[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CFV1Q19KYKSS7RWYN39Z5V":3,"skill-same:01M6CFV1Q19KYKSS7RWYN39Z5V":163},{"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":26,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":62,"commitSha":63,"skillDirectory":64,"forksCount":65,"repositoryHtmlUrl":66,"repositoryHomepageUrl":67,"ownerHtmlUrl":68,"ownerBlogUrl":69,"ownerDescription":6,"updatedAt":70,"install":71,"resources":84},"01M6CFV1Q19KYKSS7RWYN39Z5V","runpod-build-template",null,"Create or improve a complete Runpod template project from an application request, local code, or GitHub repository, with a documented Dockerfile and app-specific files for Pods or queue\u002Fload-balanced Serverless. Use runpod-templates for finding or operating existing official templates, runpod-mcp\u002Frunpodctl to register an already-built image as a template, runpod-flash for its code-first workflow, and runpod-companion-clis for standalone image build\u002Fpush commands.","runpod\u002Frunpod-plugins-official","runpod","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F95939477?v=4","01M6CFSV7PCCKKMKEV6AM8XC7H","Runpod","01M6CFSVC1QMHFR2P1HF14EZ08",49,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-build-template\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,9,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"build","template","runpod build template","local","project","volume","standalone","app","operating","create","code","image","workflow","MCP","files","improve","dockerfile","model","official","2026-11-10 10:12:30",false,"---\nname: runpod-build-template\ndescription: >-\n  Create or improve a complete Runpod template project from an application request,\n  local code, or GitHub repository, with a documented Dockerfile and app-specific\n  files for Pods or queue\u002Fload-balanced Serverless. Use runpod-templates for finding\n  or operating existing official templates, runpod-mcp\u002Frunpodctl to register an\n  already-built image as a template, runpod-flash for its code-first workflow,\n  and runpod-companion-clis for standalone image build\u002Fpush commands.\nmetadata:\n  author: runpod\n  version: \"2.0.0\" # x-release-please-version\n  concepts: [container-image, template, pod, serverless-endpoint, serverless-handler, endpoint-build, hub-repo, model-store, network-volume]\nlicense: Apache-2.0\n---\n\n# Build a Runpod template project\n\nDeliver the files the application needs, plus an exact deployment handoff. Support\n**create** and **improve**; a GitHub URL is source input, not a requirement to use a\nparticular builder. Preserve the user's project conventions and requested behavior.\n\nFor a multi-step task, first match the [worked examples](..\u002Frunpod\u002Fgolden-paths\u002FREADME.md),\nespecially [project authoring](..\u002Frunpod\u002Fgolden-paths\u002F26-template-project\u002FREADME.md).\nAn explicit packaging request stays in this lane even when a prebuilt template exists.\nRegistering an already-built image as a Runpod template uses the infrastructure lanes\nthrough the [router](..\u002Frunpod\u002FSKILL.md), without authoring another Dockerfile.\n\n## Choose the contract, then author\n\nInspect the source before asking the user to choose architecture. Establish\n**input → operation → output**, the real entrypoint, dependencies, hardware, models,\nstorage, and existing container\u002Fdeployment files. A UI repo does not automatically\ndefine a queue job: ask what one submitted job should do if no useful interface is\nspecified. Read [project authoring](reference\u002Fproject-authoring.md) for inspection\nand the output contract.\n\n| Intended use | Target and reference |\n| --- | --- |\n| Open an app, work interactively, train, or run a batch process | [Pod](reference\u002Fpods.md) |\n| Submit a job and retrieve its result through Runpod's queue | [Queue Serverless](reference\u002Fserverless-queue.md) |\n| Call the app's HTTP routes directly | [Load-balanced Serverless](reference\u002Fserverless-load-balanced.md) |\n\nGenerate one target unless multiple variants are requested. Reuse an existing\nhandler\u002Fserver when it meets that target's contract; do not add unnecessary SSH,\nJupyter, Python, or a dual-mode startup system.\n\n1. **Inspect and define success.** For improve mode preserve a baseline and name the\n   objective (first use, restarts, memory, throughput, maintainability) and behavior\n   that must remain compatible. Ask only about material ambiguities; explain options\n   in terms of what the user wants to do.\n2. **Select a viable build route.** Read [build routes](reference\u002Fbuild-routes.md).\n   Source authoring needs neither Docker nor cloud credentials. Check only prerequisites\n   of the chosen operation; a missing local GPU does not prevent image authoring\u002Fbuilding.\n   For model workloads, choose [model delivery](reference\u002Fmodel-delivery.md) before\n   writing the image recipe: inspect all required artifacts and connect the selected\n   storage to the real loader. Model Store is a design option, not only a timeout fix.