[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-nvidia-k8s-launch-kit-clean":3,"mdc--7ny5fa-key":31,"related-org-nvidia-k8s-launch-kit-clean":734,"related-repo-nvidia-k8s-launch-kit-clean":893},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":20,"repoUrl":21,"updatedAt":22,"license":23,"forks":24,"topics":25,"repo":26,"sourceUrl":29,"mdContent":30},"k8s-launch-kit-clean","remove NVIDIA Network Operator from Kubernetes","Remove an NVIDIA Network Operator deployment from a Kubernetes cluster with l8k clean. Use when the user explicitly asks to uninstall, tear down, remove, reset, or clean a Network Operator installation, delete its custom resources, or keep the Helm chart while clearing Network Operator CRs.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},"nvidia","NVIDIA","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fnvidia.png",[12,16,17],{"name":13,"slug":14,"type":15},"Deployment","deployment","tag",{"name":9,"slug":8,"type":15},{"name":18,"slug":19,"type":15},"Kubernetes","kubernetes",14,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002Fk8s-launch-kit","2026-08-31T09:19:10.855889",null,4,[],{"repoUrl":21,"stars":20,"forks":24,"topics":27,"description":28},[],"K8s Launch Kit (l8k) is a CLI tool for deploying and managing NVIDIA cloud-native solutions on Kubernetes. The tool helps provide flexible deployment workflows for optimal network performance with SR-IOV, RDMA, and other networking technologies.","https:\u002F\u002Fgithub.com\u002FNVIDIA\u002Fk8s-launch-kit\u002Ftree\u002FHEAD\u002Fskills\u002Fk8s-launch-kit-clean","---\nname: k8s-launch-kit-clean\ndescription: \"Remove an NVIDIA Network Operator deployment from a Kubernetes cluster with l8k clean. Use when the user explicitly asks to uninstall, tear down, remove, reset, or clean a Network Operator installation, delete its custom resources, or keep the Helm chart while clearing Network Operator CRs.\"\n---\n\n# Clean a Network Operator Deployment\n\nRead `k8s-launch-kit-shared` first for binary discovery, JSON output, and error\nhandling.\n\n## Safety Boundary\n\nTreat cleanup as an irreversible live-cluster mutation. Require explicit user\nauthority to remove the deployment. Do not infer cleanup authority from a\nrequest to inspect, validate, troubleshoot, or explain the command.\n\nBefore running it:\n\n1. Resolve the intended kubeconfig and show its current context.\n2. Determine the intended Network Operator namespace.\n3. Explain that all namespaced custom resources in that namespace and every\n   known cluster-scoped Network Operator CR will be deleted.\n4. Confirm whether the Helm release should be uninstalled or retained.\n\nUse read-only checks when the target is not already explicit:\n\n```bash\nkubectl --kubeconfig \u003CPATH> config current-context\nhelm --kubeconfig \u003CPATH> list --all-namespaces --filter '^network-operator$'\n```\n\nStop and ask for direction if the kubeconfig, cluster, namespace, or Helm\nretention choice remains ambiguous.\n\n## Run Cleanup\n\nAn AI agent uses JSON mode after the user authorizes the exact target:\n\n```bash\nl8k clean \\\n  --kubeconfig \u003CPATH> \\\n  --network-operator-namespace \u003CNAMESPACE> \\\n  --output json 2>\u002Fdev\u002Fnull | jq .\n```\n\nOmit `--network-operator-namespace` only when the user expects l8k to resolve\nit from `--user-config`, `.\u002Fcluster-config.yaml`, an explicit `--config-dir`,\nor the `nvidia-network-operator` default. l8k does not trust in-cluster objects\nto select a destructive cleanup target.\n\nTo retain the installed release and its chart-managed resources:\n\n```bash\nl8k clean \\\n  --kubeconfig \u003CPATH> \\\n  --network-operator-namespace \u003CNAMESPACE> \\\n  --keep-helm-chart \\\n  --output json 2>\u002Fdev\u002Fnull | jq .\n```\n\nJSON mode auto-confirms. Do not invoke it until the read-only target checks and\nauthorization are complete. `l8k clean` has no dry-run mode.\n\n## Deletion Semantics\n\nThe command:\n\n- Deletes every namespaced custom-resource instance in the resolved operator\n  namespace.\n- Deletes all `HostDeviceNetwork`, `IPoIBNetwork`, `MacvlanNetwork`,\n  `NicNodePolicy`, and `NicClusterPolicy` instances cluster-wide.\n- Sends deletion requests to the complete namespaced and cluster-scoped set\n  before monitoring any CR for finalizer completion, then uses the same\n  delete-all-then-wait ordering for re-sweeps.