[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PP86NE480ZTZXETDCKEJ02":3,"skill-same:01M6PP86NE480ZTZXETDCKEJ02":113},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":61,"ownerHtmlUrl":62,"ownerBlogUrl":63,"ownerDescription":6,"updatedAt":64,"install":65,"resources":78},"01M6PP86NE480ZTZXETDCKEJ02","runpod-companion-clis",null,"Companion CLIs for Runpod workflows — HuggingFace, GitHub, Docker, and AWS. Use runpod-build-template for complete template project authoring, and the ComfyUI model-repair guide in runpod-templates for imported workflows lacking model download metadata.","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-companion-clis\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",[24,25,9,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"companion","companion clis","runpod companion clis","Model Download","docker","repo","for","repair","windows","macos","guide","authoring","network","template project","template","image","workflows","project","model","volume","2026-11-10 10:12:30",false,"---\nname: runpod-companion-clis\ndescription: Companion CLIs for Runpod workflows — HuggingFace, GitHub, Docker, and AWS. Use runpod-build-template for complete template project authoring, and the ComfyUI model-repair guide in runpod-templates for imported workflows lacking model download metadata.\ncompatibility: Linux, macOS, Windows\nmetadata:\n  author: runpod\n  version: \"2.1.0\" # x-release-please-version\n  concepts: [container-image, network-volume, hub-repo]\nlicense: Apache-2.0\n---\n\n# Companion CLIs\n\nFor creating or improving a documented template project, start with\n[runpod-build-template](..\u002Frunpod-build-template\u002FSKILL.md); return here for the selected\nCLI operation.\n\nFour CLIs commonly needed alongside Runpod. Each has its own **credentials + command reference** in [`reference\u002F`](reference\u002F) — plus a one-time `\u003Ccli>-setup.md` for install (only opened if the CLI isn't installed). Load only the one the task needs, not all four.\n\nIf the request starts with an imported ComfyUI workflow whose model filenames lack\nverified URLs or hashes, route to the\n[ComfyUI model-repair guide](..\u002Frunpod-templates\u002Freference\u002Fcomfyui-model-repair.md) in\nrunpod-templates. Return here when the\nexact Hugging Face repository\u002Ffile is already known and the task is simply to\ndownload, cache, or bake that artifact.\n\n| CLI | Use it to | Full reference |\n|-----|-----------|----------------|\n| `hf` (HuggingFace) | Download models from the Hub to cache\u002Fbake into images | [reference\u002Fhuggingface.md](reference\u002Fhuggingface.md) |\n| `gh` (GitHub) | Manage worker repos + cut releases (Hub indexes releases) | [reference\u002Fgithub.md](reference\u002Fgithub.md) |\n| `docker` | Build\u002Fvalidate\u002Fpush images to Docker Hub for Runpod to pull | [reference\u002Fdocker.md](reference\u002Fdocker.md) |\n| `aws` (S3) | Read\u002Fwrite network-volume storage over Runpod's S3 API | [reference\u002Faws.md](reference\u002Faws.md) |\n\nEach requires credentials before use. Read the per-tool reference for auth steps and commands; install is a separate one-time `\u003Ccli>-setup.md`.\n\nThese CLIs are usually one step inside a larger job. For the whole job the verified example is\nin [runpod\u002Fgolden-paths\u002FREADME.md](..\u002Frunpod\u002Fgolden-paths\u002FREADME.md) — baking vs mounting a\nmodel ([25](..\u002Frunpod\u002Fgolden-paths\u002F25-bake-vs-mount\u002FREADME.md)), building a minimal image\n([22](..\u002Frunpod\u002Fgolden-paths\u002F22-minimal-pod-image\u002FREADME.md)), or moving data to a network\nvolume ([07](..\u002Frunpod\u002Fgolden-paths\u002F07-network-volume-handoff.md)).\n\nThese are third-party CLIs on their own release trains, so **`\u003Ccli> --help` is authoritative\nfor flags and subcommands** — the references here cover the Runpod-specific usage and the\ntraps, not the tool's full surface. Check `--help` before reporting that one of them cannot do\nsomething.