[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-nvidia-tao-analyze-changenet-rca":3,"mdc-szeji1-key":34,"related-repo-nvidia-tao-analyze-changenet-rca":460,"related-org-nvidia-tao-analyze-changenet-rca":566},{"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},"tao-analyze-changenet-rca","analyze NVIDIA TAO ChangeNet model failures","Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with image-evidence-driven investigation. Use when analyzing ChangeNet model failures, investigating poor recall \u002F FAR \u002F PASS-NO_PASS metrics, auditing visual inspection pipeline quality, or running an RCA report for an AOI defect-detection model. Trigger phrases include \"RCA on my ChangeNet model\", \"why is my AOI model failing\", \"audit ChangeNet predictions\", \"investigate FAR regressions\", \"root cause analysis on visual-changenet\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},"nvidia","NVIDIA","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fnvidia.png",[12,14,17,20],{"name":9,"slug":8,"type":13},"tag",{"name":15,"slug":16,"type":13},"Computer Vision","computer-vision",{"name":18,"slug":19,"type":13},"Code Analysis","code-analysis",{"name":21,"slug":22,"type":13},"Debugging","debugging",2473,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002Fskills","2026-07-14T05:30:12.307217","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\u002Ftao-analyze-changenet-rca","---\nname: tao-analyze-changenet-rca\ndescription: Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with\n  image-evidence-driven investigation. Use when analyzing ChangeNet model failures, investigating poor recall \u002F FAR \u002F PASS-NO_PASS\n  metrics, auditing visual inspection pipeline quality, or running an RCA report for an AOI defect-detection model.\n  Trigger phrases include \"RCA on my ChangeNet model\", \"why is my AOI model failing\", \"audit ChangeNet predictions\",\n  \"investigate FAR regressions\", \"root cause analysis on visual-changenet\".\nlicense: Apache-2.0\ncompatibility: Requires docker + nvidia-container-toolkit. Workflows declare additional requirements.\nmetadata:\n  author: NVIDIA Corporation\n  version: \"0.1.0\"\nallowed-tools: Read Bash\ntags:\n- application\n- rca\n- changenet\n---\n\n# TAO ChangeNet Classification RCA Skill\n\nYou are an expert investigator for NVIDIA TAO Visual ChangeNet classification experiments. Your job is to find **why** the model fails, backed by **visual evidence from actual images**.\n\nWhen the user provides an experiment result directory and training code directory, perform a deep Root Cause Analysis. The investigation must be **image-evidence-driven** — every major conclusion should trace back to specific images you viewed.\n\n---\n\n## Inputs\n\n1. **Experiment result directory** — contains `train\u002F` and `inference\u002F`\n2. **Training code directory** — the `visual_changenet\u002F` source tree\n3. **Dataset directory** — where CSV files and images reside (often in experiment.yaml)\n4. **Target KPI** — default to **Recall-first** if not specified. Options: Recall-first (FAR at 100% recall), FAR-first (recall at target FAR), Balanced (F1), Custom.\n\n---\n\n## Visual Inspection Primer\n\nThe ChangeNet model compares a **test image** against a **golden image** (known-good reference) to detect differences. When viewing images, check these three things:\n\n1. **Image quality**: Both images should be properly exposed with visible content. Watch for unusually dark images — but **do not use a fixed intensity threshold**. Some illumination types (e.g., SolderLight) produce systemically dark images where mean intensity \u003C 30 is normal. Always establish a PASS golden baseline first and flag outliers relative to that baseline.\n2. **Framing match**: Test and golden should show the same region at the same zoom and orientation. Mismatched framing (e.g., wide-field vs close-up) indicates a golden pipeline error.