[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69AS0T2FF3R3YHFQZAF4X3F":3,"skill-same:01M69AS0T2FF3R3YHFQZAF4X3F":78},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":6,"ownerHtmlUrl":50,"ownerBlogUrl":51,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M69AS0T2FF3R3YHFQZAF4X3F","osmo-lerobot-training",null,"Submit, monitor, analyze, and evaluate LeRobot imitation learning training jobs on OSMO with Azure ML MLflow integration and inference evaluation - Brought to you by microsoft\u002Fphysical-ai-toolchain","microsoft\u002Fphysical-ai-toolchain","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69ARCAV4WR03MSZSQPHZ2S8",138,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fphysical-ai-toolchain\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fosmo-lerobot-training\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,9],"osmo lerobot training","training","analyze","Training Jobs","evaluate","you","with","toolchain","submit","physical","mlflow","jobs","inference","learning","Evaluation","integration","monitor","ml","azure","2026-11-10 10:12:30",false,"---\nname: alert-triage\ndescription: Use for alert triage questions in the Fraud Detection and Alert Agent synthetic pilot.\n---\n\u003C!-- bic:source=blank -->\n# Alert triage\n\nPrioritizes fictional alerts by transparent risk evidence and rule severity.\n\n## Procedure\n\n1. Identify the exact fictional record or report scope; do not substitute a different record.\n2. Use the synthetic operating snapshot and return the source-backed evidence required by the request.\n3. Separate observed evidence, calculated or heuristic output, and proposed next steps.\n4. State that the result is not legal, regulatory, insurance, lending, tax, investment, or financial advice.\n5. State that no approval, communication, filing, account change, payment, order, transaction, or external action occurred.\n6. Name the authorized human review required before action.\n\n## Locked example\n\nPersona: Fraud Operations Manager\n\nPrompt: Review overnight fraud activity and show me what needs immediate attention.\n\nExpected synthetic evidence: 1,247 overnight alerts, $892K, F-78234.\n","\u003C!-- bic:source=blank -->\n# Alert triage\n\nPrioritizes fictional alerts by transparent risk evidence and rule severity.\n\n## Procedure\n\n1. Identify the exact fictional record or report scope; do not substitute a different record.\n2. Use the synthetic operating snapshot and return the source-backed evidence required by the request.\n3. Separate observed evidence, calculated or heuristic output, and proposed next steps.\n4. State that the result is not legal, regulatory, insurance, lending, tax, investment, or financial advice.\n5. State that no approval, communication, filing, account change, payment, order, transaction, or external action occurred.\n6. Name the authorized human review required before action.\n\n## Locked example\n\nPersona: Fraud Operations Manager\n\nPrompt: Review overnight fraud activity and show me what needs immediate attention.\n\nExpected synthetic evidence: 1,247 overnight alerts, $892K, F-78234.\n",{"name":43,"description":44},"alert-triage","Use for alert triage questions in the Fraud Detection and Alert Agent synthetic pilot.","main","d665f66f72c112f5d2956b180f9b534dcb1d94f8",".github\u002Fskills\u002Fosmo-lerobot-training",72,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fphysical-ai-toolchain","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-11 03:38:51",{"source":8,"skillName":43,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add microsoft\u002Fphysical-ai-toolchain --skill alert-triage",{"tool":60,"command":61},"bunx","bunx skills add microsoft\u002Fphysical-ai-toolchain --skill alert-triage",{"tool":63,"command":64},"pnpm","pnpm dlx skills add microsoft\u002Fphysical-ai-toolchain --skill alert-triage","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fphysical-ai-toolchain\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fosmo-lerobot-training\u002FSKILL.md",true,[68,74],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002FDEFAULTS.md","REFERENCE","参考文档",3873,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fphysical-ai-toolchain\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fosmo-lerobot-training\u002Freferences\u002FDEFAULTS.md",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002FREFERENCE.md",19841,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fphysical-ai-toolchain\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fosmo-lerobot-training\u002Freferences\u002FREFERENCE.md",[79,103,126,151,174,196],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":90,"publishedAt":38},"01M69AS2WAAD5CZ9S9CBSEZ226","synthetic-data","Generate synthetic