[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skills:stats":3,"skills:pro6":8,"skills:sce6":55,"skills:creators9":100,"skills:all:stars:25487:":195},{"skillCount":4,"professionCount":5,"scenarioCount":6,"creatorCount":7},482556,11,7,5953,[9,20,27,34,41,48],{"categoryNo":10,"taxonomyType":11,"taxonomyTypeDesc":12,"categoryName":13,"categoryNameEn":14,"description":15,"level":16,"skillCount":17,"parentNo":18,"parentName":18,"children":19},"01JBSEEDCAT000000000000030","PROFESSION","适用职业","开发工程师","Software Engineer","从事软件编码、测试与运维的工程师",1,13341,null,[],{"categoryNo":21,"taxonomyType":11,"taxonomyTypeDesc":12,"categoryName":22,"categoryNameEn":23,"description":24,"level":16,"skillCount":25,"parentNo":18,"parentName":18,"children":26},"01JBSEEDCAT000000000000032","设计师","Designer","视觉、交互与品牌设计人员",7902,[],{"categoryNo":28,"taxonomyType":11,"taxonomyTypeDesc":12,"categoryName":29,"categoryNameEn":30,"description":31,"level":16,"skillCount":32,"parentNo":18,"parentName":18,"children":33},"01JBSEEDCAT000000000000033","数据分析师","Data Analyst","数据分析、报表与商业智能人员",5005,[],{"categoryNo":35,"taxonomyType":11,"taxonomyTypeDesc":12,"categoryName":36,"categoryNameEn":37,"description":38,"level":16,"skillCount":39,"parentNo":18,"parentName":18,"children":40},"01JBSEEDCAT000000000000036","内容创作者","Content Creator","作者、编辑与自媒体创作者",3978,[],{"categoryNo":42,"taxonomyType":11,"taxonomyTypeDesc":12,"categoryName":43,"categoryNameEn":44,"description":45,"level":16,"skillCount":46,"parentNo":18,"parentName":18,"children":47},"01JBSEEDCAT000000000000035","市场营销","Marketer","市场推广、增长与品牌运营人员",3454,[],{"categoryNo":49,"taxonomyType":11,"taxonomyTypeDesc":12,"categoryName":50,"categoryNameEn":51,"description":52,"level":16,"skillCount":53,"parentNo":18,"parentName":18,"children":54},"01JBSEEDCAT000000000000037","律师与法务","Legal","合同、合规与法律事务人员",3337,[],[56,65,72,79,86,93],{"categoryNo":57,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":60,"categoryNameEn":61,"description":62,"level":16,"skillCount":63,"parentNo":18,"parentName":18,"children":64},"01JBSEEDCAT000000000000022","SCENARIO","使用场景","智能体与自动化","Agents & Automation","Skill、MCP、智能体与工作流自动化",39675,[],{"categoryNo":66,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":67,"categoryNameEn":68,"description":69,"level":16,"skillCount":70,"parentNo":18,"parentName":18,"children":71},"01JBSEEDCAT000000000000006","软件开发","Software Development","编码、测试、部署等软件研发任务",26798,[],{"categoryNo":73,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":74,"categoryNameEn":75,"description":76,"level":16,"skillCount":77,"parentNo":18,"parentName":18,"children":78},"01JBSEEDCAT000000000000014","设计创意","Design & Creative","视觉设计、品牌与多媒体创作",13847,[],{"categoryNo":80,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":81,"categoryNameEn":82,"description":83,"level":16,"skillCount":84,"parentNo":18,"parentName":18,"children":85},"01JBSEEDCAT000000000000001","办公效率","Office Productivity","日常办公文档、表格、演示与沟通类任务",6403,[],{"categoryNo":87,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":88,"categoryNameEn":89,"description":90,"level":16,"skillCount":91,"parentNo":18,"parentName":18,"children":92},"01JBSEEDCAT000000000000017","内容创作","Content Creation","写作、文案与营销内容生产",6063,[],{"categoryNo":94,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":95,"categoryNameEn":96,"description":97,"level":16,"skillCount":98,"parentNo":18,"parentName":18,"children":99},"01JBSEEDCAT000000000000020","研究与学习","Research & Learning","资料检索、知识整理与学习辅导",5574,[],{"records":101,"total":7,"current":16,"size":194},[102,114,123,132,142,152,162,172,182],{"accountNo":103,"login":104,"displayName":105,"avatarUrl":106,"accountType":107,"accountTypeDesc":108,"profileDescription":109,"skillCount":110,"repoCount":111,"professionCount":5,"scenarioCount":6,"totalStars":112,"updatedAt":113},"01M698VYDXZ6JW5WH3CRV650R8","microsoft","Microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","ORGANIZATION","组织","Open