\n- Keeps controllers installed until CR deletion and finalizers complete.\n- Uninstalls the `network-operator` Helm release last unless\n  `--keep-helm-chart` is set.\n- Preserves the namespace, CRDs, Secrets not owned by Helm, local files, and\n  namespaced custom resources elsewhere. Helm metadata and chart-managed\n  resources are removed with the release.\n- Treats already-missing resources and Helm releases as successful no-ops.\n\nDo not manually strip finalizers as part of the normal workflow. If cleanup\nwaits indefinitely, inspect the affected CR, operator pods, and events; request\nseparate authority before forcing finalizer removal.\n\n## Verify the Result\n\nRequire `.success == true`, then report:\n\n- `.cleanup.namespace`\n- `.cleanup.customResourcesDeleted`\n- `.cleanup.helmReleaseRemoved`\n- `.cleanup.keepHelmChart`\n\nIf the Helm release was meant to be removed, verify it is absent with the same\nread-only `helm list` command. If it was kept, verify it remains deployed.\n",{"data":32,"body":33},{"name":4,"description":6},{"type":34,"children":35},"root",[36,45,60,67,72,77,102,107,227,232,238,243,365,410,415,535,548,554,559,652,657,663,676,715,728],{"type":37,"tag":38,"props":39,"children":41},"element","h1",{"id":40},"clean-a-network-operator-deployment",[42],{"type":43,"value":44},"text","Clean a Network Operator Deployment",{"type":37,"tag":46,"props":47,"children":48},"p",{},[49,51,58],{"type":43,"value":50},"Read ",{"type":37,"tag":52,"props":53,"children":55},"code",{"className":54},[],[56],{"type":43,"value":57},"k8s-launch-kit-shared",{"type":43,"value":59}," first for binary discovery, JSON output, and error\nhandling.",{"type":37,"tag":61,"props":62,"children":64},"h2",{"id":63},"safety-boundary",[65],{"type":43,"value":66},"Safety Boundary",{"type":37,"tag":46,"props":68,"children":69},{},[70],{"type":43,"value":71},"Treat cleanup as an irreversible live-cluster mutation. Require explicit user\nauthority to remove the deployment. Do not infer cleanup authority from a\nrequest to inspect, validate, troubleshoot, or explain the command.",{"type":37,"tag":46,"props":73,"children":74},{},[75],{"type":43,"value":76},"Before running it:",{"type":37,"tag":78,"props":79,"children":80},"ol",{},[81,87,92,97],{"type":37,"tag":82,"props":83,"children":84},"li",{},[85],{"type":43,"value":86},"Resolve the intended kubeconfig and show its current context.",{"type":37,"tag":82,"props":88,"children":89},{},[90],{"type":43,"value":91},"Determine the intended Network Operator namespace.",{"type":37,"tag":82,"props":93,"children":94},{},[95],{"type":43,"value":96},"Explain that all namespaced custom resources in that namespace and every\nknown cluster-scoped Network Operator CR will be deleted.",{"type":37,"tag":82,"props":98,"children":99},{},[100],{"type":43,"value":101},"Confirm whether the Helm release should be uninstalled or retained.",{"type":37,"tag":46,"props":103,"children":104},{},[105],{"type":43,"value":106},"Use read-only checks when the target is not already explicit:",{"type":37,"tag":108,"props":109,"children":114},"pre",{"className":110,"code":111,"language":112,"meta":113,"style":113},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","kubectl --kubeconfig \u003CPATH> config current-context\nhelm --kubeconfig \u003CPATH> list --all-namespaces --filter '^network-operator$'\n","bash","",[115],{"type":37,"tag":52,"props":116,"children":117},{"__ignoreMap":113},[118,168],{"type":37,"tag":119,"props":120,"children":123},"span",{"class":121,"line":122},"line",1,[124,130,136,142,147,153,158,163],{"type":37,"tag":119,"props":125,"children":127},{"style":126},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[128],{"type":43,"value":129},"kubectl",{"type":37,"tag":119,"props":131,"children":133},{"style":132},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[134],{"type":43,"value":135}," --kubeconfig",{"type":37,"tag":119,"props":137,"children":139},{"style":138},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[140],{"type":43,"value":141}," \u003C",{"type":37,"tag":119,"props":143,"children":144},{"style":132},[145],{"type":43,"value":146},"PAT",{"type":37,"tag":119,"props":148,"children":150},{"style":149},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[151],{"type":43,"value":152},"H",{"type":37,"tag":119,"props":154,"children":155},{"style":138},[156],{"type":43,"value":157},">",{"type":37,"tag":119,"props":159,"children":160},{"style":132},[161],{"type":43,"value":162}," config",{"type":37,"tag":119,"props":164,"children":165},{"style":132},[166],{"type":43,"value":167}," current-context\n",{"type":37,"tag":119,"props":169,"children":171},{"class":121,"line":170},2,[172,177,181,185,189,193,197,202,207,212,217,222],{"type":37,"tag":119,"props":173,"children":174},{"style":126},[175],{"type":43,"value":176},"helm",{"type":37,"tag":119,"props":178,"children":179},{"style":132},[180],{"type":43,"value":135},{"type":37,"tag":119,"props":182,"children":183},{"style":138},[184],{"type":43,"value":141},{"type":37,"tag":119,"props":186,"children":187},{"style":132},[188],{"type":43,"value":146},{"type":37,"tag":119,"props":190,"children":191},{"style":149},[192],{"type":43,"value":152},{"type":37,"tag":119,"props":194,"children":195},{"style":138},[196],{"type":43,"value":157},{"type":37,"tag":119,"props":198,"children":199},{"style":132},[200],{"type":43,"value":201}," list",{"type":37,"tag":119,"props":203,"children":204},{"style":132},[205],{"type":43,"value":206}," --all-namespaces",{"type":37,"tag":119,"props":208,"children":209},{"style":132},[210],{"type":43,"value":211}," --filter",{"type":37,"tag":119,"props":213,"children":214},{"style":138},[215],{"type":43,"value":216}," '",{"type":37,"tag":119,"props":218,"children":219},{"style":132},[220],{"type":43,"value":221},"^network-operator$",{"type":37,"tag":119,"props":223,"children":224},{"style":138},[225],{"type":43,"value":226},"'\n",{"type":37,"tag":46,"props":228,"children":229},{},[230],{"type":43,"value":231},"Stop and ask for direction if the kubeconfig, cluster, namespace, or Helm\nretention choice remains ambiguous.",{"type":37,"tag":61,"props":233,"children":235},{"id":234},"run-cleanup",[236],{"type":43,"value":237},"Run Cleanup",{"type":37,"tag":46,"props":239,"children":240},{},[241],{"type":43,"value":242},"An AI agent uses JSON mode after the user authorizes the exact target:",{"type":37,"tag":108,"props":244,"children":246},{"className":110,"code":245,"language":112,"meta":113,"style":113},"l8k clean \\\n  --kubeconfig \u003CPATH> \\\n  --network-operator-namespace \u003CNAMESPACE> \\\n  --output json 2>\u002Fdev\u002Fnull | jq .\n",[247],{"type":37,"tag":52,"props":248,"children":249},{"__ignoreMap":113},[250,268,296,327],{"type":37,"tag":119,"props":251,"children":252},{"class":121,"line":122},[253,258,263],{"type":37,"tag":119,"props":254,"children":255},{"style":126},[256],{"type":43,"value":257},"l8k",{"type":37,"tag":119,"props":259,"children":260},{"style":132},[261],{"type":43,"value":262}," clean",{"type":37,"tag":119,"props":264,"children":265},{"style":149},[266],{"type":43,"value":267}," \\\n",{"type":37,"tag":119,"props":269,"children":270},{"class":121,"line":170},[271,276,280,284,288,292],{"type":37,"tag":119,"props":272,"children":273},{"style":132},[274],{"type":43,"value":275},"  --kubeconfig",{"type":37,"tag":119,"props":277,"children":278},{"style":138},[279],{"type":43,"value":141},{"type":37,"tag":119,"props":281,"children":282},{"style":132},[283],{"type":43,"value":146},{"type":37,"tag":119,"props":285,"children":286},{"style":149},[287],{"type":43,"value":152},{"type":37,"tag":119,"props":289,"children":290},{"style":138},[291],{"type":43,"value":157},{"type":37,"tag":119,"props":293,"children":294},{"style":149},[295],{"type":43,"value":267},{"type":37,"tag":119,"props":297,"children":299},{"class":121,"line":298},3,[300,305,309,314,319,323],{"type":37,"tag":119,"props":301,"children":302},{"style":132},[303],{"type":43,"value":304},"  --network-operator-namespace",{"type":37,"tag":119,"props":306,"children":307},{"style":138},[308],{"type":43,"value":141},{"type":37,"tag":119,"props":310,"children":311},{"style":132},[312],{"type":43,"value":313},"NAMESPAC",{"type":37,"tag":119,"props":315,"children":316},{"style":149},[317],{"type":43,"value":318},"E",{"type":37,"tag":119,"props":320,"children":321},{"style":138},[322],{"type":43,"value":157},{"type":37,"tag":119,"props":324,"children":325},{"style":149},[326],{"type":43,"value":267},{"type":37,"tag":119,"props":328,"children":329},{"class":121,"line":24},[330,335,340,345,350,355,360],{"type":37,"tag":119,"props":331,"children":332},{"style":132},[333],{"type":43,"value":334},"  --output",{"type":37,"tag":119,"props":336,"children":337},{"style":132},[338],{"type":43,"value":339}," json",{"type":37,"tag":119,"props":341,"children":342},{"style":138},[343],{"type":43,"value":344}," 2>",{"type":37,"tag":119,"props":346,"children":347},{"style":132},[348],{"type":43,"value":349},"\u002Fdev\u002Fnull",{"type":37,"tag":119,"props":351,"children":352},{"style":138},[353],{"type":43,"value":354}," |",{"type":37,"tag":119,"props":356,"children":357},{"style":126},[358],{"type":43,"value":359}," jq",{"type":37,"tag":119,"props":361,"children":362},{"style":132},[363],{"type":43,"value":364}," .