[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-nvidia-dicom-series-to-volume":3,"mdc-rhdf3p-key":34,"related-repo-nvidia-dicom-series-to-volume":624,"related-org-nvidia-dicom-series-to-volume":726},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":29,"sourceUrl":32,"mdContent":33},"dicom-series-to-volume","convert DICOM series to NIfTI volumes","Used for converting one CT DICOM series folder to a HU NIfTI volume with affine evidence. Not for multi-frame DICOM or clinical use.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},"nvidia","NVIDIA","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fnvidia.png",[12,16,19,20],{"name":13,"slug":14,"type":15},"Data Analysis","data-analysis","tag",{"name":17,"slug":18,"type":15},"Medical Necessity","medical-necessity",{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},"Imaging","imaging",2473,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002Fskills","2026-07-14T05:30:01.836095","Apache-2.0",281,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":31},[],"AI agent skills published by NVIDIA","https:\u002F\u002Fgithub.com\u002FNVIDIA\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Fdicom-series-to-volume","---\nname: dicom-series-to-volume\ndescription: Used for converting one CT DICOM series folder to a HU NIfTI volume with affine evidence. Not for multi-frame DICOM or clinical use.\nlicense: Apache-2.0\nallowed-tools: Bash\nmetadata:\n  author: NVIDIA MedTech Team\n  tags:\n    - MedTech\n    - DICOM\n    - NIfTI\n---\n\n# dicom_series_to_volume\n\n## Purpose\n- Used for converting one CT DICOM series folder to a HU NIfTI volume with affine evidence. Not for multi-frame DICOM or clinical use.\n- Use the wrapper exactly as documented; do not replace the upstream entrypoint with a handwritten implementation.\n- Manifest I\u002FO: inputs are `dicom_dir`; outputs are `nifti_volume` and `result_json`.\n\n## Instructions\n- Read `skill_manifest.yaml` before changing arguments, side effects, or validation gates.\n- Run `scripts\u002Fseries_to_volume.py` through the documented command below; keep outputs under a caller-provided run directory.\n- If a host agent exposes `run_script`, use `run_script(\"scripts\u002Fseries_to_volume.py\", args=[...])`; otherwise run the Bash\u002FPython command shown below.\n- Check the emitted JSON and the paired `dicom_volume_quality_v1` verifier before treating the run as evidence.\n\n## Available Scripts\n| Script | Purpose | Arguments |\n|---|---|---|\n| `scripts\u002Fseries_to_volume.py` | Primary entrypoint declared by skill_manifest.yaml. | `PATH_TO_DICOM_DIR [--output OUT.nii.gz]` |\n\n## Prerequisites\n- Runtime requirements: Python packages listed in `runtime.side_effects.pip_packages`.\n- Run commands from the repository root unless an existing section below says otherwise.\n\n## Limitations\n- Single-series only; multi-series input is rejected at preflight.\n- Multi-frame DICOM (NumberOfFrames > 1 per file) not supported.\n- Compressed transfer syntaxes (JPEG \u002F JPEG2000 \u002F RLE) not supported.\n- No voxel reorientation. The affine is derived from DICOM headers and represented in NIfTI\u002FRAS coordinates; a downstream gate (e.g. expected_axcodes) is expected to assert orientation before this volume is fed to a segmentation model.\n- Not for clinical deployment, autonomous diagnosis, regulatory submission, production inference (use a vetted converter such as dcm2niix for that).