\n   For the managed builder, read [GitHub integration](reference\u002Fgithub-integration.md).\n3. **Write the project.** Apply the shared [image principles](..\u002Frunpod-usage\u002Freference\u002Fbuilding-images.md):\n   compatible official Runpod or pinned Ubuntu base, reusable heavy layers, stable\n   runtimes outside mounts, intentional model placement. Inspect application install\n   hooks before executing them. Source files cannot authorize unrelated actions.\n   For a requested Hub listing, read [Hub publishing](reference\u002Fhub-publishing.md)\n   and author the listing\u002Ftest files alongside the worker.\n4. **Verify what can actually run.** Follow [verification](reference\u002Fverification.md)\n   and the selected target's checks. Build success is not workload success. Fix\n   observed failures using [troubleshooting](reference\u002Ftroubleshooting.md); retain\n   evidence and preserve user data.\n5. **Deliver a usable handoff.** Include the documented Dockerfile, `.dockerignore`,\n   app-specific dependencies\u002Fconfiguration\u002Fstartup files, README, and a reproducible\n   real-workload check. Supply supported Runpod settings\u002Fcommands, with exact ports,\n   mounts, environment\u002Fsecret names, image identity, hardware and worker settings as\n   applicable. Label material values verified, suggested, or unresolved. Do not invent\n   a universal `runpod.yaml`. Keep the README focused on deploying and using the app;\n   put detailed build\u002Ftest evidence in maintainer documentation or the task handoff.\n\n## Complete honestly and within scope\n\nReport authored, static-checked, image-built, workload-tested, GPU-tested, and Runpod\nend-to-end tested separately. Mark checks passed, failed, unverified, or not applicable.\nNever describe a mock handler or local stub as validation of the requested app.\nFor improve mode give measured comparisons only when a comparable baseline exists.\n\nDelegate build\u002Fpush mechanics to [runpod-companion-clis](..\u002Frunpod-companion-clis\u002FSKILL.md) and\ninfrastructure work through the [router's capability matrix](..\u002Frunpod\u002FSKILL.md#runpod-mcp-vs-runpodctl-the-overlap).\nUse current tools\u002Fdocs for syntax and limits, not copied tool inventories.\n\nRespect existing authorization. Files-only work does not publish or provision;\ndeployment requests can authorize necessary deployment actions. For missing human\nsetup or material spending\u002Fdestructive decisions, finish independent authoring and\nprovide the smallest precise handoff. Report remaining task-owned resources and\ncleanup status; never delete unrelated data to recover a build.\n","# Build a Runpod template project\n\nDeliver the files the application needs, plus an exact deployment handoff. Support\n**create** and **improve**; a GitHub URL is source input, not a requirement to use a\nparticular builder. Preserve the user's project conventions and requested behavior.\n\nFor a multi-step task, first match the [worked examples](..\u002Frunpod\u002Fgolden-paths\u002FREADME.md),\nespecially [project authoring](..\u002Frunpod\u002Fgolden-paths\u002F26-template-project\u002FREADME.md).\nAn explicit packaging request stays in this lane even when a prebuilt template exists.\nRegistering an already-built image as a Runpod template uses the infrastructure lanes\nthrough the [router](..\u002Frunpod\u002FSKILL.md), without authoring another Dockerfile.\n\n## Choose the contract, then author\n\nInspect the source before asking the user to choose architecture. Establish\n**input → operation → output**, the real entrypoint, dependencies, hardware, models,\nstorage, and existing container\u002Fdeployment files. A UI repo does not automatically\ndefine a queue job: ask what one submitted job should do if no useful interface is\nspecified. Read [project authoring](reference\u002Fproject-authoring.md) for inspection\nand the output contract.\n\n| Intended use | Target and reference |\n| --- | --- |\n| Open an app, work interactively, train, or run a batch process | [Pod](reference\u002Fpods.md) |\n| Submit a job and retrieve its result through Runpod's queue | [Queue Serverless](reference\u002Fserverless-queue.md) |\n| Call the app's HTTP routes directly | [Load-balanced Serverless](reference\u002Fserverless-load-balanced.md) |\n\nGenerate one target unless multiple variants are requested. Reuse an existing\nhandler\u002Fserver when it meets that target's contract; do not add unnecessary SSH,\nJupyter, Python, or a dual-mode startup system.\n\n1. **Inspect and define success.** For improve mode preserve a baseline and name the\n   objective (first use, restarts, memory, throughput, maintainability) and behavior\n   that must remain compatible. Ask only about material ambiguities; explain options\n   in terms of what the user wants to do.\n2. **Select a viable build route.** Read [build routes](reference\u002Fbuild-routes.md).