[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-nvidia-tao-list-capabilities":3,"mdc-5t8lox-key":31,"related-repo-nvidia-tao-list-capabilities":612,"related-org-nvidia-tao-list-capabilities":718},{"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},"tao-list-capabilities","list TAO Skill Bank capabilities","Answer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, AutoML, and platform manifests. Use when the user asks \"what can TAO Skill Bank do\", \"list TAO models\", \"which TAO workflows are available\", or \"what supports AutoML\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},"nvidia","NVIDIA","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fnvidia.png",[12,16,19],{"name":13,"slug":14,"type":15},"Documentation","documentation","tag",{"name":17,"slug":18,"type":15},"Reference","reference",{"name":9,"slug":8,"type":15},2473,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002Fskills","2026-07-14T05:27:53.176882","Apache-2.0",281,[],{"repoUrl":21,"stars":20,"forks":24,"topics":27,"description":28},[],"AI agent skills published by NVIDIA","https:\u002F\u002Fgithub.com\u002FNVIDIA\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Ftao-list-capabilities","---\nname: tao-list-capabilities\ndescription: >-\n  Answer what the TAO Skill Bank plugin can do by generating the response from\n  packaged application, data, model, AutoML, and platform manifests. Use when\n  the user asks \"what can TAO Skill Bank do\", \"list TAO models\", \"which TAO\n  workflows are available\", or \"what supports AutoML\".\nlicense: Apache-2.0\ncompatibility: Requires the packaged TAO skill bank helper scripts.\nmetadata:\n  author: NVIDIA Corporation\n  version: \"0.1.0\"\nallowed-tools: Read Bash\ntags:\n- tao\n- capabilities\n- discovery\n---\n\n# TAO Skill Bank Capabilities\n\nUse this skill when the user asks what `tao-skill-bank` can do, asks for plugin\ncapabilities, asks which application or data workflows are available, asks which\nmodels are supported, or asks what models are capable with AutoML.\n\n## Quick Start\n\nRun `scripts\u002Flist_tao_capabilities.py` for general capability questions, or\n`scripts\u002Flist_tao_models.py` for model\u002Faction and AutoML support questions.\n\n## Capability Answers\n\nFor a general capabilities answer, run the packaged helper:\n\n```bash\n${TAO_SKILL_BANK_PATH:-~\u002Ftao-skills-external}\u002Fscripts\u002Flist_tao_capabilities.py \\\n  --skill-bank ${TAO_SKILL_BANK_PATH:-~\u002Ftao-skills-external} --format text\n```\n\nUse the helper output as the source of truth for the answer instead of manually\nenumerating capabilities from this skill or plugin metadata. Include:\n\n- Every top-level application workflow under `applications\u002F` and what it can do.\n- Every top-level data workflow under `data\u002F` and what it can do.\n- Supported execution platforms from `scripts\u002Flist_tao_platforms.py`.\n- The fine-tuning\u002Fdeployment workflow coverage for models under `models\u002F`: train,\n  evaluate, inference, export, and TensorRT engine generation when those actions\n  are present in the packaged schema manifest.\n- AutoML support and the AutoML train-schema gate.\n\n## Model Lists\n\nWhen the user asks which TAO models are available or which actions a model can\nrun, use the packaged model-list script instead of manually scanning model\nfolders:\n\n```bash\n${TAO_SKILL_BANK_PATH:-~\u002Ftao-skills-external}\u002Fscripts\u002Flist_tao_models.py \\\n  --skill-bank ${TAO_SKILL_BANK_PATH:-~\u002Ftao-skills-external} --scope all --format text\n```\n\nThe model list comes from `skills\u002Fmodels\u002Fschemas.manifest.json`.