source projects and samples from Microsoft",4300,236,832929,"2026-11-15 04:18:35",{"accountNo":115,"login":116,"displayName":116,"avatarUrl":117,"accountType":107,"accountTypeDesc":108,"profileDescription":118,"skillCount":119,"repoCount":120,"professionCount":6,"scenarioCount":6,"totalStars":121,"updatedAt":122},"01M698P3FSAZ6B4R928ZF19KPT","openclaw","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F252820863?v=4","Your personal, open source AI assistant.",369,32,437811,"2026-11-15 03:04:02",{"accountNo":124,"login":125,"displayName":126,"avatarUrl":127,"accountType":107,"accountTypeDesc":108,"profileDescription":18,"skillCount":128,"repoCount":129,"professionCount":5,"scenarioCount":6,"totalStars":130,"updatedAt":131},"01M697XGDPXJAVQ8391V2BCYTE","anthropics","Anthropic","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F76263028?v=4",716,18,427323,"2026-11-15 05:52:49",{"accountNo":133,"login":134,"displayName":135,"avatarUrl":136,"accountType":107,"accountTypeDesc":108,"profileDescription":18,"skillCount":137,"repoCount":138,"professionCount":6,"scenarioCount":139,"totalStars":140,"updatedAt":141},"01M6AC29YGCR4S2NTJFV0G8B81","openai","OpenAI","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F14957082?v=4",177,23,6,344400,"2026-11-15 03:07:28",{"accountNo":143,"login":144,"displayName":145,"avatarUrl":146,"accountType":107,"accountTypeDesc":108,"profileDescription":18,"skillCount":147,"repoCount":148,"professionCount":149,"scenarioCount":6,"totalStars":150,"updatedAt":151},"01M6AC83E6K4FDKK7HZ8WNMQKE","apache","The Apache Software Foundation","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F47359?v=4",440,76,8,298252,"2026-11-15 04:11:16",{"accountNo":153,"login":154,"displayName":155,"avatarUrl":156,"accountType":107,"accountTypeDesc":108,"profileDescription":157,"skillCount":158,"repoCount":159,"professionCount":5,"scenarioCount":6,"totalStars":160,"updatedAt":161},"01M6AC83DS133TPXFSP1DHNCC6","github","GitHub","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9919?v=4","How people build software.",1022,30,278314,"2026-11-15 06:45:15",{"accountNo":163,"login":164,"displayName":165,"avatarUrl":166,"accountType":107,"accountTypeDesc":108,"profileDescription":167,"skillCount":168,"repoCount":169,"professionCount":5,"scenarioCount":6,"totalStars":170,"updatedAt":171},"01M698VYEFDM0VJBZDYYJ2T83S","google","Google","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1342004?v=4","Google ❤️ Open Source",542,50,243804,"2026-11-15 03:00:30",{"accountNo":173,"login":174,"displayName":175,"avatarUrl":176,"accountType":107,"accountTypeDesc":108,"profileDescription":18,"skillCount":177,"repoCount":178,"professionCount":179,"scenarioCount":6,"totalStars":180,"updatedAt":181},"01M6AC83EPDGBFN19MWYRREJD0","Significant-Gravitas","AutoGPT","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F130738209?v=4",87,2,10,188029,"2026-11-15 06:21:09",{"accountNo":183,"login":184,"displayName":185,"avatarUrl":186,"accountType":187,"accountTypeDesc":188,"profileDescription":189,"skillCount":190,"repoCount":191,"professionCount":139,"scenarioCount":6,"totalStars":192,"updatedAt":193},"01M6DJCCDDG53MTYYRTXAXFG17","garrytan","Garry Tan","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F19957?v=4","USER","个人作者","Writes software, dreams. ",340,3,175019,"2026-11-15 03:57:03",9,{"records":196,"total":4,"current":564,"size":129},[197,236,257,281,308,332,354,370,393,410,428,452,470,487,503,520,535,549],{"skillNo":198,"name":199,"nameZh":18,"description":200,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":209,"categories":210,"keywords":214,"publishedAt":235},"01M6PSEBJ7FGTQBH1PZ6C5546Z","tao-run-automl","Run