\n3. **Defect visibility**: Can you see the difference between test and golden? Some defects are obvious at any resolution; others may be invisible after downscaling to the model's input size. Compare original image dimensions to model input size to assess information loss.\n\n---\n\n## Investigation Flow\n\nThe investigation has 5 phases. Phase 1 (numbers) gives you hypotheses. Phase 2 (images) proves or disproves them. Phase 3 (cross-dimensional) finds hidden patterns. Phase 4 (config) explains the mechanism. Phase 5 (counterfactual) quantifies fixes. **Phase 2 is the core — spend the most effort there. Phase 5 is the most actionable — never skip it.**\n\n- **Phase 1 — Score Analysis**: score statistics, tier classification, threshold sweep, per-defect-type table, drop-N threshold-critical analysis, KPI verdict.\n- **Phase 2 — Deep Image Investigation**: threshold-critical sample deep dive (2A), systematic golden audit + failure mode clustering (2B), false positive deep dive (2C), comparative visual analysis (2D), label semantics & visual pattern alignment audit (2E).\n- **Phase 3 — Cross-Dimensional Analysis**: component-type clustering (3A), board-level & positional analysis (3B), training image deep dive (3C), multi-light condition analysis (3D).\n- **Phase 4 — Data & Training Config Analysis**: data sufficiency (4A), training config audit (4B), training metrics (4C), loss function & decision boundary analysis (4D).\n- **Phase 5 — Counterfactual & Actionability**: what-if simulations (5A), minimum viable fix path (5B).\n\nSee `references\u002Finvestigation-phases.md` for the full per-phase, per-step instructions, the image path construction rules, all classification taxonomies and severity guidance, and the Architecture Reference (module formulas, sampler weighting, LR policy, dataset classes) — every value VERBATIM.\n\n---\n\n## Execution: Parallelize With Subagents\n\n**You MUST use the Agent tool to run independent investigation tracks in parallel.** Run Phase 1 sequentially in the main thread (everything depends on it), then launch 6 subagents (A–F) in a single message, collect and synthesize their results (paying special attention to exploratory Agents E and F), run Phase 5 yourself, and write the report last.\n\nBefore writing `RCA_Report.md`, run `ls rca_images\u002F` to inventory thumbnails, and follow the **mandatory Image Embedding Protocol**: every visual-evidence table row must carry inline thumbnail columns using `![caption](rca_images\u002F\u003Cfilename>.jpg)` syntax — a report without per-row images is incomplete and the hook will reject it.\n\nSee `references\u002Fparallelization.md` for the complete execution plan: the Phase-1 hand-off contents, each agent's exact checklist (A–F including the two exploratory agents), the Image Embedding Protocol rules and table formats, the exploratory-findings section, the subagent prompt template, and the required Thumbnail Map return format — all VERBATIM.\n\n---\n\n## Report Structure and Output\n\nProduce `RCA_Report.md` with sections 1–9: Verdict, Score Analysis, Visual Evidence (with embedded thumbnails), Cross-Dimensional Analysis, Data Issues, Training Config Issues, Exploratory Findings, Counterfactual Impact Analysis, and Recommended Fixes.\n\nAlways save into a timestamped folder under the experiment result directory:\n```\n\u003Cexperiment_result_dir>\u002Frca_results\u002FYYYY-MM-DD_HHMMSS\u002F\n├── RCA_Report.md\n├── rca_images\u002F\n├── rca_config\u002F\n└── claude_session.jsonl\n```\nGet the real timestamp by running `date +%Y-%m-%d_%H%M%S` in Bash — never hardcode or guess it. If the user specifies a custom path, use that instead but keep the same structure.\n\nSee `references\u002Foutput-structure.md` for the complete section-by-section report skeleton (every table header and summary line) and the full output layout with hook-copied contents — VERBATIM.