\n\n## AutoML Lists\n\nWhen the user asks what models are capable with AutoML, use the same model-list\nscript in AutoML mode, or the compatibility wrapper:\n\n```bash\n${TAO_SKILL_BANK_PATH:-~\u002Ftao-skills-external}\u002Fscripts\u002Flist_tao_models.py \\\n  --skill-bank ${TAO_SKILL_BANK_PATH:-~\u002Ftao-skills-external} --scope automl --format text\n```\n\n```bash\n${TAO_SKILL_BANK_PATH:-~\u002Ftao-skills-external}\u002Fscripts\u002Flist_automl_support.py \\\n  --skill-bank ${TAO_SKILL_BANK_PATH:-~\u002Ftao-skills-external} --format text\n```\n\nAutoML support requires `skills\u002Fmodels\u002F\u003Cnetwork>\u002Fschemas\u002Ftrain.schema.json` to be\npackaged with the plugin and parse successfully as JSON. If that dataclass schema\nis missing or invalid, do not describe the model as AutoML-supported.\n",{"data":32,"body":42},{"name":4,"description":6,"license":23,"compatibility":33,"metadata":34,"allowed-tools":37,"tags":38},"Requires the packaged TAO skill bank helper scripts.",{"author":35,"version":36},"NVIDIA Corporation","0.1.0","Read Bash",[39,40,41],"tao","capabilities","discovery",{"type":43,"children":44},"root",[45,54,69,76,97,103,108,217,222,283,289,294,390,402,408,413,507,593,606],{"type":46,"tag":47,"props":48,"children":50},"element","h1",{"id":49},"tao-skill-bank-capabilities",[51],{"type":52,"value":53},"text","TAO Skill Bank Capabilities",{"type":46,"tag":55,"props":56,"children":57},"p",{},[58,60,67],{"type":52,"value":59},"Use this skill when the user asks what ",{"type":46,"tag":61,"props":62,"children":64},"code",{"className":63},[],[65],{"type":52,"value":66},"tao-skill-bank",{"type":52,"value":68}," can do, asks for plugin\ncapabilities, asks which application or data workflows are available, asks which\nmodels are supported, or asks what models are capable with AutoML.",{"type":46,"tag":70,"props":71,"children":73},"h2",{"id":72},"quick-start",[74],{"type":52,"value":75},"Quick Start",{"type":46,"tag":55,"props":77,"children":78},{},[79,81,87,89,95],{"type":52,"value":80},"Run ",{"type":46,"tag":61,"props":82,"children":84},{"className":83},[],[85],{"type":52,"value":86},"scripts\u002Flist_tao_capabilities.py",{"type":52,"value":88}," for general capability questions, or\n",{"type":46,"tag":61,"props":90,"children":92},{"className":91},[],[93],{"type":52,"value":94},"scripts\u002Flist_tao_models.py",{"type":52,"value":96}," for model\u002Faction and AutoML support questions.",{"type":46,"tag":70,"props":98,"children":100},{"id":99},"capability-answers",[101],{"type":52,"value":102},"Capability Answers",{"type":46,"tag":55,"props":104,"children":105},{},[106],{"type":52,"value":107},"For a general capabilities answer, run the packaged helper:",{"type":46,"tag":109,"props":110,"children":115},"pre",{"className":111,"code":112,"language":113,"meta":114,"style":114},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","${TAO_SKILL_BANK_PATH:-~\u002Ftao-skills-external}\u002Fscripts\u002Flist_tao_capabilities.py \\\n  --skill-bank ${TAO_SKILL_BANK_PATH:-~\u002Ftao-skills-external} --format text\n","bash","",[116],{"type":46,"tag":61,"props":117,"children":118},{"__ignoreMap":114},[119,167],{"type":46,"tag":120,"props":121,"children":124},"span",{"class":122,"line":123},"line",1,[125,131,137,142,147,152,157,162],{"type":46,"tag":120,"props":126,"children":128},{"style":127},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[129],{"type":52,"value":130},"${",{"type":46,"tag":120,"props":132,"children":134},{"style":133},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[135],{"type":52,"value":136},"TAO_SKILL_BANK_PATH",{"type":46,"tag":120,"props":138,"children":139},{"style":127},[140],{"type":52,"value":141},":-",{"type":46,"tag":120,"props":143,"children":144},{"style":133},[145],{"type":52,"value":146},"~",{"type":46,"tag":120,"props":148,"children":149},{"style":127},[150],{"type":52,"value":151},"\u002F",{"type":46,"tag":120,"props":153,"children":154},{"style":133},[155],{"type":52,"value":156},"tao-skills-external",{"type":46,"tag":120,"props":158,"children":159},{"style":127},[160],{"type":52,"value":161},"}",{"type":46,"tag":120,"props":163,"children":164},{"style":133},[165],{"type":52,"value":166},"\u002Fscripts\u002Flist_tao_capabilities.py \\\n",{"type":46,"tag":120,"props":168,"children":170},{"class":122,"line":169},2,[171,177,182,186,190,194,198,202,206,212],{"type":46,"tag":120,"props":172,"children":174},{"style":173},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[175],{"type":52,"value":176},"  --skill-bank",{"type":46,"tag":120,"props":178,"children":179},{"style":127},[180],{"type":52,"value":181}," ${",{"type":46,"tag":120,"props":183,"children":184},{"style":133},[185],{"type":52,"value":136},{"type":46,"tag":120,"props":187,"children":188},{"style":127},[189],{"type":52,"value":141},{"type":46,"tag":120,"props":191,"children":192},{"style":133},[193],{"type":52,"value":146},{"type":46,"tag":120,"props":195,"children":196},{"style":127},[197],{"type":52,"value":151},{"type":46,"tag":120,"props":199,"children":200},{"style":133},[201],{"type":52,"value":156},{"type":46,"tag":120,"props":203,"children":204},{"style":127},[205],{"type":52,"value":161},{"type":46,"tag":120,"props":207,"children":209},{"style":208},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[210],{"type":52,"value":211}," --format",{"type":46,"tag":120,"props":213,"children":214},{"style":208},[215],{"type":52,"value":216}," text\n",{"type":46,"tag":55,"props":218,"children":219},{},[220],{"type":52,"value":221},"Use the helper output as the source of truth for the answer instead of manually\nenumerating capabilities from this skill or plugin metadata. Include:",{"type":46,"tag":223,"props":224,"children":225},"ul",{},[226,240,252,265,278],{"type":46,"tag":227,"props":228,"children":229},"li",{},[230,232,238],{"type":52,"value":231},"Every top-level application workflow under ",{"type":46,"tag":61,"props":233,"children":235},{"className":234},[],[236],{"type":52,"value":237},"applications\u002F",{"type":52,"value":239}," and what it can do.",{"type":46,"tag":227,"props":241,"children":242},{},[243,245,251],{"type":52,"value":244},"Every top-level data workflow under ",{"type":46,"tag":61,"props":246,"children":248},{"className":247},[],[249],{"type":52,"value":250},"data\u002F",{"type":52,"value":239},{"type":46,"tag":227,"props":253,"children":254},{},[255,257,263],{"type":52,"value":256},"Supported execution platforms from ",{"type":46,"tag":61,"props":258,"children":260},{"className":259},[],[261],{"type":52,"value":262},"scripts\u002Flist_tao_platforms.py",{"type":52,"value":264},".",{"type":46,"tag":227,"props":266,"children":267},{},[268,270,276],{"type":52,"value":269},"The fine-tuning\u002Fdeployment workflow coverage for models under ",{"type":46,"tag":61,"props":271,"children":273},{"className":272},[],[274],{"type":52,"value":275},"models\u002F",{"type":52,"value":277},": train,\nevaluate, inference, export, and TensorRT engine generation when those actions\nare present in the packaged schema manifest.",{"type":46,"tag":227,"props":279,"children":280},{},[281],{"type":52,"value":282},"AutoML support and the AutoML train-schema gate.",{"type":46,"tag":70,"props":284,"children":286},{"id":285},"model-lists",[287],{"type":52,"value":288},"Model Lists",{"type":46,"tag":55,"props":290,"children":291},{},[292],{"type":52,"value":293},"When the user asks which TAO models are available or which actions a model can\nrun, use the packaged model-list script instead of manually scanning model\nfolders:",{"type":46,"tag":109,"props":295,"children":297},{"className":111,"code":296,"language":113,"meta":114,"style":114},"${TAO_SKILL_BANK_PATH:-~\u002Ftao-skills-external}\u002Fscripts\u002Flist_tao_models.py \\\n  --skill-bank ${TAO_SKILL_BANK_PATH:-~\u002Ftao-skills-external} --scope all --format