AutoML \u002F hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian, hyperband, asha, bohb, llm, hybrid, autoresearch), WandB experiment tracking, job execution on any TAO SDK platform, result interpretation, and per-rec custom evaluation hooks. Use when the user mentions TAO AutoML, hyperparameter optimization, HPO, automl, automl_settings, AutoMLRunner, tao_automl, bayesian search, hyperband, ASHA, LLM-guided search, autoresearch, or wants to tune training hyperparameters for any TAO network. Platform-agnostic — runs on any SDK (Lepton, Brev, SLURM, Kubernetes, Docker).","headmktlucca-ui\u002Fneuroads-lp","headmktlucca-ui","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F247379838?v=4","01M6PDVAV6M1W96D1SR1PDF8CS","NeuroAds","01M6PDVAZ4P281GNDKD45CYTF5",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-run-automl\u002FSKILL.md",[211],{"categoryNo":212,"categoryName":213,"taxonomyType":58,"taxonomyTypeDesc":59},"01JBSEEDCAT000000000000011","运维与部署",[215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234],"automl","run","tao","tao run automl","workflow","workflows","interpretation","training","search","autoresearch","Bash","read","hooks","selection","Experiment Tracking","WandB","result","hpo","brev","lepton","2026-11-10 10:12:30",{"skillNo":237,"name":238,"nameZh":18,"description":239,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":240,"categories":241,"keywords":245,"publishedAt":235},"01M6PSE2YVS430EPTD4CS6N9GT","tao-run-automl-deft-pipeline","Run the canonical NVIDIA AOI three-phase training pipeline — Phase 1 AutoML baseline (HPO), Phase 2 DEFT loop (RCA → SDG → mining → plain-train retrain), Phase 3 AutoML refinement on the DEFT-augmented dataset. This is the default entry point for any \"run the AOI workflow\", \"fine-tune my PCB AOI model end-to-end\", \"improve my AOI ChangeNet model\", or \"AOI workflow with AutoML\" request — route here instead of tao-run-deft-aoi directly unless the user explicitly asks for the DEFT loop ONLY (e.g. \"run JUST the DEFT loop\", \"skip AutoML, only DEFT\"). Also handles the same three-phase pattern for non-AOI DEFT applications — AutoML baseline then DEFT loop warm-started from AutoML's winning HPs then post-DEFT AutoML refinement on the iteration-augmented dataset. Trigger phrases include \"run the AOI workflow\", \"AOI end-to-end\", \"AutoML + DEFT\", \"AutoML then DEFT\", \"tune hyperparameters then DEFT\", \"DEFT with AutoML at both ends\", \"warm-start DEFT\", \"improve my AOI model\".","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-run-automl-deft-pipeline\u002FSKILL.md",[242],{"categoryNo":243,"categoryName":244,"taxonomyType":58,"taxonomyTypeDesc":59},"01JBSEEDCAT000000000000023","Skill与智能体开发",[215,216,246,247,217,248,218,219,220,222,225,249,250,251,252,253,254,255,256,232],"pipeline","deft","tao run automl deft pipeline","improve","loop","model","only","default","iteration","end","dataset",{"skillNo":258,"name":259,"nameZh":18,"description":260,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":261,"categories":262,"keywords":263,"publishedAt":235},"01M6PSDXG1FPHJ8W541XF60EP2","tao-route-visual-changenet-samples","Routes the weakest VCN samples (output of `tao-analyze-gaps-visual-changenet`) into per-augmentation-module subsets — one parquet for k-NN mining, one for AnomalyGen (Cosmos SDG) — based on each module's label eligibility. Use as the immediate next step after DEFT gap analysis in a VCN AOI SDA iteration.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-route-visual-changenet-samples\u002FSKILL.md",[],[264,265,217,266,267,268,269,225,270,271,254,272,273,274,275,276,277,278,279,280],"route","visual","changenet","tao route visual changenet samples","NVIDIA","analysis","use","requirements","runtime","module","as","cosmos","gap analysis","K-NN","standalone","for","sda",{"skillNo":282,"name":283,"nameZh":18,"description":284,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":285,"categories":286,"keywords":291,"publishedAt":235},"01M6PSDM005P78DAKJPX7XF4JG","tao-port-huggingface-model","Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline). Use when the user asks to \"integrate a HuggingFace model into TAO\", \"add an HF model to TAO Toolkit\", \"wire a HuggingFace ViT\u002FDETR\u002F SegFormer into tao-pytorch\", \"build a TAO trainer + deploy pipeline for an HF CV model\", or pastes a HuggingFace model URL\u002FID and wants it turned into a TAO model. Covers the full 7-phase loop: prerequisites check, HuggingFace inspection and validation, codebase exploration, tao-core configuration and native trainer implementation, ONNX export plus TensorRT deploy integration, packaging and L0 testing, container-based end-to-end validation, and (conditional) accuracy\u002Flatency tuning. Supports classification, object detection, semantic \u002F instance \u002F panoptic segmentation, zero-shot detection, and depth estimation.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-port-huggingface-model\u002FSKILL.md",[287,290],{"categoryNo":288,"categoryName":289,"taxonomyType":58,"taxonomyTypeDesc":59},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":212,"categoryName":213,"taxonomyType":58,"taxonomyTypeDesc":59},[292,251,293,217,294,295,296,297,298,299,250,226,300,301,302,303,304,305,306,307],"HuggingFace","port","tao port huggingface model","testing","config","deploy pipeline","git","segmentation","write","edit","packaging","exploration","local","URL","login","phase",{"skillNo":309,"name":310,"nameZh":18,"description":311,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":312,"categories":313,"keywords":318,"publishedAt":235},"01M6PSDC5JARNYFKQTW00TMY53","tao-mine-aoi-images","Runs the DEFT embed-then-mine workflow for VCN AOI iterations — embeds the gap-analysis target parquet, embeds a source pool, and mines nearest-neighbour source images for downstream augmentation. Use as the immediate next step after `tao-route-visual-changenet-samples` when expanding a real-image augmentation queue from the mining subset.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-mine-aoi-images\u002FSKILL.md",[314,317],{"categoryNo":315,"categoryName":316,"taxonomyType":58,"taxonomyTypeDesc":59},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":243,"categoryName":244,"taxonomyType":58,"taxonomyTypeDesc":59},[319,320,217,321,322,323,219,324,325,269,225,226,264,326,327,328,329,330,331,280],"images","mine","aoi","tao mine aoi images","image","data","gap-analysis","next","embedding","at","bank","source","mining",{"skillNo":333,"name":334,"nameZh":18,"description":335,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":336,"categories":337,"keywords":339,"publishedAt":235},"01M6PSD8CKWFV5NMVD71PFM3DF","tao-list-capabilities","Answer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, AutoML, and platform manifests.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-list-capabilities\u002FSKILL.md",[338],{"categoryNo":243,"categoryName":244,"taxonomyType":58,"taxonomyTypeDesc":59},[340,341,342,217,343,344,268,345,225,251,226,346,347,348,349,350,351,352,353,329],"capabilities","list capabilities","list","tao list capabilities","plugin","discovery","do","what the","platform","scripts","helper","answer","can","manifests",{"skillNo":355,"name":356,"nameZh":18,"description":357,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":358,"categories":359,"keywords":361,"publishedAt":235},"01M6PSD4AEQ6TPK5CWQ5T0MSP5","tao-launch-workflow","Shared launch intake for any TAO workflow or action. Use when the user wants to run TAO AutoML, train, evaluate, infer, export, generate TensorRT engines, or launch DEFT\u002Fworkflow jobs on an execution platform.