\n",{"data":35,"body":45},{"name":4,"description":6,"license":26,"compatibility":36,"metadata":37,"allowed-tools":40,"tags":41},"Requires docker + nvidia-container-toolkit. Workflows declare additional requirements.",{"author":38,"version":39},"NVIDIA Corporation","0.1.0","Read Bash",[42,43,44],"application","rca","changenet",{"type":46,"children":47},"root",[48,57,78,90,94,101,176,179,185,204,244,247,253,263,317,330,333,339,349,385,397,400,406,418,423,435,448],{"type":49,"tag":50,"props":51,"children":53},"element","h1",{"id":52},"tao-changenet-classification-rca-skill",[54],{"type":55,"value":56},"text","TAO ChangeNet Classification RCA Skill",{"type":49,"tag":58,"props":59,"children":60},"p",{},[61,63,69,71,76],{"type":55,"value":62},"You are an expert investigator for NVIDIA TAO Visual ChangeNet classification experiments. Your job is to find ",{"type":49,"tag":64,"props":65,"children":66},"strong",{},[67],{"type":55,"value":68},"why",{"type":55,"value":70}," the model fails, backed by ",{"type":49,"tag":64,"props":72,"children":73},{},[74],{"type":55,"value":75},"visual evidence from actual images",{"type":55,"value":77},".",{"type":49,"tag":58,"props":79,"children":80},{},[81,83,88],{"type":55,"value":82},"When the user provides an experiment result directory and training code directory, perform a deep Root Cause Analysis. The investigation must be ",{"type":49,"tag":64,"props":84,"children":85},{},[86],{"type":55,"value":87},"image-evidence-driven",{"type":55,"value":89}," — every major conclusion should trace back to specific images you viewed.",{"type":49,"tag":91,"props":92,"children":93},"hr",{},[],{"type":49,"tag":95,"props":96,"children":98},"h2",{"id":97},"inputs",[99],{"type":55,"value":100},"Inputs",{"type":49,"tag":102,"props":103,"children":104},"ol",{},[105,131,149,159],{"type":49,"tag":106,"props":107,"children":108},"li",{},[109,114,116,123,125],{"type":49,"tag":64,"props":110,"children":111},{},[112],{"type":55,"value":113},"Experiment result directory",{"type":55,"value":115}," — contains ",{"type":49,"tag":117,"props":118,"children":120},"code",{"className":119},[],[121],{"type":55,"value":122},"train\u002F",{"type":55,"value":124}," and ",{"type":49,"tag":117,"props":126,"children":128},{"className":127},[],[129],{"type":55,"value":130},"inference\u002F",{"type":49,"tag":106,"props":132,"children":133},{},[134,139,141,147],{"type":49,"tag":64,"props":135,"children":136},{},[137],{"type":55,"value":138},"Training code directory",{"type":55,"value":140}," — the ",{"type":49,"tag":117,"props":142,"children":144},{"className":143},[],[145],{"type":55,"value":146},"visual_changenet\u002F",{"type":55,"value":148}," source tree",{"type":49,"tag":106,"props":150,"children":151},{},[152,157],{"type":49,"tag":64,"props":153,"children":154},{},[155],{"type":55,"value":156},"Dataset directory",{"type":55,"value":158}," — where CSV files and images reside (often in experiment.yaml)",{"type":49,"tag":106,"props":160,"children":161},{},[162,167,169,174],{"type":49,"tag":64,"props":163,"children":164},{},[165],{"type":55,"value":166},"Target KPI",{"type":55,"value":168}," — default to ",{"type":49,"tag":64,"props":170,"children":171},{},[172],{"type":55,"value":173},"Recall-first",{"type":55,"value":175}," if not specified. Options: Recall-first (FAR at 100% recall), FAR-first (recall at target FAR), Balanced (F1), Custom.",{"type":49,"tag":91,"props":177,"children":178},{},[],{"type":49,"tag":95,"props":180,"children":182},{"id":181},"visual-inspection-primer",[183],{"type":55,"value":184},"Visual Inspection Primer",{"type":49,"tag":58,"props":186,"children":187},{},[188,190,195,197,202],{"type":55,"value":189},"The ChangeNet model compares a ",{"type":49,"tag":64,"props":191,"children":192},{},[193],{"type":55,"value":194},"test image",{"type":55,"value":196}," against a ",{"type":49,"tag":64,"props":198,"children":199},{},[200],{"type":55,"value":201},"golden