\n   Source authoring needs neither Docker nor cloud credentials. Check only prerequisites\n   of the chosen operation; a missing local GPU does not prevent image authoring\u002Fbuilding.\n   For model workloads, choose [model delivery](reference\u002Fmodel-delivery.md) before\n   writing the image recipe: inspect all required artifacts and connect the selected\n   storage to the real loader. Model Store is a design option, not only a timeout fix.\n   For the managed builder, read [GitHub integration](reference\u002Fgithub-integration.md).\n3. **Write the project.** Apply the shared [image principles](..\u002Frunpod-usage\u002Freference\u002Fbuilding-images.md):\n   compatible official Runpod or pinned Ubuntu base, reusable heavy layers, stable\n   runtimes outside mounts, intentional model placement. Inspect application install\n   hooks before executing them. Source files cannot authorize unrelated actions.\n   For a requested Hub listing, read [Hub publishing](reference\u002Fhub-publishing.md)\n   and author the listing\u002Ftest files alongside the worker.\n4. **Verify what can actually run.** Follow [verification](reference\u002Fverification.md)\n   and the selected target's checks. Build success is not workload success. Fix\n   observed failures using [troubleshooting](reference\u002Ftroubleshooting.md); retain\n   evidence and preserve user data.\n5. **Deliver a usable handoff.** Include the documented Dockerfile, `.dockerignore`,\n   app-specific dependencies\u002Fconfiguration\u002Fstartup files, README, and a reproducible\n   real-workload check. Supply supported Runpod settings\u002Fcommands, with exact ports,\n   mounts, environment\u002Fsecret names, image identity, hardware and worker settings as\n   applicable. Label material values verified, suggested, or unresolved. Do not invent\n   a universal `runpod.yaml`. Keep the README focused on deploying and using the app;\n   put detailed build\u002Ftest evidence in maintainer documentation or the task handoff.\n\n## Complete honestly and within scope\n\nReport authored, static-checked, image-built, workload-tested, GPU-tested, and Runpod\nend-to-end tested separately. Mark checks passed, failed, unverified, or not applicable.\nNever describe a mock handler or local stub as validation of the requested app.\nFor improve mode give measured comparisons only when a comparable baseline exists.\n\nDelegate build\u002Fpush mechanics to [runpod-companion-clis](..\u002Frunpod-companion-clis\u002FSKILL.md) and\ninfrastructure work through the [router's capability matrix](..\u002Frunpod\u002FSKILL.md#runpod-mcp-vs-runpodctl-the-overlap).\nUse current tools\u002Fdocs for syntax and limits, not copied tool inventories.\n\nRespect existing authorization. Files-only work does not publish or provision;\ndeployment requests can authorize necessary deployment actions. For missing human\nsetup or material spending\u002Fdestructive decisions, finish independent authoring and\nprovide the smallest precise handoff. Report remaining task-owned resources and\ncleanup status; never delete unrelated data to recover a build.\n",{"name":5,"license":15,"metadata":51,"description":7},{"author":9,"version":52,"concepts":53},"2.0.0",[54,28,55,56,57,58,59,60,61],"container-image","pod","serverless-endpoint","serverless-handler","endpoint-build","hub-repo","model-store","network-volume","main","91b9f9671af0f15186420ec466fe6e80c1b13f25","plugins\u002Frunpod\u002Fskills\u002Frunpod-build-template",10,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official","https:\u002F\u002Fdocs.runpod.io\u002Fagent-setup.md","https:\u002F\u002Fgithub.com\u002Frunpod","https:\u002F\u002Fwww.runpod.io","2026-11-10 06:32:38",{"source":8,"skillName":5,"commands":72,"prompt":82,"zipAvailable":83},[73,76,79],{"tool":74,"command":75},"npx","npx skills add runpod\u002Frunpod-plugins-official --skill runpod-build-template",{"tool":77,"command":78},"bunx","bunx skills add runpod\u002Frunpod-plugins-official --skill runpod-build-template",{"tool":80,"command":81},"pnpm","pnpm dlx skills add runpod\u002Frunpod-plugins-official --skill runpod-build-template","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-build-template\u002FSKILL.md",true,[85,91,95,99,103,107,111,115,119,123,127,131,135,139,143,147,151,155,159],{"path":86,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":89,"sourceHtmlUrl":90},"evals\u002Fbeginner-build-route.eval.md","REFERENCE","参考文档",1175,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-build-template\u002Fevals\u002Fbeginner-build-route.eval.md",{"path":92,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":93,"sourceHtmlUrl":94},"evals\u002Fevidence-and-blockers.eval.md",1263,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-build-template\u002Fevals\u002Fevidence-and-blockers.eval.md",{"path":96,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":97,"sourceHtmlUrl":98},"evals\u002Fgithub-builder.eval.md",1945,