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-launch-workflow\u002FSKILL.md",[360],{"categoryNo":243,"categoryName":244,"taxonomyType":58,"taxonomyTypeDesc":59},[219,362,217,363,364,216,365,268,366,225,226,270,367,348,368,349,350,329,279,369],"launch","tao launch workflow","generate","intake","execution","shared","infer","evaluate",{"skillNo":371,"name":372,"nameZh":18,"description":373,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":374,"categories":375,"keywords":377,"publishedAt":235},"01M6PSCXSA656B8FZNEGR5T4F2","tao-generate-video-reasoning-annotations","Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level captions, structured descriptions, and QA pairs (MCQ, binary, open-ended) with reasoning traces, via VLM\u002FLLM distillation. Use when the user wants to \"create video training data\", \"generate video QA datasets\", \"build CoT reasoning traces from videos\", \"auto-label videos\", or run the video_reasoning_annotation pipeline. Triggers include \"video annotation\", \"video CoT\", \"video QA\", \"chain-of-thought\", \"video captioning pipeline\", \"video distillation\".","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-generate-video-reasoning-annotations\u002FSKILL.md",[376],{"categoryNo":315,"categoryName":316,"taxonomyType":58,"taxonomyTypeDesc":59},[378,364,379,380,381,217,382,222,383,384,246,385,386,387,225,388,389,390,391,392],"generate video","reasoning","Video","annotations","tao generate video reasoning annotations","create","qa","api","Captions","open","auto","chain","auto-label","captioning","qa-generation",{"skillNo":394,"name":395,"nameZh":18,"description":396,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":397,"categories":398,"keywords":400,"publishedAt":235},"01M6PSCN8500GQG1W2P9ZH1TA1","tao-generate-referring-expressions","Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region descriptions, scene captions, grounded referring expressions, and (optionally) verified expressions via VLM distillation. Use when the user wants to generate referring-expression annotations from images with KITTI labels, build region descriptions, produce grouped grounding phrases tied to bboxes, run a double-check verification pass on grounding expressions, auto-label traffic \u002F scene images for referring datasets, or run the image_referring_expression pipeline. Triggers include 'referring expression', 'region description', 'KITTI labels', 'spatial relationship annotation', 'auto-label image referring expression', 'image_referring_expression'.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-generate-referring-expressions\u002FSKILL.md",[399],{"categoryNo":315,"categoryName":316,"taxonomyType":58,"taxonomyTypeDesc":59},[364,217,401,323,216,402,246,385,386,225,388,319,403,404,405,406,407,390,408,409],"tao generate referring expressions","verification","relationship","expression","traffic","labels","bounding-boxes","referring-expression","kitti",{"skillNo":411,"name":412,"nameZh":18,"description":413,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":414,"categories":415,"keywords":417,"publishedAt":235},"01M6PSCG13ZMPJP2QRT5SNW3JC","tao-generate-image-grounding","Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them to pixel-space bounding boxes via a VLM. Use when the user wants to ground captions to bboxes, generate phrase-grounded annotations, auto-label images for grounding, or run the image_grounding pipeline. Triggers include 'image grounding', 'phrase grounding', 'ground captions', 'auto-label image grounding', 'image_grounding'.