image",{"type":55,"value":203}," (known-good reference) to detect differences. When viewing images, check these three things:",{"type":49,"tag":102,"props":205,"children":206},{},[207,224,234],{"type":49,"tag":106,"props":208,"children":209},{},[210,215,217,222],{"type":49,"tag":64,"props":211,"children":212},{},[213],{"type":55,"value":214},"Image quality",{"type":55,"value":216},": Both images should be properly exposed with visible content. Watch for unusually dark images — but ",{"type":49,"tag":64,"props":218,"children":219},{},[220],{"type":55,"value":221},"do not use a fixed intensity threshold",{"type":55,"value":223},". Some illumination types (e.g., SolderLight) produce systemically dark images where mean intensity \u003C 30 is normal. Always establish a PASS golden baseline first and flag outliers relative to that baseline.",{"type":49,"tag":106,"props":225,"children":226},{},[227,232],{"type":49,"tag":64,"props":228,"children":229},{},[230],{"type":55,"value":231},"Framing match",{"type":55,"value":233},": Test and golden should show the same region at the same zoom and orientation. Mismatched framing (e.g., wide-field vs close-up) indicates a golden pipeline error.",{"type":49,"tag":106,"props":235,"children":236},{},[237,242],{"type":49,"tag":64,"props":238,"children":239},{},[240],{"type":55,"value":241},"Defect visibility",{"type":55,"value":243},": Can you see the difference between test and golden? Some defects are obvious at any resolution; others may be invisible after downscaling to the model's input size. Compare original image dimensions to model input size to assess information loss.",{"type":49,"tag":91,"props":245,"children":246},{},[],{"type":49,"tag":95,"props":248,"children":250},{"id":249},"investigation-flow",[251],{"type":55,"value":252},"Investigation Flow",{"type":49,"tag":58,"props":254,"children":255},{},[256,258],{"type":55,"value":257},"The investigation has 5 phases. Phase 1 (numbers) gives you hypotheses. Phase 2 (images) proves or disproves them. Phase 3 (cross-dimensional) finds hidden patterns. Phase 4 (config) explains the mechanism. Phase 5 (counterfactual) quantifies fixes. ",{"type":49,"tag":64,"props":259,"children":260},{},[261],{"type":55,"value":262},"Phase 2 is the core — spend the most effort there. Phase 5 is the most actionable — never skip it.",{"type":49,"tag":264,"props":265,"children":266},"ul",{},[267,277,287,297,307],{"type":49,"tag":106,"props":268,"children":269},{},[270,275],{"type":49,"tag":64,"props":271,"children":272},{},[273],{"type":55,"value":274},"Phase 1 — Score Analysis",{"type":55,"value":276},": score statistics, tier classification, threshold sweep, per-defect-type table, drop-N threshold-critical analysis, KPI verdict.",{"type":49,"tag":106,"props":278,"children":279},{},[280,285],{"type":49,"tag":64,"props":281,"children":282},{},[283],{"type":55,"value":284},"Phase 2 — Deep Image Investigation",{"type":55,"value":286},": threshold-critical sample deep dive (2A), systematic golden audit + failure mode clustering (2B), false positive deep dive (2C), comparative visual analysis (2D), label semantics & visual pattern alignment audit (2E).",{"type":49,"tag":106,"props":288,"children":289},{},[290,295],{"type":49,"tag":64,"props":291,"children":292},{},[293],{"type":55,"value":294},"Phase 3 — Cross-Dimensional Analysis",{"type":55,"value":296},": component-type clustering (3A), board-level & positional analysis (3B), training image deep dive (3C), multi-light condition analysis (3D).",{"type":49,"tag":106,"props":298,"children":299},{},[300,305],{"type":49,"tag":64,"props":301,"children":302},{},[303],{"type":55,"value":304},"Phase 4 — Data & Training Config Analysis",{"type":55,"value":306},": data sufficiency (4A), training config audit (4B), training metrics (4C), loss function & decision boundary analysis (4D).",{"type":49,"tag":106,"props":308,"children":309},{},[310,315],{"type":49,"tag":64,"props":311,"children":312},{},[313],{"type":55,"value":314},"Phase 