\n\n## Windows: choose the shell, then set up WSL2 if needed\n\nCheck existing native, WSL2 or remote tools before installing another copy. The Windows\n`hf` and `gh` setup recipes in this skill use WSL2 and their Linux installers. If choosing\nthat route and WSL2 is missing, run this in PowerShell as Administrator, then restart if\nprompted:\n\n```powershell\nwsl --install\n```\n\nAfterward open the Ubuntu app to finish setup, then follow the **Linux** instructions in\neach reference. Keep commands, credentials and paths in the selected environment. File\nauthoring alone does not require installing these CLIs.\n\n## HuggingFace CLI\n\nDownload models locally so they're cached for a Docker build\u002Frun. Auth and `hf download` recipes: **[reference\u002Fhuggingface.md](reference\u002Fhuggingface.md)** (install: [reference\u002Fhuggingface-setup.md](reference\u002Fhuggingface-setup.md)).\n\n- Use the standalone `hf` CLI, **not** `pip install huggingface_hub` (that's the older `huggingface-cli` with different syntax).\n- Auth via `hf auth login`, or `export HF_TOKEN=hf_...` (env var wins over saved token).\n\n## GitHub CLI\n\nManage worker repositories and cut releases. Auth and commands: **[reference\u002Fgithub.md](reference\u002Fgithub.md)** (install + SSH-key setup: [reference\u002Fgithub-setup.md](reference\u002Fgithub-setup.md)).\n\n- **The Hub indexes releases, not commits** — every Hub listing update needs a new `gh release create`.\n- One SSH key (`ssh-keygen -t ed25519`) registers with both GitHub (`gh ssh-key add`) and HuggingFace (paste in browser).\n\n## Docker\n\nBuild, validate, and push images to Docker Hub. Credentials and commands: **[reference\u002Fdocker.md](reference\u002Fdocker.md)** (install: [reference\u002Fdocker-setup.md](reference\u002Fdocker-setup.md)).\n\n- **Always build `--platform=linux\u002Famd64`** — Runpod runs on x86 Linux.\n- **Always use explicit semantic tags; never `latest`** — `latest` doesn't track the newest push, so workers can silently pull the wrong image.\n- Docker Hub auth uses a **personal access token**, not your password. For private images, register the credential once in Console → Container Registry Settings.\n\n## AWS CLI\n\nAccess network-volume storage over Runpod's S3-compatible API (bucket name = network volume ID). Credentials, region rules, and commands: **[reference\u002Faws.md](reference\u002Faws.md)** (install: [reference\u002Faws-setup.md](reference\u002Faws-setup.md)).\n\n- Runpod's S3 API, **not AWS**: access key = Runpod **user id** (`user_...`), secret = S3 API key (`rps_...`).\n- **S3 API keys are Console-only.** No `runpodctl`\u002FREST\u002FGraphQL creates them — if they're not already in `~\u002F.aws\u002Fcredentials`\u002Fenv and S3 access is needed, **stop and ask the user** to generate them (Settings > S3 API Keys).\n- Every command needs `--region DATACENTER --endpoint-url https:\u002F\u002Fs3api-DATACENTER.runpod.io\u002F` (datacenter = the volume's DC, not an AWS region).\n- For large\u002Fmany-file transfers with resume, prefer `runpodctl network-volume upload`\u002F`download` (v3.1.0+, same S3 API keys; see the `runpodctl` skill). On an older runpodctl, see [reference\u002Faws.md → optional resumable volume transfers](reference\u002Faws.md#optional-resumable-volume-transfers-community-tool).\n","# Companion CLIs\n\nFor creating or improving a documented template project, start with\n[runpod-build-template](..\u002Frunpod-build-template\u002FSKILL.md); return here for the selected\nCLI operation.\n\nFour CLIs commonly needed alongside Runpod. Each has its own **credentials + command reference** in [`reference\u002F`](reference\u002F) — plus a one-time `\u003Ccli>-setup.md` for install (only opened if the CLI isn't installed). Load only the one the task needs, not all four.