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-generate-image-grounding\u002FSKILL.md",[416],{"categoryNo":315,"categoryName":316,"taxonomyType":58,"taxonomyTypeDesc":59},[323,364,418,419,217,420,421,422,423,268,246,386,319,424,425,426,279,407,390,427],"generate image","grounding","tao generate image grounding","gemini","gemini api","docker","pixel","triggers","openai-compatible","2d-grounding",{"skillNo":429,"name":430,"nameZh":18,"description":431,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":432,"categories":433,"keywords":439,"publishedAt":235},"01M6PSC3V41PQ3W55Q24SXZQRQ","tao-finetune-huggingface-model","Fine-tune any HuggingFace CV \u002F VLM \u002F LLM model on local NVIDIA GPUs inside an NGC PyTorch container. Use when the user wants to fine-tune a HuggingFace model (full or LoRA), train a vision \u002F VLM \u002F LLM model end-to-end, generate a reproducible HF training pipeline, smoke-test a HuggingFace model locally before scale-up, push a fine-tuned model to the HF Hub with a model card, or emit a self-contained rerun skill for an existing HuggingFace finetune. Supports image classification, object detection, semantic \u002F instance \u002F panoptic segmentation, depth estimation, image-text-to-text VLM (SFT \u002F LoRA), and LLM SFT \u002F DPO \u002F GRPO. Six-step workflow: inspect and qualify, hardware and NGC image, research, generate and smoke, train + eval + infer, push and emit rerun skill.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-finetune-huggingface-model\u002FSKILL.md",[434,435,438],{"categoryNo":315,"categoryName":316,"taxonomyType":58,"taxonomyTypeDesc":59},{"categoryNo":436,"categoryName":437,"taxonomyType":58,"taxonomyTypeDesc":59},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":243,"categoryName":244,"taxonomyType":58,"taxonomyTypeDesc":59},[292,251,440,217,441,323,222,364,299,442,443,444,445,304,446,447,448,449,450,451],"finetune","tao finetune huggingface model","disk","text","eval","free disk","project","free","card","qualify","vram","inspect",{"skillNo":453,"name":454,"nameZh":18,"description":455,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":456,"categories":457,"keywords":459,"publishedAt":235},"01M6PSBYF3QVADR1TBBEC5XRPE","tao-finetune-cosmos-reason","Cosmos-Reason2-8B video QA supervised fine-tuning with FSDP parallelism. Use when training or evaluating video question-answering models, fine-tuning Cosmos-Reason2 with SFT, or working with Cosmos-RL. Trigger phrases include \"fine-tune Cosmos-Reason\", \"Cosmos-RL SFT\", \"video QA fine-tune\", \"Cosmos-Reason2-8B training\".","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-finetune-cosmos-reason\u002FSKILL.md",[458],{"categoryNo":315,"categoryName":316,"taxonomyType":58,"taxonomyTypeDesc":59},[275,440,460,217,461,423,222,462,384,268,463,380,225,464,270,465,466,467,468,469],"reason","tao finetune cosmos reason","toolkit","Fine-Tuning","question","container","rl","trigger","FSDP","cosmos-reason",{"skillNo":471,"name":472,"nameZh":18,"description":473,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":474,"categories":475,"keywords":477,"publishedAt":235},"01M6PSBS57RBK0Q0MM95NDA0H6","tao-finetune-cosmos-embed","Cosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication, and fine-tuning. Use when the user asks to \"fine-tune Cosmos-Embed1\", \"run cosmos-embed inference\", \"export Cosmos-Embed1\", \"embed videos\", or \"search videos with text\".","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-finetune-cosmos-embed\u002FSKILL.md",[476],{"categoryNo":315,"categoryName":316,"taxonomyType":58,"taxonomyTypeDesc":59},[275,440,478,217,479,216,223,480,268,481,482,380,225,443,226,483,484,485,327,486],"embed","tao finetune cosmos embed","multimodal","deduplication","tuning","export","vision","token","text-to-video",{"skillNo":488,"name":489,"nameZh":18,"description":490,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":491,"categories":492,"keywords":494,"publishedAt":235},"01M6PSBKV1BXJDC0CBPFX1N192","tao-finetune-clip","CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment. Use when fine-tuning or training CLIP, running zero-shot classification, computing image embeddings, or deploying CLIP to ONNX\u002FTensorRT.