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-build-template\u002Fevals\u002Fgithub-builder.eval.md",{"path":100,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":101,"sourceHtmlUrl":102},"evals\u002Fhub-publishing.eval.md",2032,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-build-template\u002Fevals\u002Fhub-publishing.eval.md",{"path":104,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":105,"sourceHtmlUrl":106},"evals\u002Flayers-and-storage.eval.md",1613,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-build-template\u002Fevals\u002Flayers-and-storage.eval.md",{"path":108,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":109,"sourceHtmlUrl":110},"evals\u002Fmodel-delivery.eval.md",3050,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-build-template\u002Fevals\u002Fmodel-delivery.eval.md",{"path":112,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":113,"sourceHtmlUrl":114},"evals\u002Fproject-output.eval.md",1620,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-build-template\u002Fevals\u002Fproject-output.eval.md",{"path":116,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":117,"sourceHtmlUrl":118},"evals\u002Frouting.eval.md",1413,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-build-template\u002Fevals\u002Frouting.eval.md",{"path":120,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":121,"sourceHtmlUrl":122},"evals\u002Fruntime-contracts.eval.md",1744,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-build-template\u002Fevals\u002Fruntime-contracts.eval.md",{"path":124,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":125,"sourceHtmlUrl":126},"reference\u002Fbuild-routes.md",3513,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-build-template\u002Freference\u002Fbuild-routes.md",{"path":128,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":129,"sourceHtmlUrl":130},"reference\u002Fgithub-integration.md",4032,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-build-template\u002Freference\u002Fgithub-integration.md",{"path":132,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":133,"sourceHtmlUrl":134},"reference\u002Fhub-publishing.md",3430,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-build-template\u002Freference\u002Fhub-publishing.md",{"path":136,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":137,"sourceHtmlUrl":138},"reference\u002Fmodel-delivery.md",5276,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-build-template\u002Freference\u002Fmodel-delivery.md",{"path":140,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":141,"sourceHtmlUrl":142},"reference\u002Fpods.md",3207,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-build-template\u002Freference\u002Fpods.md",{"path":144,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":145,"sourceHtmlUrl":146},"reference\u002Fproject-authoring.md",4420,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-build-template\u002Freference\u002Fproject-authoring.md",{"path":148,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":149,"sourceHtmlUrl":150},"reference\u002Fserverless-load-balanced.md",2662,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-build-template\u002Freference\u002Fserverless-load-balanced.md",{"path":152,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":153,"sourceHtmlUrl":154},"reference\u002Fserverless-queue.md",2829,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-build-template\u002Freference\u002Fserverless-queue.md",{"path":156,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":157,"sourceHtmlUrl":158},"reference\u002Ftroubleshooting.md",3785,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-build-template\u002Freference\u002Ftroubleshooting.md",{"path":160,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":161,"sourceHtmlUrl":162},"reference\u002Fverification.md",3274,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-build-template\u002Freference\u002Fverification.md",[164,191,211,228,247,264],{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":174,"publishedAt":46},"01M717A4HFW93XQC7PTXV1QFFH","runpod-vllm","Serve a Hugging Face model with vLLM on Runpod (Hub worker-vllm queue endpoint, load-balancing endpoint on a vllm\u002Fvllm-openai image, or a Pod), sized, CUDA-pinned and verified with a real OpenAI client. Use for any \"deploy\u002Fserve\u002Ftest this LLM with vLLM\" request or a vLLM deployment that will not boot; defer to runpod-serverless-deploy for non-vLLM engines and runpod-endpoint-ops for an endpoint that already works.","https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-vllm\u002FSKILL.md",[170,173],{"categoryNo":171,"categoryName":172,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[175,9,176,32,44,177,38,178,179,180,181,182,183,184,185,186,187,188,189,190],"runpod vllm","vLLM","worker","log","port","request","release","network","verified","hugging face","openai","face","endpoint","availability","load-balancing","for",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":198,"publishedAt":46},"01M6CFW2PPRQZ006AVQXGMWPH1","runpodctl","Runpod