\n",{"type":37,"tag":46,"props":366,"children":367},{},[368,370,376,378,384,386,392,394,400,402,408],{"type":43,"value":369},"Omit ",{"type":37,"tag":52,"props":371,"children":373},{"className":372},[],[374],{"type":43,"value":375},"--network-operator-namespace",{"type":43,"value":377}," only when the user expects l8k to resolve\nit from ",{"type":37,"tag":52,"props":379,"children":381},{"className":380},[],[382],{"type":43,"value":383},"--user-config",{"type":43,"value":385},", ",{"type":37,"tag":52,"props":387,"children":389},{"className":388},[],[390],{"type":43,"value":391},".\u002Fcluster-config.yaml",{"type":43,"value":393},", an explicit ",{"type":37,"tag":52,"props":395,"children":397},{"className":396},[],[398],{"type":43,"value":399},"--config-dir",{"type":43,"value":401},",\nor the ",{"type":37,"tag":52,"props":403,"children":405},{"className":404},[],[406],{"type":43,"value":407},"nvidia-network-operator",{"type":43,"value":409}," default. l8k does not trust in-cluster objects\nto select a destructive cleanup target.",{"type":37,"tag":46,"props":411,"children":412},{},[413],{"type":43,"value":414},"To retain the installed release and its chart-managed resources:",{"type":37,"tag":108,"props":416,"children":418},{"className":110,"code":417,"language":112,"meta":113,"style":113},"l8k clean \\\n  --kubeconfig \u003CPATH> \\\n  --network-operator-namespace \u003CNAMESPACE> \\\n  --keep-helm-chart \\\n  --output json 2>\u002Fdev\u002Fnull | jq .\n",[419],{"type":37,"tag":52,"props":420,"children":421},{"__ignoreMap":113},[422,437,464,491,503],{"type":37,"tag":119,"props":423,"children":424},{"class":121,"line":122},[425,429,433],{"type":37,"tag":119,"props":426,"children":427},{"style":126},[428],{"type":43,"value":257},{"type":37,"tag":119,"props":430,"children":431},{"style":132},[432],{"type":43,"value":262},{"type":37,"tag":119,"props":434,"children":435},{"style":149},[436],{"type":43,"value":267},{"type":37,"tag":119,"props":438,"children":439},{"class":121,"line":170},[440,444,448,452,456,460],{"type":37,"tag":119,"props":441,"children":442},{"style":132},[443],{"type":43,"value":275},{"type":37,"tag":119,"props":445,"children":446},{"style":138},[447],{"type":43,"value":141},{"type":37,"tag":119,"props":449,"children":450},{"style":132},[451],{"type":43,"value":146},{"type":37,"tag":119,"props":453,"children":454},{"style":149},[455],{"type":43,"value":152},{"type":37,"tag":119,"props":457,"children":458},{"style":138},[459],{"type":43,"value":157},{"type":37,"tag":119,"props":461,"children":462},{"style":149},[463],{"type":43,"value":267},{"type":37,"tag":119,"props":465,"children":466},{"class":121,"line":298},[467,471,475,479,483,487],{"type":37,"tag":119,"props":468,"children":469},{"style":132},[470],{"type":43,"value":304},{"type":37,"tag":119,"props":472,"children":473},{"style":138},[474],{"type":43,"value":141},{"type":37,"tag":119,"props":476,"children":477},{"style":132},[478],{"type":43,"value":313},{"type":37,"tag":119,"props":480,"children":481},{"style":149},[482],{"type":43,"value":318},{"type":37,"tag":119,"props":484,"children":485},{"style":138},[486],{"type":43,"value":157},{"type":37,"tag":119,"props":488,"children":489},{"style":149},[490],{"type":43,"value":267},{"type":37,"tag":119,"props":492,"children":493},{"class":121,"line":24},[494,499],{"type":37,"tag":119,"props":495,"children":496},{"style":132},[497],{"type":43,"value":498},"  --keep-helm-chart",{"type":37,"tag":119,"props":500,"children":501},{"style":149},[502],{"type":43,"value":267},{"type":37,"tag":119,"props":504,"children":506},{"class":121,"line":505},5,[507,511,515,519,523,527,531],{"type":37,"tag":119,"props":508,"children":509},{"style":132},[510],{"type":43,"value":334},{"type":37,"tag":119,"props":512,"children":513},{"style":132},[514],{"type":43,"value":339},{"type":37,"tag":119,"props":516,"children":517},{"style":138},[518],{"type":43,"value":344},{"type":37,"tag":119,"props":520,"children":521},{"style":132},[522],{"type":43,"value":349},{"type":37,"tag":119,"props":524,"children":525},{"style":138},[526],{"type":43,"value":354},{"type":37,"tag":119,"props":528,"children":529},{"style":126},[530],{"type":43,"value":359},{"type":37,"tag":119,"props":532,"children":533},{"style":132},[534],{"type":43,"value":364},{"type":37,"tag":46,"props":536,"children":537},{},[538,540,546],{"type":43,"value":539},"JSON mode auto-confirms. Do not invoke it until the read-only target checks and\nauthorization are complete. ",{"type":37,"tag":52,"props":541,"children":543},{"className":542},[],[544],{"type":43,"value":545},"l8k clean",{"type":43,"value":547}," has no dry-run mode.",{"type":37,"tag":61,"props":549,"children":551},{"id":550},"deletion-semantics",[552],{"type":43,"value":553},"Deletion Semantics",{"type":37,"tag":46,"props":555,"children":556},{},[557],{"type":43,"value":558},"The command:",{"type":37,"tag":560,"props":561,"children":562},"ul",{},[563,568,611,616,621,642,647],{"type":37,"tag":82,"props":564,"children":565},{},[566],{"type":43,"value":567},"Deletes every namespaced custom-resource instance in the resolved operator\nnamespace.",{"type":37,"tag":82,"props":569,"children":570},{},[571,573,579,580,586,587,593,595,601,603,609],{"type":43,"value":572},"Deletes all ",{"type":37,"tag":52,"props":574,"children":576},{"className":575},[],[577],{"type":43,"value":578},"HostDeviceNetwork",{"type":43,"value":385},{"type":37,"tag":52,"props":581,"children":583},{"className":582},[],[584],{"type":43,"value":585},"IPoIBNetwork",{"type":43,"value":385},{"type":37,"tag":52,"props":588,"children":590},{"className":589},[],[591],{"type":43,"value":592},"MacvlanNetwork",{"type":43,"value":594},",\n",{"type":37,"tag":52,"props":596,"children":598},{"className":597},[],[599],{"type":43,"value":600},"NicNodePolicy",{"type":43,"value":602},", and ",{"type":37,"tag":52,"props":604,"children":606},{"className":605},[],[607],{"type":43,"value":608},"NicClusterPolicy",{"type":43,"value":610}," instances cluster-wide.",{"type":37,"tag":82,"props":612,"children":613},{},[614],{"type":43,"value":615},"Sends deletion requests to the complete namespaced and cluster-scoped set\nbefore monitoring any CR for finalizer completion, then uses the same\ndelete-all-then-wait ordering for re-sweeps.",{"type":37,"tag":82,"props":617,"children":618},{},[619],{"type":43,"value":620},"Keeps controllers installed until CR deletion and finalizers complete.",{"type":37,"tag":82,"props":622,"children":623},{},[624,626,632,634,640],{"type":43,"value":625},"Uninstalls the ",{"type":37,"tag":52,"props":627,"children":629},{"className":628},[],[630],{"type":43,"value":631},"network-operator",{"type":43,"value":633}," Helm release last unless\n",{"type":37,"tag":52,"props":635,"children":637},{"className":636},[],[638],{"type":43,"value":639},"--keep-helm-chart",{"type":43,"value":641}," is set.",{"type":37,"tag":82,"props":643,"children":644},{},[645],{"type":43,"value":646},"Preserves the namespace, CRDs, Secrets not owned by Helm, local files, and\nnamespaced custom resources elsewhere. Helm metadata and chart-managed\nresources are removed with the release.",{"type":37,"tag":82,"props":648,"children":649},{},[650],{"type":43,"value":651},"Treats already-missing resources and Helm releases as successful no-ops.",{"type":37,"tag":46,"props":653,"children":654},{},[655],{"type":43,"value":656},"Do not manually strip finalizers as part of the normal workflow. If cleanup\nwaits indefinitely, inspect the affected CR, operator pods, and events; request\nseparate authority before forcing finalizer removal.",{"type":37,"tag":61,"props":658,"children":660},{"id":659},"verify-the-result",[661],{"type":43,"value":662},"Verify the Result",{"type":37,"tag":46,"props":664,"children":665},{},[666,668,674],{"type":43,"value":667},"Require ",{"type":37,"tag":52,"props":669,"children":671},{"className":670},[],[672],{"type":43,"value":673},".success == true",{"type":43,"value":675},", then