\n\n## Troubleshooting\n| Error | Cause | Fix |\n|---|---|---|\n| Missing dependency or import error | Runtime package drift from `skill_manifest.yaml`. | Install the packages declared in the manifest or use the documented setup command. |\n| Empty or schema-invalid output | Wrong input path, unsupported modality, or upstream failure. | Re-run with a known fixture and inspect the wrapper JSON plus stderr. |\n| Validation gate failure | Output violated a declared engineering invariant. | Keep the failed evidence pack and use the gate message to repair inputs or wrapper code. |\n\nReads one DICOM series, sorts slices by `ImagePositionPatient`, applies\n`RescaleSlope` and `RescaleIntercept`, builds an affine from orientation and\nspacing tags, and writes a `.nii.gz` plus JSON summary.\n\n```bash\npython scripts\u002Fseries_to_volume.py PATH_TO_DICOM_DIR --output PATH_TO_OUT.nii.gz\n```\n\nFor a trusted run with the paired verifier:\n\n```bash\npython -m eval_engine.run_trusted skills\u002Fdicom-series-to-volume \\\n  --fixture PATH_TO_DICOM_DIR \\\n  --out runs\u002Fdicom_series_to_volume_trusted\n```\n\nKey output fields: `n_slices`, `series_instance_uid`, `output.path`,\n`output.shape`, `output.spacing`, `output.axcodes`, `output.affine`,\n`hu_range`, and `runtime.conversion_seconds`.\n\nScope limits: single-series CT only; no multi-frame DICOM, compressed transfer\nsyntax handling, RT structure sets, auto-reorientation, or clinical use.\n",{"data":35,"body":43},{"name":4,"description":6,"license":26,"allowed-tools":36,"metadata":37},"Bash",{"author":38,"tags":39},"NVIDIA MedTech Team",[40,41,42],"MedTech","DICOM","NIfTI",{"type":44,"children":45},"root",[46,54,61,105,111,174,180,237,243,263,269,297,303,390,427,471,476,542,613,618],{"type":47,"tag":48,"props":49,"children":51},"element","h1",{"id":50},"dicom_series_to_volume",[52],{"type":53,"value":50},"text",{"type":47,"tag":55,"props":56,"children":58},"h2",{"id":57},"purpose",[59],{"type":53,"value":60},"Purpose",{"type":47,"tag":62,"props":63,"children":64},"ul",{},[65,70,75],{"type":47,"tag":66,"props":67,"children":68},"li",{},[69],{"type":53,"value":6},{"type":47,"tag":66,"props":71,"children":72},{},[73],{"type":53,"value":74},"Use the wrapper exactly as documented; do not replace the upstream entrypoint with a handwritten implementation.",{"type":47,"tag":66,"props":76,"children":77},{},[78,80,87,89,95,97,103],{"type":53,"value":79},"Manifest I\u002FO: inputs are ",{"type":47,"tag":81,"props":82,"children":84},"code",{"className":83},[],[85],{"type":53,"value":86},"dicom_dir",{"type":53,"value":88},"; outputs are ",{"type":47,"tag":81,"props":90,"children":92},{"className":91},[],[93],{"type":53,"value":94},"nifti_volume",{"type":53,"value":96}," and ",{"type":47,"tag":81,"props":98,"children":100},{"className":99},[],[101],{"type":53,"value":102},"result_json",{"type":53,"value":104},".",{"type":47,"tag":55,"props":106,"children":108},{"id":107},"instructions",[109],{"type":53,"value":110},"Instructions",{"type":47,"tag":62,"props":112,"children":113},{},[114,127,140,161],{"type":47,"tag":66,"props":115,"children":116},{},[117,119,125],{"type":53,"value":118},"Read ",{"type":47,"tag":81,"props":120,"children":122},{"className":121},[],[123],{"type":53,"value":124},"skill_manifest.yaml",{"type":53,"value":126}," before changing arguments, side effects, or validation gates.",{"type":47,"tag":66,"props":128,"children":129},{},[130,132,138],{"type":53,"value":131},"Run ",{"type":47,"tag":81,"props":133,"children":135},{"className":134},[],[136],{"type":53,"value":137},"scripts\u002Fseries_to_volume.py",{"type":53,"value":139}," through the documented command below; keep outputs under a caller-provided run directory.",{"type":47,"tag":66,"props":141,"children":142},{},[143,145,151,153,159],{"type":53,"value":144},"If a host agent exposes ",{"type":47,"tag":81,"props":146,"children":148},{"className":147},[],[149],{"type":53,"value":150},"run_script",{"type":53,"value":152},", use ",{"type":47,"tag":81,"props":154,"children":156},{"className":155},[],[157],{"type":53,"value":158},"run_script(\"scripts\u002Fseries_to_volume.py\", args=[...])",{"type":53,"value":160},"; otherwise run the Bash\u002FPython command shown below.",{"type":47,"tag":66,"props":162,"children":163},{},[164,166,172],{"type":53,"value":165},"Check the emitted JSON and the paired ",{"type":47,"tag":81,"props":167,"children":169},{"className":168},[],[170],{"type":53,"value":171},"dicom_volume_quality_v1",{"type":53,"value":173}," verifier before treating the run as evidence.",{"type":47,"tag":55,"props":175,"children":177},{"id":176},"available-scripts",[178],{"type":53,"value":179},"Available Scripts",{"type":47,"tag":181,"props":182,"children":183},"table",{},[184,207],{"type":47,"tag":185,"props":186,"children":187},"thead",{},[188],{"type":47,"tag":189,"props":190,"children":191},"tr",{},[192,198,202],{"type":47,"tag":193,"props":194,"children":195},"th",{},[196],{"type":53,"value":197},"Script",{"type":47,"tag":193,"props":199,"children":200},{},[201],{"type":53,"value":60},{"type":47,"tag":193,"props":203,"children":204},{},[205],{"type":53,"value":206},"Arguments",{"type":47,"tag":208,"props":209,"children":210},"tbody",{},[211],{"type":47,"tag":189,"props":212,"children":213},{},[214,223,228],{"type":47,"tag":215,"props":216,"children":217},"td",{},[218],{"type":47,"tag":81,"props":219,"children":221},{"className":220},[],[222],{"type":53,"value":137},{"type":47,"tag":215,"props":224,"children":225},{},[226],{"type":53,"value":227},"Primary entrypoint declared by skill_manifest.yaml.",{"type":47,"tag":215,"props":229,"children":230},{},[231],{"type":47,"tag":81,"props":232,"children":234},{"className":233},[],[235],{"type":53,"value":236},"PATH_TO_DICOM_DIR [--output OUT.nii.gz]",{"type":47,"tag":55,"props":238,"children":240},{"id":239},"prerequisites",[241],{"type":53,"value":242},"Prerequisites",{"type":47,"tag":62,"props":244,"children":245},{},[246,258],{"type":47,"tag":66,"props":247,"children":248},{},[249,251,257],{"type":53,"value":250},"Runtime requirements: Python packages listed in ",{"type":47,"tag":81,"props":252,"children":254},{"className":253},[],[255],{"type":53,"value":256},"runtime.side_effects.pip_packages",{"type":53,"value":104},{"type":47,"tag":66,"props":259,"children":260},{},[261],{"type":53,"value":262},"Run commands from the repository root unless an existing section below says otherwise.",{"type":47,"tag":55,"props":264,"children":266},{"id":265},"limitations",[267],{"type":53,"value":268},"Limitations",{"type":47,"tag":62,"props":270,"children":271},{},[272,277,282,287,292],{"type":47,"tag":66,"props":273,"children":274},{},[275],{"type":53,"value":276},"Single-series only; multi-series input is rejected at preflight.",{"type":47,"tag":66,"props":278,"children":279},{},[280],{"type":53,"value":281},"Multi-frame DICOM (NumberOfFrames > 1 per file) not supported.",{"type":47,"tag":66,"props":283,"children":284},{},[285],{"type":53,"value":286},"Compressed transfer syntaxes (JPEG \u002F JPEG2000 \u002F RLE) not supported.",{"type":47,"tag":66,"props":288,"children":289},{},[290],{"type":53,"value":291},"No voxel reorientation. The affine is derived from DICOM headers and represented in NIfTI\u002FRAS coordinates; a downstream gate (e.g. expected_axcodes) is expected to assert orientation before this volume is fed to a segmentation model.",{"type":47,"tag":66,"props":293,"children":294},{},[295],{"type":53,"value":296},"Not for clinical deployment, autonomous diagnosis, regulatory submission, production