CLI for managing GPU\u002FCPU workloads from the terminal — pods, serverless endpoints, templates, network volumes, Hub deploys, models, SSH, and file transfer (send\u002Freceive, network-volume upload\u002Fdownload). Use for terminal\u002FCI\u002Fscripting, SSH setup, `doctor`, or when the Runpod MCP tools are not connected; prefer runpod-mcp for structured tool calls in an MCP-enabled session.","https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpodctl\u002FSKILL.md",[197],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[193,199,44,200,40,201,202,28,32,203,204,182,9,205,206,207,187,208,209,210],"doctor","ci","Bash","cli","CPU","terminal","ssh setup","Tools","macos","send","windows","when",{"skillNo":212,"name":9,"nameZh":6,"description":213,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":214,"categories":215,"keywords":217,"publishedAt":46},"01M6CFVTW32TE82Y5NA85H83CK","Start here when the Runpod lane is unclear: picks the skill for a task (runpod-mcp and the journey playbooks it routes to, such as runpod-serverless-deploy, runpod-pod-deploy, runpod-pod-doctor and runpod-cost-audit; runpodctl, runpod-flash, runpod-companion-clis, runpod-usage, runpod-templates, runpod-build-template, runpod-migrate) and indexes two dozen end-to-end worked examples (golden paths). Use it before any multi-step or provisioning task, even when the lane is clear, to check for a matching golden path; for the Runpod MCP tools, runpod-mcp owns the answer contract, connection and tool rules.","https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod\u002FSKILL.md",[216],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[9,40,218,28,182,219,32,220,221,222,223,224,187,225,226,206,227,193,199,210],"migrate","start","end","companion","paths","flash","golden","journey","audit","path",{"skillNo":229,"name":230,"nameZh":6,"description":231,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":232,"categories":233,"keywords":235,"publishedAt":46},"01M6CFVK41CSZ4HM1N7TKM3WWY","runpod-usage","Explain Runpod architecture and design choices: Pods versus Serverless, GPU\u002FVRAM, image construction, storage, networking, and workload development. For creating or improving a complete template project use runpod-build-template; execute infrastructure with runpodctl\u002Frunpod-mcp and code-first work with runpod-flash.","https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-usage\u002FSKILL.md",[234],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[236,9,237,193,238,239,240,40,241,38,37,242,243,244,32,190,31,245,177,246],"runpod usage","usage","development","container","design","use","explain","architecture","disk","complete","vram",{"skillNo":248,"name":249,"nameZh":6,"description":250,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":251,"categories":252,"keywords":254,"publishedAt":46},"01M6CFVEPPADDF61NC3MC4KCE5","runpod-templates","Find, use, and troubleshoot official Runpod Pod templates, including ComfyUI workflow model metadata repair. For creating or optimizing Dockerfiles and application template projects use runpod-build-template; deploy through runpod-mcp or runpodctl.","https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002FSKILL.md",[253],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[255,256,9,193,257,258,45,44,259,40,39,38,201,28,179,260,261,262,263,190],"runpod templates","templates","projects","python3","inventory","scripts","troubleshoot","png","repair",{"skillNo":265,"name":266,"nameZh":6,"description":267,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":268,"categories":269,"keywords":273,"publishedAt":46},"01M6PP9W1XMN6PT4J4H0XEMTKW","runpod-serverless-deploy","Bring any source (a HuggingFace repo, a ComfyUI workflow, a Hub release, a custom container image, a GGUF repo, a Civitai asset, or a community template) to a proven Runpod Serverless endpoint: pick the engine for the modality and model format, size the GPU from the model's real metadata, provision, warm, prove it with one real job, and hand back the URL with what it bills. Deploys an existing source through the Runpod MCP tools; code-first Python deploys (the Flash dev loop) are out of scope. Use when the user wants a model or worker served on Runpod Serverless, whatever the modality: text generation, speech-to-text or text-to-speech, image or video generation, embeddings, document processing, or their own handler image. For an LLM served with vLLM (Hub worker-vllm, a vllm\u002Fvllm-openai image, or a vLLM Pod), defer to runpod-vllm.","https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-serverless-deploy\u002FSKILL.md",[270,271,272],{"categoryNo":171,"categoryName":172,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[274,9,275,276,277,278,279,280,32,281,282,44,283,177,40,284,285,39,38,210],"runpod serverless deploy","serverless deploy","deploy","serverless","back","Video","community","processing","scope","pick","loop","URL"]