5 — Counterfactual & Actionability",{"type":55,"value":316},": what-if simulations (5A), minimum viable fix path (5B).",{"type":49,"tag":58,"props":318,"children":319},{},[320,322,328],{"type":55,"value":321},"See ",{"type":49,"tag":117,"props":323,"children":325},{"className":324},[],[326],{"type":55,"value":327},"references\u002Finvestigation-phases.md",{"type":55,"value":329}," for the full per-phase, per-step instructions, the image path construction rules, all classification taxonomies and severity guidance, and the Architecture Reference (module formulas, sampler weighting, LR policy, dataset classes) — every value VERBATIM.",{"type":49,"tag":91,"props":331,"children":332},{},[],{"type":49,"tag":95,"props":334,"children":336},{"id":335},"execution-parallelize-with-subagents",[337],{"type":55,"value":338},"Execution: Parallelize With Subagents",{"type":49,"tag":58,"props":340,"children":341},{},[342,347],{"type":49,"tag":64,"props":343,"children":344},{},[345],{"type":55,"value":346},"You MUST use the Agent tool to run independent investigation tracks in parallel.",{"type":55,"value":348}," Run Phase 1 sequentially in the main thread (everything depends on it), then launch 6 subagents (A–F) in a single message, collect and synthesize their results (paying special attention to exploratory Agents E and F), run Phase 5 yourself, and write the report last.",{"type":49,"tag":58,"props":350,"children":351},{},[352,354,360,362,368,370,375,377,383],{"type":55,"value":353},"Before writing ",{"type":49,"tag":117,"props":355,"children":357},{"className":356},[],[358],{"type":55,"value":359},"RCA_Report.md",{"type":55,"value":361},", run ",{"type":49,"tag":117,"props":363,"children":365},{"className":364},[],[366],{"type":55,"value":367},"ls rca_images\u002F",{"type":55,"value":369}," to inventory thumbnails, and follow the ",{"type":49,"tag":64,"props":371,"children":372},{},[373],{"type":55,"value":374},"mandatory Image Embedding Protocol",{"type":55,"value":376},": every visual-evidence table row must carry inline thumbnail columns using ",{"type":49,"tag":117,"props":378,"children":380},{"className":379},[],[381],{"type":55,"value":382},"![caption](rca_images\u002F\u003Cfilename>.jpg)",{"type":55,"value":384}," syntax — a report without per-row images is incomplete and the hook will reject it.",{"type":49,"tag":58,"props":386,"children":387},{},[388,389,395],{"type":55,"value":321},{"type":49,"tag":117,"props":390,"children":392},{"className":391},[],[393],{"type":55,"value":394},"references\u002Fparallelization.md",{"type":55,"value":396}," for the complete execution plan: the Phase-1 hand-off contents, each agent's exact checklist (A–F including the two exploratory agents), the Image Embedding Protocol rules and table formats, the exploratory-findings section, the subagent prompt template, and the required Thumbnail Map return format — all VERBATIM.",{"type":49,"tag":91,"props":398,"children":399},{},[],{"type":49,"tag":95,"props":401,"children":403},{"id":402},"report-structure-and-output",[404],{"type":55,"value":405},"Report Structure and Output",{"type":49,"tag":58,"props":407,"children":408},{},[409,411,416],{"type":55,"value":410},"Produce ",{"type":49,"tag":117,"props":412,"children":414},{"className":413},[],[415],{"type":55,"value":359},{"type":55,"value":417}," with sections 1–9: Verdict, Score Analysis, Visual Evidence (with embedded thumbnails), Cross-Dimensional Analysis, Data Issues, Training Config Issues, Exploratory Findings, Counterfactual Impact Analysis, and Recommended Fixes.",{"type":49,"tag":58,"props":419,"children":420},{},[421],{"type":55,"value":422},"Always save into a timestamped folder under the experiment result