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-finetune-clip\u002FSKILL.md",[493],{"categoryNo":212,"categoryName":213,"taxonomyType":58,"taxonomyTypeDesc":59},[495,440,217,496,323,423,497,222,498,499,268,463,500,251,270,465,327,501,502,279],"clip","tao finetune clip","onnx","deployment","ZeRO","classification","Vision-Language","Zero-Shot",{"skillNo":504,"name":505,"nameZh":18,"description":506,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":507,"categories":508,"keywords":509,"publishedAt":235},"01M6PSBFVB2RGCNP2F6Y6ZPG5M","tao-convert-dataset-format","Run `tao-daft convert` to convert NVIDIA TAO DAFT datasets between supported formats. Do not use for non-DAFT data. Use when the user asks to convert a DAFT dataset, change DAFT format, change a TAO dataset format, or run `tao-daft convert`.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-convert-dataset-format\u002FSKILL.md",[],[510,511,256,217,512,513,514,515,216,516,268,225,270,517,346,275,518,279,469,519],"convert","format","tao convert dataset format","python","sdk","change","package","conversion","pip","nvidia-tao",{"skillNo":521,"name":522,"nameZh":18,"description":523,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":524,"categories":525,"keywords":526,"publishedAt":235},"01M6PSBB6P1J6R60WWDAGM8KFJ","tao-analyze-gaps-vlm-bcq","Extract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes\u002Fno) predictions. Use after running VLM evaluation when you have a predictions JSON and need to identify failure cases for DEFT root cause analysis on a binary-classification VLM workflow.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-analyze-gaps-vlm-bcq\u002FSKILL.md",[],[527,217,528,529,530,423,219,462,268,269,500,225,464,270,465,531,532,533,534,279],"analyze","gaps","vlm","tao analyze gaps vlm bcq","false","predictions","you","yes",{"skillNo":536,"name":537,"nameZh":18,"description":538,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":539,"categories":540,"keywords":542,"publishedAt":235},"01M6PSB4K5QQZ8XTM9D2V8DWT2","tao-analyze-gaps-visual-changenet","Performs gap analysis on NVIDIA TAO Visual ChangeNet (VCN) Classify experiments by invoking the data-services container (`tao_toolkit.data_services` from `versions.yaml`) directly via `docker run … gap_analysis vcn_aoi …` — picks the optimal decision threshold, ranks per-sample weakness, and emits a top-K weakest parquet expanded per-lighting for downstream augmentation. Use when analyzing VCN classification failures, picking SDA augmentation targets, auditing PASS\u002FNO_PASS boundary cases, or running DEFT gap analysis on an AOI ChangeNet model.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-analyze-gaps-visual-changenet\u002FSKILL.md",[541],{"categoryNo":212,"categoryName":213,"taxonomyType":58,"taxonomyTypeDesc":59},[527,265,217,528,266,543,323,216,544,269,225,251,545,226,546,547,548,328,329,280],"tao analyze gaps visual changenet","analyzing","decision","sample","classify","top",{"skillNo":550,"name":551,"nameZh":18,"description":552,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":553,"categories":554,"keywords":555,"publishedAt":235},"01M6PSAY18K7ZT8Q54X6ADST3F","tao-analyze-changenet-rca","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\".","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-analyze-changenet-rca\u002FSKILL.md",[],[556,527,217,266,557,323,220,558,559,544,246,269,560,225,251,226,561,532,562,563],"rca","tao analyze changenet rca","experiments","audit","why","deep","my","defect",25487]