report:",{"type":37,"tag":560,"props":677,"children":678},{},[679,688,697,706],{"type":37,"tag":82,"props":680,"children":681},{},[682],{"type":37,"tag":52,"props":683,"children":685},{"className":684},[],[686],{"type":43,"value":687},".cleanup.namespace",{"type":37,"tag":82,"props":689,"children":690},{},[691],{"type":37,"tag":52,"props":692,"children":694},{"className":693},[],[695],{"type":43,"value":696},".cleanup.customResourcesDeleted",{"type":37,"tag":82,"props":698,"children":699},{},[700],{"type":37,"tag":52,"props":701,"children":703},{"className":702},[],[704],{"type":43,"value":705},".cleanup.helmReleaseRemoved",{"type":37,"tag":82,"props":707,"children":708},{},[709],{"type":37,"tag":52,"props":710,"children":712},{"className":711},[],[713],{"type":43,"value":714},".cleanup.keepHelmChart",{"type":37,"tag":46,"props":716,"children":717},{},[718,720,726],{"type":43,"value":719},"If the Helm release was meant to be removed, verify it is absent with the same\nread-only ",{"type":37,"tag":52,"props":721,"children":723},{"className":722},[],[724],{"type":43,"value":725},"helm list",{"type":43,"value":727}," command. If it was kept, verify it remains deployed.",{"type":37,"tag":729,"props":730,"children":731},"style",{},[732],{"type":43,"value":733},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":735,"total":892},[736,754,770,781,793,807,820,834,847,858,872,881],{"slug":737,"name":737,"fn":738,"description":739,"org":740,"tags":741,"stars":751,"repoUrl":752,"updatedAt":753},"nemoclaw-user-guide","retrieve NemoClaw documentation and configuration","Guides human users' AI agents to the NemoClaw docs MCP server and canonical Fern documentation in Markdown form. Use when users ask how to install, configure, operate, troubleshoot, secure, or learn NemoClaw with an AI coding assistant. Trigger keywords - nemoclaw docs, use nemoclaw with ai agent, nemoclaw mcp docs, nemoclaw install help, nemoclaw quickstart, nemoclaw markdown docs, llms.txt, agent skills.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[742,745,748],{"name":743,"slug":744,"type":15},"Documentation","documentation",{"name":746,"slug":747,"type":15},"MCP","mcp",{"name":749,"slug":750,"type":15},"Search","search",21777,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FNemoClaw","2026-08-25T03:29:57.273192",{"slug":755,"name":755,"fn":756,"description":757,"org":758,"tags":759,"stars":767,"repoUrl":768,"updatedAt":769},"mcore-build-and-dependency","manage Megatron-LM development environments","Container-based dev environment setup and dependency management for Megatron-LM. Covers acquiring and launching the CI container, uv package management, and updating uv.lock.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[760,763,764],{"name":761,"slug":762,"type":15},"Containers","containers",{"name":13,"slug":14,"type":15},{"name":765,"slug":766,"type":15},"Python","python",17049,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FMegatron-LM","2026-07-27T06:06:11.249662",{"slug":771,"name":771,"fn":772,"description":773,"org":774,"tags":775,"stars":767,"repoUrl":768,"updatedAt":780},"mcore-bump-base-image","update NVIDIA PyTorch base images","Bump the NVIDIA PyTorch base image (`nvcr.io\u002Fnvidia\u002Fpytorch:YY.MM-py3`) used by Megatron-LM CI. Covers the two pin sites (GitHub CI in `docker\u002F.ngc_version.dev` and GitLab CI in `.gitlab\u002Fstages\u002F01.build.yml`), the post-bump CI loop (re-run functional tests, refresh golden values, mark broken tests), and the gotchas that bit PRs",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[776,779],{"name":777,"slug":778,"type":15},"CI\u002FCD","ci-cd",{"name":13,"slug":14,"type":15},"2026-07-14T05:25:59.97109",{"slug":782,"name":782,"fn":783,"description":784,"org":785,"tags":786,"stars":767,"repoUrl":768,"updatedAt":792},"mcore-cicd","manage CI\u002FCD pipelines for Megatron-LM","CI\u002FCD reference for Megatron-LM. Covers CI pipeline structure, PR scope labels, triggering internal GitLab CI (which force-pushes the current branch to a pull-request\u002FBRANCH ref — always dry-run and verify the destination first; never run against shared or protected branches), and CI failure investigation.