training data using NVIDIA Cosmos world foundation models for SDG pipelines","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fphysical-ai-toolchain\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fsynthetic-data\u002FSKILL.md",[85],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[91,92,93,20,94,95,96,97,98,99,100,101,102],"synthetic data","data","synthetic","generate","NVIDIA","pipelines","models","foundation","world","cosmos","for","Training Data",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":114,"publishedAt":38},"01M69ARYW92CVD1H0AZ10RDWFF","infrastructure","Deploy and manage Azure infrastructure for the Physical AI Toolchain including Terraform IaC, Kubernetes setup, GPU configuration, and network topology","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fphysical-ai-toolchain\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Finfrastructure\u002FSKILL.md",[109],{"categoryNo":110,"categoryName":111,"taxonomyType":112,"taxonomyTypeDesc":113},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",[105,115,116,117,37,118,119,120,121,122,123,124,28,125,26,101],"kubernetes","deploy","setup","terraform","gpu","topology","network","iac","manage","configuration","terraform iac",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":38},"01M69ARWVH4BA8RWYR6EVJV2XF","fleet-intelligence","Monitor robot fleet telemetry via Azure IoT Operations, drift detection, Grafana dashboards, and Fabric analytics","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fphysical-ai-toolchain\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Ffleet-intelligence\u002FSKILL.md",[],[133,134,135,136,137,37,35,138,139,140,141,142,143,144,145,146,147,148,149,150],"fleet intelligence","intelligence","fleet","telemetry","analytics","fabric","iot","grafana","detection","grafana dashboards","dashboards","operations","drift","robot","via","azure iot operations","azure iot","drift detection",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":164,"publishedAt":38},"01M69ARV021DNVZY7DWWDMBM7H","fleet-deployment","Deploy trained robot policies to edge fleets via FluxCD GitOps, image automation, and deployment gating","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fphysical-ai-toolchain\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Ffleet-deployment\u002FSKILL.md",[157,158,161],{"categoryNo":110,"categoryName":111,"taxonomyType":112,"taxonomyTypeDesc":113},{"categoryNo":159,"categoryName":160,"taxonomyType":112,"taxonomyTypeDesc":113},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":162,"categoryName":163,"taxonomyType":112,"taxonomyTypeDesc":113},"01JBSEEDCAT000000000000023","Skill与智能体开发",[165,166,135,167,168,116,169,170,146,147,171,172,173],"fleet deployment","deployment","image","automation","edge","gitops","fluxcd","fleets","gating",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":182,"publishedAt":38},"01M69ARRY00ZAZDB0N7EERY8Q8","environment-deployment","Generate, transfer, and consume environment-specific Azure, AKS, OSMO, ACR, and Azure ML deployment bundles. Use when: discovering deployed environment details; creating OSMO image manifests or platform values; preparing a HiL host; uploading or downloading deployment files through Azure Key Vault; or deploying with generated environment configuration.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fphysical-ai-toolchain\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fenvironment-deployment\u002FSKILL.md",[180,181],{"categoryNo":110,"categoryName":111,"taxonomyType":112,"taxonomyTypeDesc":113},{"categoryNo":159,"categoryName":160,"taxonomyType":112,"taxonomyTypeDesc":113},[183,166,184,167,37,36,94,185,186,187,188,189,124,190,191,192,25,193,194,195],"environment deployment","environment","aks","vault","generated","use","files","azure key vault","platform","host","values","manifests","when",{"skillNo":197,"name":198,"nameZh":6,"description":199,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":200,"categories":201,"keywords":206,"publishedAt":38},"01M69ARPMK4GHCD723YBTWYYJS","e2e-tests","Autonomously launch, monitor, retry, and report all Physical AI cloud E2E tests across independent Azure ML and OSMO GPU infrastructure.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fphysical-ai-toolchain\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fe2e-tests\u002FSKILL.md",[202,205],{"categoryNo":203,"categoryName":204,"taxonomyType":112,"taxonomyTypeDesc":113},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":110,"categoryName":111,"taxonomyType":112,"taxonomyTypeDesc":113},[207,208,209,210,211,212,37,36,35,213,119,214,215,216,217,218,219,28,25,220],"e2e tests","e2e","tests","cli","linux","launch","report","cloud","kubectl","Bash","jq","azure cli","across","retry"]