inference (use a vetted converter such as dcm2niix for that).",{"type":47,"tag":55,"props":298,"children":300},{"id":299},"troubleshooting",[301],{"type":53,"value":302},"Troubleshooting",{"type":47,"tag":181,"props":304,"children":305},{},[306,327],{"type":47,"tag":185,"props":307,"children":308},{},[309],{"type":47,"tag":189,"props":310,"children":311},{},[312,317,322],{"type":47,"tag":193,"props":313,"children":314},{},[315],{"type":53,"value":316},"Error",{"type":47,"tag":193,"props":318,"children":319},{},[320],{"type":53,"value":321},"Cause",{"type":47,"tag":193,"props":323,"children":324},{},[325],{"type":53,"value":326},"Fix",{"type":47,"tag":208,"props":328,"children":329},{},[330,354,372],{"type":47,"tag":189,"props":331,"children":332},{},[333,338,349],{"type":47,"tag":215,"props":334,"children":335},{},[336],{"type":53,"value":337},"Missing dependency or import error",{"type":47,"tag":215,"props":339,"children":340},{},[341,343,348],{"type":53,"value":342},"Runtime package drift from ",{"type":47,"tag":81,"props":344,"children":346},{"className":345},[],[347],{"type":53,"value":124},{"type":53,"value":104},{"type":47,"tag":215,"props":350,"children":351},{},[352],{"type":53,"value":353},"Install the packages declared in the manifest or use the documented setup command.",{"type":47,"tag":189,"props":355,"children":356},{},[357,362,367],{"type":47,"tag":215,"props":358,"children":359},{},[360],{"type":53,"value":361},"Empty or schema-invalid output",{"type":47,"tag":215,"props":363,"children":364},{},[365],{"type":53,"value":366},"Wrong input path, unsupported modality, or upstream failure.",{"type":47,"tag":215,"props":368,"children":369},{},[370],{"type":53,"value":371},"Re-run with a known fixture and inspect the wrapper JSON plus stderr.",{"type":47,"tag":189,"props":373,"children":374},{},[375,380,385],{"type":47,"tag":215,"props":376,"children":377},{},[378],{"type":53,"value":379},"Validation gate failure",{"type":47,"tag":215,"props":381,"children":382},{},[383],{"type":53,"value":384},"Output violated a declared engineering invariant.",{"type":47,"tag":215,"props":386,"children":387},{},[388],{"type":53,"value":389},"Keep the failed evidence pack and use the gate message to repair inputs or wrapper code.",{"type":47,"tag":391,"props":392,"children":393},"p",{},[394,396,402,404,410,411,417,419,425],{"type":53,"value":395},"Reads one DICOM series, sorts slices by ",{"type":47,"tag":81,"props":397,"children":399},{"className":398},[],[400],{"type":53,"value":401},"ImagePositionPatient",{"type":53,"value":403},", applies\n",{"type":47,"tag":81,"props":405,"children":407},{"className":406},[],[408],{"type":53,"value":409},"RescaleSlope",{"type":53,"value":96},{"type":47,"tag":81,"props":412,"children":414},{"className":413},[],[415],{"type":53,"value":416},"RescaleIntercept",{"type":53,"value":418},", builds an affine from orientation and\nspacing tags, and writes a ",{"type":47,"tag":81,"props":420,"children":422},{"className":421},[],[423],{"type":53,"value":424},".nii.gz",{"type":53,"value":426}," plus JSON summary.",{"type":47,"tag":428,"props":429,"children":434},"pre",{"className":430,"code":431,"language":432,"meta":433,"style":433},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","python scripts\u002Fseries_to_volume.py PATH_TO_DICOM_DIR --output