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[787,788,789],{"name":777,"slug":778,"type":15},{"name":13,"slug":14,"type":15},{"name":790,"slug":791,"type":15},"GitHub","github","2026-08-28T14:38:16.959248",{"slug":794,"name":794,"fn":795,"description":796,"org":797,"tags":798,"stars":767,"repoUrl":768,"updatedAt":806},"mcore-create-issue","investigate CI failures and create issues","Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[799,802,803],{"name":800,"slug":801,"type":15},"Debugging","debugging",{"name":790,"slug":791,"type":15},{"name":804,"slug":805,"type":15},"Triage","triage","2026-07-14T05:25:57.442089",{"slug":808,"name":808,"fn":809,"description":810,"org":811,"tags":812,"stars":767,"repoUrl":768,"updatedAt":819},"mcore-linting-and-formatting","lint and format Megatron-LM code","Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[813,816],{"name":814,"slug":815,"type":15},"Best Practices","best-practices",{"name":817,"slug":818,"type":15},"Code Analysis","code-analysis","2026-07-14T05:25:56.18433",{"slug":821,"name":821,"fn":822,"description":823,"org":824,"tags":825,"stars":767,"repoUrl":768,"updatedAt":833},"mcore-migrate-gpt-to-hybrid","migrate Megatron-LM models to HybridModel","Migration guide for moving Megatron Core GPTModel checkpoints, model providers, training commands, and layer mappings to HybridModel, including the mechanical steps for transferring an existing pretrain_gpt.py launch script.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[826,829,832],{"name":827,"slug":828,"type":15},"Machine Learning","machine-learning",{"name":830,"slug":831,"type":15},"Migration","migration",{"name":9,"slug":8,"type":15},"2026-08-21T03:36:57.470256",{"slug":835,"name":835,"fn":836,"description":837,"org":838,"tags":839,"stars":767,"repoUrl":768,"updatedAt":846},"mcore-onboard-gb200-1node-tests","onboard functional tests for GB200","Onboard 1-node GitHub MR functional tests for GB200 from existing mr-scoped 2-node tests.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[840,843],{"name":841,"slug":842,"type":15},"QA","qa",{"name":844,"slug":845,"type":15},"Testing","testing","2026-07-14T05:25:53.673039",{"slug":848,"name":848,"fn":849,"description":850,"org":851,"tags":852,"stars":767,"repoUrl":768,"updatedAt":857},"mcore-run-on-slurm","launch distributed training jobs on SLURM","How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[853,854],{"name":13,"slug":14,"type":15},{"name":855,"slug":856,"type":15},"Infrastructure","infrastructure","2026-07-14T05:25:49.362534",{"slug":859,"name":859,"fn":860,"description":861,"org":862,"tags":863,"stars":767,"repoUrl":768,"updatedAt":871},"mcore-split-pr","split pull requests to reduce review load","Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[864,867,868],{"name":865,"slug":866,"type":15},"Code Review","code-review",{"name":790,"slug":791,"type":15},{"name":869,"slug":870,"type":15},"Pull Requests","pull-requests","2026-08-25T03:29:16.211287",{"slug":873,"name":873,"fn":874,"description":875,"org":876,"tags":877,"stars":767,"repoUrl":768,"updatedAt":880},"mcore-testing","run and manage Megatron-LM tests","Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[878,879],{"name":841,"slug":842,"type":15},{"name":844,"slug":845,"type":15},"2026-07-14T05:25:54.928983",{"slug":882,"name":882,"fn":883,"description":884,"org":885,"tags":886,"stars":767,"repoUrl":768,"updatedAt":891},"nightly-sync","manage nightly main-to-dev sync workflows","Domain knowledge for the nightly main-to-dev sync workflow. Covers merge strategy, CI architecture, failure investigation, and known issues.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[887,890],{"name":888,"slug":889,"type":15},"Automation","automation",{"name":777,"slug":778,"type":15},"2026-07-30T05:29:03.275638",563,{"items":894,"total":981},[895,901,914,927,943,955,969],{"slug":4,"name":4,"fn":5,"description":6,"org":896,"tags":897,"stars":20,"repoUrl":21,"updatedAt":22},{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[898,899,900],{"name":13,"slug":14,"type":15},{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"slug":902,"name":902,"fn":903,"description":904,"org":905,"tags":906,"stars":20,"repoUrl":21,"updatedAt":913},"k8s-launch-kit-config","configure k8s-launch-kit clusters","Use this skill when the user needs help understanding, creating, or editing a k8s-launch-kit (l8k) configuration file (l8k-config.yaml or cluster-config.yaml). Activate for: config file questions, parameter tuning, subnet configuration, NV-IPAM setup, DOCA driver settings, maintenance concurrency, NIC configuration operator settings, changing MTU, VFs, resource names, or understanding what any config field does.