text\n",[298],{"type":46,"tag":61,"props":299,"children":300},{"__ignoreMap":114},[301,337],{"type":46,"tag":120,"props":302,"children":303},{"class":122,"line":123},[304,308,312,316,320,324,328,332],{"type":46,"tag":120,"props":305,"children":306},{"style":127},[307],{"type":52,"value":130},{"type":46,"tag":120,"props":309,"children":310},{"style":133},[311],{"type":52,"value":136},{"type":46,"tag":120,"props":313,"children":314},{"style":127},[315],{"type":52,"value":141},{"type":46,"tag":120,"props":317,"children":318},{"style":133},[319],{"type":52,"value":146},{"type":46,"tag":120,"props":321,"children":322},{"style":127},[323],{"type":52,"value":151},{"type":46,"tag":120,"props":325,"children":326},{"style":133},[327],{"type":52,"value":156},{"type":46,"tag":120,"props":329,"children":330},{"style":127},[331],{"type":52,"value":161},{"type":46,"tag":120,"props":333,"children":334},{"style":133},[335],{"type":52,"value":336},"\u002Fscripts\u002Flist_tao_models.py \\\n",{"type":46,"tag":120,"props":338,"children":339},{"class":122,"line":169},[340,344,348,352,356,360,364,368,372,377,382,386],{"type":46,"tag":120,"props":341,"children":342},{"style":173},[343],{"type":52,"value":176},{"type":46,"tag":120,"props":345,"children":346},{"style":127},[347],{"type":52,"value":181},{"type":46,"tag":120,"props":349,"children":350},{"style":133},[351],{"type":52,"value":136},{"type":46,"tag":120,"props":353,"children":354},{"style":127},[355],{"type":52,"value":141},{"type":46,"tag":120,"props":357,"children":358},{"style":133},[359],{"type":52,"value":146},{"type":46,"tag":120,"props":361,"children":362},{"style":127},[363],{"type":52,"value":151},{"type":46,"tag":120,"props":365,"children":366},{"style":133},[367],{"type":52,"value":156},{"type":46,"tag":120,"props":369,"children":370},{"style":127},[371],{"type":52,"value":161},{"type":46,"tag":120,"props":373,"children":374},{"style":208},[375],{"type":52,"value":376}," --scope",{"type":46,"tag":120,"props":378,"children":379},{"style":208},[380],{"type":52,"value":381}," all",{"type":46,"tag":120,"props":383,"children":384},{"style":208},[385],{"type":52,"value":211},{"type":46,"tag":120,"props":387,"children":388},{"style":208},[389],{"type":52,"value":216},{"type":46,"tag":55,"props":391,"children":392},{},[393,395,401],{"type":52,"value":394},"The model list comes from ",{"type":46,"tag":61,"props":396,"children":398},{"className":397},[],[399],{"type":52,"value":400},"skills\u002Fmodels\u002Fschemas.manifest.json",{"type":52,"value":264},{"type":46,"tag":70,"props":403,"children":405},{"id":404},"automl-lists",[406],{"type":52,"value":407},"AutoML Lists",{"type":46,"tag":55,"props":409,"children":410},{},[411],{"type":52,"value":412},"When the user asks what models are capable with AutoML, use the same model-list\nscript in AutoML mode, or the compatibility wrapper:",{"type":46,"tag":109,"props":414,"children":416},{"className":111,"code":415,"language":113,"meta":114,"style":114},"${TAO_SKILL_BANK_PATH:-~\u002Ftao-skills-external}\u002Fscripts\u002Flist_tao_models.py \\\n  --skill-bank ${TAO_SKILL_BANK_PATH:-~\u002Ftao-skills-external} --scope automl --format text\n",[417],{"type":46,"tag":61,"props":418,"children":419},{"__ignoreMap":114},[420,455],{"type":46,"tag":120,"props":421,"children":422},{"class":122,"line":123},[423,427,431,435,439,443,447,451],{"type":46,"tag":120,"props":424,"children":425},{"style":127},[426],{"type":52,"value":130},{"type":46,"tag":120,"props":428,"children":429},{"style":133},[430],{"type":52,"value":136},{"type":46,"tag":120,"props":432,"children":433},{"style":127},[434],{"type":52,"value":141},{"type":46,"tag":120,"props":436,"children":437},{"style":133},[438],{"type":52,"value":146},{"type":46,"tag":120,"props":440,"children":441},{"style":127},[442],{"type":52,"value":151},{"type":46,"tag":120,"props":444,"children":445},{"style":133},[446],{"type":52,"value":156},{"type":46,"tag":120,"props":448,"children":449},{"style":127},[450],{"type":52,"value":161},{"type":46,"tag":120,"props":452,"children":453},{"style":133},[454],{"type":52,"value":336},{"type":46,"tag":120,"props":456,"children":457},{"class":122,"line":169},[458,462,466,470,474,478,482,486,490,494,499,503],{"type":46,"tag":120,"props":459,"children":460},{"style":173},[461],{"type":52,"value":176},{"type":46,"tag":120,"props":463,"children":464},{"style":127},[465],{"type":52,"value":181},{"type":46,"tag":120,"props":467,"children