PATH_TO_OUT.nii.gz\n","bash","",[435],{"type":47,"tag":81,"props":436,"children":437},{"__ignoreMap":433},[438],{"type":47,"tag":439,"props":440,"children":443},"span",{"class":441,"line":442},"line",1,[444,450,456,461,466],{"type":47,"tag":439,"props":445,"children":447},{"style":446},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[448],{"type":53,"value":449},"python",{"type":47,"tag":439,"props":451,"children":453},{"style":452},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[454],{"type":53,"value":455}," scripts\u002Fseries_to_volume.py",{"type":47,"tag":439,"props":457,"children":458},{"style":452},[459],{"type":53,"value":460}," PATH_TO_DICOM_DIR",{"type":47,"tag":439,"props":462,"children":463},{"style":452},[464],{"type":53,"value":465}," --output",{"type":47,"tag":439,"props":467,"children":468},{"style":452},[469],{"type":53,"value":470}," PATH_TO_OUT.nii.gz\n",{"type":47,"tag":391,"props":472,"children":473},{},[474],{"type":53,"value":475},"For a trusted run with the paired verifier:",{"type":47,"tag":428,"props":477,"children":479},{"className":430,"code":478,"language":432,"meta":433,"style":433},"python -m eval_engine.run_trusted skills\u002Fdicom-series-to-volume \\\n  --fixture PATH_TO_DICOM_DIR \\\n  --out runs\u002Fdicom_series_to_volume_trusted\n",[480],{"type":47,"tag":81,"props":481,"children":482},{"__ignoreMap":433},[483,511,528],{"type":47,"tag":439,"props":484,"children":485},{"class":441,"line":442},[486,490,495,500,505],{"type":47,"tag":439,"props":487,"children":488},{"style":446},[489],{"type":53,"value":449},{"type":47,"tag":439,"props":491,"children":492},{"style":452},[493],{"type":53,"value":494}," -m",{"type":47,"tag":439,"props":496,"children":497},{"style":452},[498],{"type":53,"value":499}," eval_engine.run_trusted",{"type":47,"tag":439,"props":501,"children":502},{"style":452},[503],{"type":53,"value":504}," skills\u002Fdicom-series-to-volume",{"type":47,"tag":439,"props":506,"children":508},{"style":507},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[509],{"type":53,"value":510}," \\\n",{"type":47,"tag":439,"props":512,"children":514},{"class":441,"line":513},2,[515,520,524],{"type":47,"tag":439,"props":516,"children":517},{"style":452},[518],{"type":53,"value":519},"  --fixture",{"type":47,"tag":439,"props":521,"children":522},{"style":452},[523],{"type":53,"value":460},{"type":47,"tag":439,"props":525,"children":526},{"style":507},[527],{"type":53,"value":510},{"type":47,"tag":439,"props":529,"children":531},{"class":441,"line":530},3,[532,537],{"type":47,"tag":439,"props":533,"children":534},{"style":452},[535],{"type":53,"value":536},"  --out",{"type":47,"tag":439,"props":538,"children":539},{"style":452},[540],{"type":53,"value":541}," runs\u002Fdicom_series_to_volume_trusted\n",{"type":47,"tag":391,"props":543,"children":544},{},[545,547,553,555,561,562,568,570,576,577,583,584,590,591,597,598,604,606,612],{"type":53,"value":546},"Key output fields: ",{"type":47,"tag":81,"props":548,"children":550},{"className":549},[],[551],{"type":53,"value":552},"n_slices",{"type":53,"value":554},", ",{"type":47,"tag":81,"props":556,"children":558},{"className":557},[],[559],{"type":53,"value":560},"series_instance_uid",{"type":53,"value":554},{"type":47,"tag":81,"props":563,"children":565},{"className":564},[],[566],{"type":53,"value":567},"output.path",{"type":53,"value":569},",\n",{"type":47,"tag":81,"props":571,"children":573},{"className":572},[],[574],{"type":53,"value":575},"output.shape",{"type":53,"value":554},{"type":47,"tag":81,"props":578,"children":580},{"className":579},[],[581],{"type":53,"value":582},"output.spacing",{"type":53,"value":554},{"type":47,"tag":81,"props":585,"children":587},{"className":586},[],[588],{"type":53,"value":589},"output.axcodes",{"type":53,"value":554},{"type":47,"tag":81,"props":592,"children":594},{"className":593},[],[595],{"type":53,"value":596},"output.affine",{"type":53,"value":569},{"type":47,"tag":81,"props":599,"children":601},{"className":600},[],[602],{"type":53,"value":603},"hu_range",{"type":53,"value":605},", and ",{"type":47,"tag":81,"props":607,"children":609},{"className":608},[],[610],{"type":53,"value":611},"runtime.conversion_seconds",{"type":53,"value":104},{"type":47,"tag":391,"props":614,"children":615},{},[616],{"type":53,"value":617},"Scope limits: single-series CT only; no multi-frame DICOM, compressed transfer\nsyntax handling, RT structure sets, auto-reorientation, or clinical use.",{"type":47,"tag":619,"props":620,"children":621},"style",{},[622],{"type":53,"value":623},"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":625,"total":725},[626,641,655,669,681,696,711],{"slug":627,"name":627,"fn":628,"description":629,"org":630,"tags":631,"stars":23,"repoUrl":24,"updatedAt":640},"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},[632,633,636,637],{"name":13,"slug":14,"type":15},{"name":634,"slug":635,"type":15},"Data Engineering","data-engineering",{"name":9,"slug":8,"type":15},{"name":638,"slug":639,"type":15},"Performance","performance","2026-07-14T05:28:43.176466",{"slug":642,"name":642,"fn":643,"description":644,"org":645,"tags":646,"stars":23,"repoUrl":24,"updatedAt":654},"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},[647,650,653],{"name":648,"slug":649,"type":15},"Deployment","deployment",{"name":651,"slug":652,"type":15},"Infrastructure","infrastructure",{"name":9,"slug":8,"type":15},"2026-07-14T05:29:06.667109",{"slug":656,"name":656,"fn":657,"description":658,"org":659,"tags":660,"stars":23,"repoUrl":24,"updatedAt":668},"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},[661,664,665],{"name":662,"slug":663,"type":15},"Agents","agents",{"name":9,"slug":8,"type":15},{"name":666,"slug":667,"type":15},"Research","research","2026-07-14T05:28:06.816956",{"slug":670,"name":670,"fn":671,"description":672,"org":673,"tags":674,"stars":23,"repoUrl":24,"updatedAt":680},"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},[675,676,677],{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"name":678,"slug":679,"type":15},"Testing","testing","2026-07-17T05:29:03.913266",{"slug":682,"name":682,"fn":683,"description":684,"org":685,"tags":686,"stars":23,"repoUrl":24,"updatedAt":695},"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},[687,690,691,692],{"name":688,"slug":689,"type":15},"Automation","automation",{"name":21,"slug":22,"type":15},{"name":9,"slug":8,"type":15},{"name":693,"slug":694,"type":15},"Video","video","2026-07-17T05:28:53.905004",{"slug":697,"name":697,"fn":698,"description":699,"org":700,"tags":701,"stars":23,"repoUrl":24,"updatedAt":710},"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},[702,703,706,707],{"name":648,"slug":649,"type":15},{"name":704,"slug":705,"type":15},"Docker","docker",{"name":9,"slug":8,"type":15},{"name":708,"slug":709,"type":15},"Operations","operations","2026-07-17T05:28:56.913999",{"slug":712,"name":712,"fn":713,"description":714,"org":715,"tags":716,"stars":23,"repoUrl":24,"updatedAt":724},"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},[717,718,721],{"name":9,"slug":8,"type":15},{"name":719,"slug":720,"type":15},"Quantum Computing","quantum-computing",{"name":722,"slug":723,"type":15},"Simulation","simulation","2026-07-14T05:26:58.898253",305,{"items":727,"total":877},[728,746,761,772,784,798,811,825,836,845,859,868],{"slug":729,"name":729,"fn":730,"description":731,"org":732,"tags":733,"stars":743,"repoUrl":744,"updatedAt":745},"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},[734,737,740],{"name":735,"slug":736,"type":15},"Documentation","documentation",{"name":738,"slug":739,"type":15},"MCP","mcp",{"name":741,"slug":742,"type":15},"Search","search",21777,