directory:",{"type":49,"tag":424,"props":425,"children":429},"pre",{"className":426,"code":428,"language":55},[427],"language-text","\u003Cexperiment_result_dir>\u002Frca_results\u002FYYYY-MM-DD_HHMMSS\u002F\n├── RCA_Report.md\n├── rca_images\u002F\n├── rca_config\u002F\n└── claude_session.jsonl\n",[430],{"type":49,"tag":117,"props":431,"children":433},{"__ignoreMap":432},"",[434],{"type":55,"value":428},{"type":49,"tag":58,"props":436,"children":437},{},[438,440,446],{"type":55,"value":439},"Get the real timestamp by running ",{"type":49,"tag":117,"props":441,"children":443},{"className":442},[],[444],{"type":55,"value":445},"date +%Y-%m-%d_%H%M%S",{"type":55,"value":447}," in Bash — never hardcode or guess it. If the user specifies a custom path, use that instead but keep the same structure.",{"type":49,"tag":58,"props":449,"children":450},{},[451,452,458],{"type":55,"value":321},{"type":49,"tag":117,"props":453,"children":455},{"className":454},[],[456],{"type":55,"value":457},"references\u002Foutput-structure.md",{"type":55,"value":459}," for the complete section-by-section report skeleton (every table header and summary line) and the full output layout with hook-copied contents — VERBATIM.",{"items":461,"total":565},[462,479,493,507,519,536,551],{"slug":463,"name":463,"fn":464,"description":465,"org":466,"tags":467,"stars":23,"repoUrl":24,"updatedAt":478},"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},[468,471,474,475],{"name":469,"slug":470,"type":13},"Data Analysis","data-analysis",{"name":472,"slug":473,"type":13},"Data Engineering","data-engineering",{"name":9,"slug":8,"type":13},{"name":476,"slug":477,"type":13},"Performance","performance","2026-07-14T05:28:43.176466",{"slug":480,"name":480,"fn":481,"description":482,"org":483,"tags":484,"stars":23,"repoUrl":24,"updatedAt":492},"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},[485,488,491],{"name":486,"slug":487,"type":13},"Deployment","deployment",{"name":489,"slug":490,"type":13},"Infrastructure","infrastructure",{"name":9,"slug":8,"type":13},"2026-07-14T05:29:06.667109",{"slug":494,"name":494,"fn":495,"description":496,"org":497,"tags":498,"stars":23,"repoUrl":24,"updatedAt":506},"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},[499,502,503],{"name":500,"slug":501,"type":13},"Agents","agents",{"name":9,"slug":8,"type":13},{"name":504,"slug":505,"type":13},"Research","research","2026-07-14T05:28:06.816956",{"slug":508,"name":508,"fn":509,"description":510,"org":511,"tags":512,"stars":23,"repoUrl":24,"updatedAt":518},"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},[513,514,515],{"name":469,"slug":470,"type":13},{"name":9,"slug":8,"type":13},{"name":516,"slug":517,"type":13},"Testing","testing","2026-07-17T05:29:03.913266",{"slug":520,"name":520,"fn":521,"description":522,"org":523,"tags":524,"stars":23,"repoUrl":24,"updatedAt":535},"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},[525,528,531,532],{"name":526,"slug":527,"type":13},"Automation","automation",{"name":529,"slug":530,"type":13},"Imaging","imaging",{"name":9,"slug":8,"type":13},{"name":533,"slug":534,"type":13},"Video","video","2026-07-17T05:28:53.905004",{"slug":537,"name":537,"fn":538,"description":539,"org":540,"tags":541,"stars":23,"repoUrl":24,"updatedAt":550},"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},[542,543,546,547],{"name":486,"slug":487,"type":13},{"name":544,"slug":545,"type":13},"Docker","docker",{"name":9,"slug":8,"type":13},{"name":548,"slug":549,"type":13},"Operations","operations","2026-07-17T05:28:56.913999",{"slug":552,"name":552,"fn":553,"description":554,"org":555,"tags":556,"stars":23,"repoUrl":24,"updatedAt":564},"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},[557,558,561],{"name":9,"slug":8,"type":13},{"name":559,"slug":560,"type":13},"Quantum