":468},{"style":133},[469],{"type":52,"value":136},{"type":46,"tag":120,"props":471,"children":472},{"style":127},[473],{"type":52,"value":141},{"type":46,"tag":120,"props":475,"children":476},{"style":133},[477],{"type":52,"value":146},{"type":46,"tag":120,"props":479,"children":480},{"style":127},[481],{"type":52,"value":151},{"type":46,"tag":120,"props":483,"children":484},{"style":133},[485],{"type":52,"value":156},{"type":46,"tag":120,"props":487,"children":488},{"style":127},[489],{"type":52,"value":161},{"type":46,"tag":120,"props":491,"children":492},{"style":208},[493],{"type":52,"value":376},{"type":46,"tag":120,"props":495,"children":496},{"style":208},[497],{"type":52,"value":498}," automl",{"type":46,"tag":120,"props":500,"children":501},{"style":208},[502],{"type":52,"value":211},{"type":46,"tag":120,"props":504,"children":505},{"style":208},[506],{"type":52,"value":216},{"type":46,"tag":109,"props":508,"children":510},{"className":111,"code":509,"language":113,"meta":114,"style":114},"${TAO_SKILL_BANK_PATH:-~\u002Ftao-skills-external}\u002Fscripts\u002Flist_automl_support.py \\\n  --skill-bank ${TAO_SKILL_BANK_PATH:-~\u002Ftao-skills-external} --format text\n",[511],{"type":46,"tag":61,"props":512,"children":513},{"__ignoreMap":114},[514,550],{"type":46,"tag":120,"props":515,"children":516},{"class":122,"line":123},[517,521,525,529,533,537,541,545],{"type":46,"tag":120,"props":518,"children":519},{"style":127},[520],{"type":52,"value":130},{"type":46,"tag":120,"props":522,"children":523},{"style":133},[524],{"type":52,"value":136},{"type":46,"tag":120,"props":526,"children":527},{"style":127},[528],{"type":52,"value":141},{"type":46,"tag":120,"props":530,"children":531},{"style":133},[532],{"type":52,"value":146},{"type":46,"tag":120,"props":534,"children":535},{"style":127},[536],{"type":52,"value":151},{"type":46,"tag":120,"props":538,"children":539},{"style":133},[540],{"type":52,"value":156},{"type":46,"tag":120,"props":542,"children":543},{"style":127},[544],{"type":52,"value":161},{"type":46,"tag":120,"props":546,"children":547},{"style":133},[548],{"type":52,"value":549},"\u002Fscripts\u002Flist_automl_support.py \\\n",{"type":46,"tag":120,"props":551,"children":552},{"class":122,"line":169},[553,557,561,565,569,573,577,581,585,589],{"type":46,"tag":120,"props":554,"children":555},{"style":173},[556],{"type":52,"value":176},{"type":46,"tag":120,"props":558,"children":559},{"style":127},[560],{"type":52,"value":181},{"type":46,"tag":120,"props":562,"children":563},{"style":133},[564],{"type":52,"value":136},{"type":46,"tag":120,"props":566,"children":567},{"style":127},[568],{"type":52,"value":141},{"type":46,"tag":120,"props":570,"children":571},{"style":133},[572],{"type":52,"value":146},{"type":46,"tag":120,"props":574,"children":575},{"style":127},[576],{"type":52,"value":151},{"type":46,"tag":120,"props":578,"children":579},{"style":133},[580],{"type":52,"value":156},{"type":46,"tag":120,"props":582,"children":583},{"style":127},[584],{"type":52,"value":161},{"type":46,"tag":120,"props":586,"children":587},{"style":208},[588],{"type":52,"value":211},{"type":46,"tag":120,"props":590,"children":591},{"style":208},[592],{"type":52,"value":216},{"type":46,"tag":55,"props":594,"children":595},{},[596,598,604],{"type":52,"value":597},"AutoML support requires ",{"type":46,"tag":61,"props":599,"children":601},{"className":600},[],[602],{"type":52,"value":603},"skills\u002Fmodels\u002F\u003Cnetwork>\u002Fschemas\u002Ftrain.schema.json",{"type":52,"value":605}," to be\npackaged with the plugin and parse successfully as JSON. If that dataclass schema\nis missing or invalid, do not describe the model as AutoML-supported.",{"type":46,"tag":607,"props":608,"children":609},"style",{},[610],{"type":52,"value":611},"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":613,"total":717},[614,631,645,659,671,688,703],{"slug":615,"name":615,"fn":616,"description":617,"org":618,"tags":619,"stars":20,"repoUrl":21,"updatedAt":630},"accelerated-computing-cudf","accelerate data processing with cuDF","Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV\u002FParquet I\u002FO, nullable semantics, and multi-GPU DataFrame workloads.