":85},"skill-card.md",2512,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnvidia\u002Fskills\u002Fdynamo-interconnect-check\u002Fskill-card.md",{"path":87,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":90,"sourceHtmlUrl":91},"skill.oms.sig","OTHER","其他",5093,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnvidia\u002Fskills\u002Fdynamo-interconnect-check\u002Fskill.oms.sig",[93,115,128,145,169,182],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":97,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":105,"publishedAt":24},"01M6ACYN431ER9AFG508JJH3VT","supabase-postgres-best-practices","Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.","MIT","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fsupabase\u002Fskills\u002Fsupabase-postgres-best-practices\u002FSKILL.md",[100],{"categoryNo":101,"categoryName":102,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",[106,107,108,109,110,111,112,113,114],"best practices","supabase postgres best practices","writing","performance","sql","code","database","metrics","examples",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":97,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":124,"publishedAt":24},"01M6ACQRGGJYVNDPQWB9XGWRNZ","minimal-skill","Minimal example skill for plugin-eval tests. Use when the user wants a compact demonstration of a well-structured skill.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fplugin-eval\u002Ffixtures\u002Fminimal-skill\u002FSKILL.md",[121],{"categoryNo":122,"categoryName":123,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000023","Skill与智能体开发",[125,126,127],"minimal skill","example skill","plugin",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":24},"01M6ACQ406M83341YPKPEXBXDZ","physical-ai-neural-reconstruction","Router for NVIDIA NuRec\u002FNRE: USDZ rendering, NCore conversion, 3DGS, gRPC sensor sim, PhysicalAI HF datasets. Do NOT use for SimReady or infra setup.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnvidia\u002Fskills\u002Fphysical-ai-neural-reconstruction\u002FSKILL.md",[],[135,136,137,138,139,140,141,142,143,144],"physical ai neural reconstruction","https","python","github","docker","setup","toolkit","gpu","index","grpc",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":154,"publishedAt":24},"01M6ACPVRFPVATXD7H38Z56QC5","physical-ai-infrastructure-setup-and-resilient-scaling","Use when the user wants to set up, scale, validate, or harden NVIDIA physical AI infrastructure for synthetic data generation workflows across local MicroK8s or Azure AKS, including Kubernetes clusters, inference endpoint deployment, OSMO deployment, workload submission readiness, and infrastructure failure recovery. Trigger keywords: physical ai infrastructure, resilient scaling, SDG infrastructure, microk8s, azure aks, NVCF deployment, NIM Operator, OSMO deploy, workflow scaling. Don't trigger for: OSMO log summarization or workload-only operations unless infrastructure setup, scaling, validation, or recovery is requested.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnvidia\u002Fskills\u002Fphysical-ai-infrastructure-setup-and-resilient-scaling\u002FSKILL.md",[151],{"categoryNo":152,"categoryName":153,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000011","运维与部署",[155,140,156,23,157,22,158,159,160,161,162,163,164,165,166,21,167,168],"physical ai infrastructure setup and resilient scaling","infrastructure","terraform","synthetic data","workload","ml","cli","kubernetes","inference","workflow","workflows","component","deploy","azure",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":176,"publishedAt":24},"01M6ACPG9JPDSS6MMKVKR3P56E","omniverse-usd-performance-tuning","Top-level workflow skill for USD performance diagnosis and optimization. Use for slow loading, high memory, low FPS, or 'optimize my scene' requests; delegates auth\u002Fruntime setup to Phase 0 owners.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnvidia\u002Fskills\u002Fomniverse-usd-performance-tuning\u002FSKILL.md",[175],{"categoryNo":122,"categoryName":123,"taxonomyType":103,"taxonomyTypeDesc":104},[177,109,178,137,179,180,164,140,160,181],"omniverse usd performance tuning","auth","memory","triage","authentication",{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":189,"publishedAt":24},"01M6ACP73X9YS5Y730C2WE58YF","omniverse-realtime-viewer","Use as the top-level router for Omniverse Realtime Viewer USD app requests and focused viewer reference documents.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnvidia\u002Fskills\u002Fomniverse-realtime-viewer\u002FSKILL.md",[188],{"categoryNo":122,"categoryName":123,"taxonomyType":103,"taxonomyTypeDesc":104},[190,191,137,164,192,193,194,160,22,195,142,196],"omniverse realtime viewer","realtime","electron","react","documents","cpp","typescript"]