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FNemoClaw","2026-07-20T06:00:01.461044",{"slug":747,"name":747,"fn":748,"description":749,"org":750,"tags":751,"stars":758,"repoUrl":759,"updatedAt":760},"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},[752,755,756],{"name":753,"slug":754,"type":15},"Containers","containers",{"name":648,"slug":649,"type":15},{"name":757,"slug":449,"type":15},"Python",17049,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FMegatron-LM","2026-07-27T06:06:11.249662",{"slug":762,"name":762,"fn":763,"description":764,"org":765,"tags":766,"stars":758,"repoUrl":759,"updatedAt":771},"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},[767,770],{"name":768,"slug":769,"type":15},"CI\u002FCD","ci-cd",{"name":648,"slug":649,"type":15},"2026-07-14T05:25:59.97109",{"slug":773,"name":773,"fn":774,"description":775,"org":776,"tags":777,"stars":758,"repoUrl":759,"updatedAt":783},"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},[778,779,780],{"name":768,"slug":769,"type":15},{"name":648,"slug":649,"type":15},{"name":781,"slug":782,"type":15},"GitHub","github","2026-07-27T06:06:12.278222",{"slug":785,"name":785,"fn":786,"description":787,"org":788,"tags":789,"stars":758,"repoUrl":759,"updatedAt":797},"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},[790,793,794],{"name":791,"slug":792,"type":15},"Debugging","debugging",{"name":781,"slug":782,"type":15},{"name":795,"slug":796,"type":15},"Triage","triage","2026-07-14T05:25:57.442089",{"slug":799,"name":799,"fn":800,"description":801,"org":802,"tags":803,"stars":758,"repoUrl":759,"updatedAt":810},"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},[804,807],{"name":805,"slug":806,"type":15},"Best Practices","best-practices",{"name":808,"slug":809,"type":15},"Code Analysis","code-analysis","2026-07-14T05:25:56.18433",{"slug":812,"name":812,"fn":813,"description":814,"org":815,"tags":816,"stars":758,"repoUrl":759,"updatedAt":824},"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},[817,820,823],{"name":818,"slug":819,"type":15},"Machine Learning","machine-learning",{"name":821,"slug":822,"type":15},"Migration","migration",{"name":9,"slug":8,"type":15},"2026-07-17T06:07:11.777011",{"slug":826,"name":826,"fn":827,"description":828,"org":829,"tags":830,"stars":758,"repoUrl":759,"updatedAt":835},"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},[831,834],{"name":832,"slug":833,"type":15},"QA","qa",{"name":678,"slug":679,"type":15},"2026-07-14T05:25:53.673039",{"slug":837,"name":837,"fn":838,"description":839,"org":840,"tags":841,"stars":758,"repoUrl":759,"updatedAt":844},"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},[842,843],{"name":648,"slug":649,"type":15},{"name":651,"slug":652,"type":15},"2026-07-14T05:25:49.362534",{"slug":846,"name":846,"fn":847,"description":848,"org":849,"tags":850,"stars":758,"repoUrl":759,"updatedAt":858},"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},[851,854,855],{"name":852,"slug":853,"type":15},"Code Review","code-review",{"name":781,"slug":782,"type":15},{"name":856,"slug":857,"type":15},"Pull Requests","pull-requests","2026-07-14T05:26:01.226578",{"slug":860,"name":860,"fn":861,"description":862,"org":863,"tags":864,"stars":758,"repoUrl":759,"updatedAt":867},"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},[865,866],{"name":832,"slug":833,"type":15},{"name":678,"slug":679,"type":15},"2026-07-14T05:25:54.928983",{"slug":869,"name":869,"fn":870,"description":871,"org":872,"tags":873,"stars":758,"repoUrl":759,"updatedAt":876},"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},[874,875],{"name":688,"slug":689,"type":15},{"name":768,"slug":769,"type":15},"2026-07-30T05:29:03.275638",496]