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[620,623,626,627],{"name":621,"slug":622,"type":15},"Data Analysis","data-analysis",{"name":624,"slug":625,"type":15},"Data Engineering","data-engineering",{"name":9,"slug":8,"type":15},{"name":628,"slug":629,"type":15},"Performance","performance","2026-07-14T05:28:43.176466",{"slug":632,"name":632,"fn":633,"description":634,"org":635,"tags":636,"stars":20,"repoUrl":21,"updatedAt":644},"aiq-deploy","deploy and manage NVIDIA AI-Q infrastructure","Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[637,640,643],{"name":638,"slug":639,"type":15},"Deployment","deployment",{"name":641,"slug":642,"type":15},"Infrastructure","infrastructure",{"name":9,"slug":8,"type":15},"2026-07-14T05:29:06.667109",{"slug":646,"name":646,"fn":647,"description":648,"org":649,"tags":650,"stars":20,"repoUrl":21,"updatedAt":658},"aiq-research","conduct deep research with AI-Q","Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[651,654,655],{"name":652,"slug":653,"type":15},"Agents","agents",{"name":9,"slug":8,"type":15},{"name":656,"slug":657,"type":15},"Research","research","2026-07-14T05:28:06.816956",{"slug":660,"name":660,"fn":661,"description":662,"org":663,"tags":664,"stars":20,"repoUrl":21,"updatedAt":670},"amc-run-sample-calibration","run AMC sample dataset calibration","Run end-to-end calibration on the shipped sample dataset (sdg_08_2_sample_data_010926.zip) against a running AMC microservice. Use when user says 'test sample dataset', 'run sample calibration', 'verify AMC install', or 'launch and test'.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[665,666,667],{"name":621,"slug":622,"type":15},{"name":9,"slug":8,"type":15},{"name":668,"slug":669,"type":15},"Testing","testing","2026-07-17T05:29:03.913266",{"slug":672,"name":672,"fn":673,"description":674,"org":675,"tags":676,"stars":20,"repoUrl":21,"updatedAt":687},"amc-run-video-calibration","calibrate video datasets with AutoMagicCalib","Calibrate a new dataset from pre-recorded video files via the AutoMagicCalib REST API. Use when user has local MP4s and says 'calibrate my videos', 'run AMC on these videos', or similar. For RTSP\u002Flive streams, use amc-run-rtsp-calibration instead.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[677,680,683,684],{"name":678,"slug":679,"type":15},"Automation","automation",{"name":681,"slug":682,"type":15},"Imaging","imaging",{"name":9,"slug":8,"type":15},{"name":685,"slug":686,"type":15},"Video","video","2026-07-17T05:28:53.905004",{"slug":689,"name":689,"fn":690,"description":691,"org":692,"tags":693,"stars":20,"repoUrl":21,"updatedAt":702},"amc-setup-calibration-stack","deploy AutoMagicCalib microservice with Docker","Launch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy auto calibration', 'launch auto calibration', 'launch AMC', 'start MS+UI', or 'set up auto-magic-calib'. Requires NGC API key.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[694,695,698,699],{"name":638,"slug":639,"type":15},{"name":696,"slug":697,"type":15},"Docker","docker",{"name":9,"slug":8,"type":15},{"name":700,"slug":701,"type":15},"Operations","operations","2026-07-17T05:28:56.913999",{"slug":704,"name":704,"fn":705,"description":706,"org":707,"tags":708,"stars":20,"repoUrl":21,"updatedAt":716},"cudaq-guide","develop quantum applications with CUDA-Q","CUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[709,710,713],{"name":9,"slug":8,"type":15},{"name":711,"slug":712,"type":15},"Quantum