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[907,910,911,912],{"name":908,"slug":909,"type":15},"Configuration","configuration",{"name":13,"slug":14,"type":15},{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},"2026-08-18T03:28:51.307428",{"slug":915,"name":915,"fn":916,"description":917,"org":918,"tags":919,"stars":20,"repoUrl":21,"updatedAt":926},"k8s-launch-kit-deploy","deploy NVIDIA networking manifests to Kubernetes","Use this skill when the user wants to deploy generated NVIDIA networking manifests to a Kubernetes cluster using k8s-launch-kit (l8k). Activate for: applying manifests, deploying to cluster, the `l8k deploy` subcommand or the legacy --deploy flag on `l8k generate`, applying generated files, or any mention of pushing l8k output to a live cluster. Even if the user just says 'apply these' or 'push to cluster' after generating manifests, use this skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[920,921,922,925],{"name":13,"slug":14,"type":15},{"name":18,"slug":19,"type":15},{"name":923,"slug":924,"type":15},"Networking","networking",{"name":9,"slug":8,"type":15},"2026-08-21T03:37:09.450931",{"slug":928,"name":928,"fn":929,"description":930,"org":931,"tags":932,"stars":20,"repoUrl":21,"updatedAt":942},"k8s-launch-kit-discover","discover Kubernetes cluster network hardware capabilities","Use this skill when the user wants to discover their Kubernetes cluster's network hardware capabilities using k8s-launch-kit (l8k). Activate for: cluster discovery, hardware detection, NIC detection, finding what GPUs or NICs are in a cluster, creating a cluster config file, or when the user says 'discover' in the context of l8k or NVIDIA networking.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[933,936,937,938,939],{"name":934,"slug":935,"type":15},"Hardware","hardware",{"name":18,"slug":19,"type":15},{"name":923,"slug":924,"type":15},{"name":9,"slug":8,"type":15},{"name":940,"slug":941,"type":15},"Operations","operations","2026-08-18T03:28:54.319378",{"slug":944,"name":944,"fn":945,"description":946,"org":947,"tags":948,"stars":20,"repoUrl":21,"updatedAt":954},"k8s-launch-kit-dryrun","preview NVIDIA networking deployment changes","Use this skill when the user wants to preview what k8s-launch-kit (l8k) would deploy without making changes, or wants to safely validate their configuration before applying. Activate for: dry-run, preview, validation, 'what would happen if', testing configurations, schema discovery, checking generated manifests, or any cautious pre-deployment step. Also use when the user asks 'is my config valid' or 'show me what would be created' -- even without mentioning dry-run explicitly.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[949,950,951,952,953],{"name":908,"slug":909,"type":15},{"name":13,"slug":14,"type":15},{"name":18,"slug":19,"type":15},{"name":923,"slug":924,"type":15},{"name":9,"slug":8,"type":15},"2026-07-14T05:31:56.325698",{"slug":956,"name":956,"fn":957,"description":958,"org":959,"tags":960,"stars":20,"repoUrl":21,"updatedAt":968},"k8s-launch-kit-generate","generate Kubernetes manifests for NVIDIA networking","Use this skill when the user wants to generate Kubernetes YAML manifests for NVIDIA networking deployment using k8s-launch-kit (l8k). Activate for: manifest generation, profile selection, choosing between SR-IOV\u002Fhost-device\u002FRDMA-shared\u002FIPoIB\u002FMacVLAN\u002FSpectrum-X, creating deployment files, or when the user asks 'which profile should I use' or needs help choosing a network configuration.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[961,962,963,964,965],{"name":13,"slug":14,"type":15},{"name":18,"slug":19,"type":15},{"name":923,"slug":924,"type":15},{"name":9,"slug":8,"type":15},{"name":966,"slug":967,"type":15},"YAML","yaml","2026-08-18T03:28:53.305045",{"slug":970,"name":970,"fn":971,"description":972,"org":973,"tags":974,"stars":20,"repoUrl":21,"updatedAt":980},"k8s-launch-kit-pipeline","run end-to-end NVIDIA networking deployment pipelines","Use this skill when the user wants to run the full k8s-launch-kit (l8k) pipeline end-to-end: discover cluster hardware, select a profile, generate manifests, and deploy them all in one command. Also activate for CI\u002FCD integration, automation pipelines, 'one-liner', 'complete workflow', or end-to-end NVIDIA networking deployment.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[975,976,977,978,979],{"name":888,"slug":889,"type":15},{"name":13,"slug":14,"type":15},{"name":18,"slug":19,"type":15},{"name":923,"slug":924,"type":15},{"name":9,"slug":8,"type":15},"2026-08-09T04:03:59.379481",11]