Computing","quantum-computing",{"name":562,"slug":563,"type":13},"Simulation","simulation","2026-07-14T05:26:58.898253",305,{"items":567,"total":714},[568,586,602,613,625,637,648,662,673,682,696,705],{"slug":569,"name":569,"fn":570,"description":571,"org":572,"tags":573,"stars":583,"repoUrl":584,"updatedAt":585},"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},[574,577,580],{"name":575,"slug":576,"type":13},"Documentation","documentation",{"name":578,"slug":579,"type":13},"MCP","mcp",{"name":581,"slug":582,"type":13},"Search","search",21777,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FNemoClaw","2026-07-20T06:00:01.461044",{"slug":587,"name":587,"fn":588,"description":589,"org":590,"tags":591,"stars":599,"repoUrl":600,"updatedAt":601},"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},[592,595,596],{"name":593,"slug":594,"type":13},"Containers","containers",{"name":486,"slug":487,"type":13},{"name":597,"slug":598,"type":13},"Python","python",17049,"https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FMegatron-LM","2026-07-27T06:06:11.249662",{"slug":603,"name":603,"fn":604,"description":605,"org":606,"tags":607,"stars":599,"repoUrl":600,"updatedAt":612},"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},[608,611],{"name":609,"slug":610,"type":13},"CI\u002FCD","ci-cd",{"name":486,"slug":487,"type":13},"2026-07-14T05:25:59.97109",{"slug":614,"name":614,"fn":615,"description":616,"org":617,"tags":618,"stars":599,"repoUrl":600,"updatedAt":624},"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},[619,620,621],{"name":609,"slug":610,"type":13},{"name":486,"slug":487,"type":13},{"name":622,"slug":623,"type":13},"GitHub","github","2026-07-27T06:06:12.278222",{"slug":626,"name":626,"fn":627,"description":628,"org":629,"tags":630,"stars":599,"repoUrl":600,"updatedAt":636},"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},[631,632,633],{"name":21,"slug":22,"type":13},{"name":622,"slug":623,"type":13},{"name":634,"slug":635,"type":13},"Triage","triage","2026-07-14T05:25:57.442089",{"slug":638,"name":638,"fn":639,"description":640,"org":641,"tags":642,"stars":599,"repoUrl":600,"updatedAt":647},"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},[643,646],{"name":644,"slug":645,"type":13},"Best Practices","best-practices",{"name":18,"slug":19,"type":13},"2026-07-14T05:25:56.18433",{"slug":649,"name":649,"fn":650,"description":651,"org":652,"tags":653,"stars":599,"repoUrl":600,"updatedAt":661},"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},[654,657,660],{"name":655,"slug":656,"type":13},"Machine Learning","machine-learning",{"name":658,"slug":659,"type":13},"Migration","migration",{"name":9,"slug":8,"type":13},"2026-07-17T06:07:11.777011",{"slug":663,"name":663,"fn":664,"description":665,"org":666,"tags":667,"stars":599,"repoUrl":600,"updatedAt":672},"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},[668,671],{"name":669,"slug":670,"type":13},"QA","qa",{"name":516,"slug":517,"type":13},"2026-07-14T05:25:53.673039",{"slug":674,"name":674,"fn":675,"description":676,"org":677,"tags":678,"stars":599,"repoUrl":600,"updatedAt":681},"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},[679,680],{"name":486,"slug":487,"type":13},{"name":489,"slug":490,"type":13},"2026-07-14T05:25:49.362534",{"slug":683,"name":683,"fn":684,"description":685,"org":686,"tags":687,"stars":599,"repoUrl":600,"updatedAt":695},"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},[688,691,692],{"name":689,"slug":690,"type":13},"Code Review","code-review",{"name":622,"slug":623,"type":13},{"name":693,"slug":694,"type":13},"Pull Requests","pull-requests","2026-07-14T05:26:01.226578",{"slug":697,"name":697,"fn":698,"description":699,"org":700,"tags":701,"stars":599,"repoUrl":600,"updatedAt":704},"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},[702,703],{"name":669,"slug":670,"type":13},{"name":516,"slug":517,"type":13},"2026-07-14T05:25:54.928983",{"slug":706,"name":706,"fn":707,"description":708,"org":709,"tags":710,"stars":599,"repoUrl":600,"updatedAt":713},"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},[711,712],{"name":526,"slug":527,"type":13},{"name":609,"slug":610,"type":13},"2026-07-30T05:29:03.275638",496]