Computing","quantum-computing",{"name":714,"slug":715,"type":15},"Simulation","simulation","2026-07-14T05:26:58.898253",305,{"items":719,"total":868},[720,736,752,763,775,789,802,816,827,836,850,859],{"slug":721,"name":721,"fn":722,"description":723,"org":724,"tags":725,"stars":733,"repoUrl":734,"updatedAt":735},"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},[726,727,730],{"name":13,"slug":14,"type":15},{"name":728,"slug":729,"type":15},"MCP","mcp",{"name":731,"slug":732,"type":15},"Search","search",21777,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FNemoClaw","2026-07-20T06:00:01.461044",{"slug":737,"name":737,"fn":738,"description":739,"org":740,"tags":741,"stars":749,"repoUrl":750,"updatedAt":751},"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},[742,745,746],{"name":743,"slug":744,"type":15},"Containers","containers",{"name":638,"slug":639,"type":15},{"name":747,"slug":748,"type":15},"Python","python",17049,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FMegatron-LM","2026-07-27T06:06:11.249662",{"slug":753,"name":753,"fn":754,"description":755,"org":756,"tags":757,"stars":749,"repoUrl":750,"updatedAt":762},"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},[758,761],{"name":759,"slug":760,"type":15},"CI\u002FCD","ci-cd",{"name":638,"slug":639,"type":15},"2026-07-14T05:25:59.97109",{"slug":764,"name":764,"fn":765,"description":766,"org":767,"tags":768,"stars":749,"repoUrl":750,"updatedAt":774},"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},[769,770,771],{"name":759,"slug":760,"type":15},{"name":638,"slug":639,"type":15},{"name":772,"slug":773,"type":15},"GitHub","github","2026-07-27T06:06:12.278222",{"slug":776,"name":776,"fn":777,"description":778,"org":779,"tags":780,"stars":749,"repoUrl":750,"updatedAt":788},"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},[781,784,785],{"name":782,"slug":783,"type":15},"Debugging","debugging",{"name":772,"slug":773,"type":15},{"name":786,"slug":787,"type":15},"Triage","triage","2026-07-14T05:25:57.442089",{"slug":790,"name":790,"fn":791,"description":792,"org":793,"tags":794,"stars":749,"repoUrl":750,"updatedAt":801},"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},[795,798],{"name":796,"slug":797,"type":15},"Best Practices","best-practices",{"name":799,"slug":800,"type":15},"Code Analysis","code-analysis","2026-07-14T05:25:56.18433",{"slug":803,"name":803,"fn":804,"description":805,"org":806,"tags":807,"stars":749,"repoUrl":750,"updatedAt":815},"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.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[808,811,814],{"name":809,"slug":810,"type":15},"Machine Learning","machine-learning",{"name":812,"slug":813,"type":15},"Migration","migration",{"name":9,"slug":8,"type":15},"2026-07-17T06:07:11.777011",{"slug":817,"name":817,"fn":818,"description":819,"org":820,"tags":821,"stars":749,"repoUrl":750,"updatedAt":826},"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},[822,825],{"name":823,"slug":824,"type":15},"QA","qa",{"name":668,"slug":669,"type":15},"2026-07-14T05:25:53.673039",{"slug":828,"name":828,"fn":829,"description":830,"org":831,"tags":832,"stars":749,"repoUrl":750,"updatedAt":835},"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},[833,834],{"name":638,"slug":639,"type":15},{"name":641,"slug":642,"type":15},"2026-07-14T05:25:49.362534",{"slug":837,"name":837,"fn":838,"description":839,"org":840,"tags":841,"stars":749,"repoUrl":750,"updatedAt":849},"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},[842,845,846],{"name":843,"slug":844,"type":15},"Code Review","code-review",{"name":772,"slug":773,"type":15},{"name":847,"slug":848,"type":15},"Pull Requests","pull-requests","2026-07-14T05:26:01.226578",{"slug":851,"name":851,"fn":852,"description":853,"org":854,"tags":855,"stars":749,"repoUrl":750,"updatedAt":858},"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},[856,857],{"name":823,"slug":824,"type":15},{"name":668,"slug":669,"type":15},"2026-07-14T05:25:54.928983",{"slug":860,"name":860,"fn":861,"description":862,"org":863,"tags":864,"stars":749,"repoUrl":750,"updatedAt":867},"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},[865,866],{"name":678,"slug":679,"type":15},{"name":759,"slug":760,"type":15},"2026-07-30T05:29:03.275638",496]