\n\nIf the request starts with an imported ComfyUI workflow whose model filenames lack\nverified URLs or hashes, route to the\n[ComfyUI model-repair guide](..\u002Frunpod-templates\u002Freference\u002Fcomfyui-model-repair.md) in\nrunpod-templates. Return here when the\nexact Hugging Face repository\u002Ffile is already known and the task is simply to\ndownload, cache, or bake that artifact.\n\n| CLI | Use it to | Full reference |\n|-----|-----------|----------------|\n| `hf` (HuggingFace) | Download models from the Hub to cache\u002Fbake into images | [reference\u002Fhuggingface.md](reference\u002Fhuggingface.md) |\n| `gh` (GitHub) | Manage worker repos + cut releases (Hub indexes releases) | [reference\u002Fgithub.md](reference\u002Fgithub.md) |\n| `docker` | Build\u002Fvalidate\u002Fpush images to Docker Hub for Runpod to pull | [reference\u002Fdocker.md](reference\u002Fdocker.md) |\n| `aws` (S3) | Read\u002Fwrite network-volume storage over Runpod's S3 API | [reference\u002Faws.md](reference\u002Faws.md) |\n\nEach requires credentials before use. Read the per-tool reference for auth steps and commands; install is a separate one-time `\u003Ccli>-setup.md`.\n\nThese CLIs are usually one step inside a larger job. For the whole job the verified example is\nin [runpod\u002Fgolden-paths\u002FREADME.md](..\u002Frunpod\u002Fgolden-paths\u002FREADME.md) — baking vs mounting a\nmodel ([25](..\u002Frunpod\u002Fgolden-paths\u002F25-bake-vs-mount\u002FREADME.md)), building a minimal image\n([22](..\u002Frunpod\u002Fgolden-paths\u002F22-minimal-pod-image\u002FREADME.md)), or moving data to a network\nvolume ([07](..\u002Frunpod\u002Fgolden-paths\u002F07-network-volume-handoff.md)).\n\nThese are third-party CLIs on their own release trains, so **`\u003Ccli> --help` is authoritative\nfor flags and subcommands** — the references here cover the Runpod-specific usage and the\ntraps, not the tool's full surface. Check `--help` before reporting that one of them cannot do\nsomething.\n\n## Windows: choose the shell, then set up WSL2 if needed\n\nCheck existing native, WSL2 or remote tools before installing another copy. The Windows\n`hf` and `gh` setup recipes in this skill use WSL2 and their Linux installers. If choosing\nthat route and WSL2 is missing, run this in PowerShell as Administrator, then restart if\nprompted:\n\n```powershell\nwsl --install\n```\n\nAfterward open the Ubuntu app to finish setup, then follow the **Linux** instructions in\neach reference. Keep commands, credentials and paths in the selected environment. File\nauthoring alone does not require installing these CLIs.\n\n## HuggingFace CLI\n\nDownload models locally so they're cached for a Docker build\u002Frun. Auth and `hf download` recipes: **[reference\u002Fhuggingface.md](reference\u002Fhuggingface.md)** (install: [reference\u002Fhuggingface-setup.md](reference\u002Fhuggingface-setup.md)).\n\n- Use the standalone `hf` CLI, **not** `pip install huggingface_hub` (that's the older `huggingface-cli` with different syntax).\n- Auth via `hf auth login`, or `export HF_TOKEN=hf_...` (env var wins over saved token).\n\n## GitHub CLI\n\nManage worker repositories and cut releases. Auth and commands: **[reference\u002Fgithub.md](reference\u002Fgithub.md)** (install + SSH-key setup: [reference\u002Fgithub-setup.md](reference\u002Fgithub-setup.md)).\n\n- **The Hub indexes releases, not commits** — every Hub listing update needs a new `gh release create`.\n- One SSH key (`ssh-keygen -t ed25519`) registers with both GitHub (`gh ssh-key add`) and HuggingFace (paste in browser).\n\n## Docker\n\nBuild, validate, and push images to Docker Hub. Credentials and commands: **[reference\u002Fdocker.md](reference\u002Fdocker.md)** (install: [reference\u002Fdocker-setup.md](reference\u002Fdocker-setup.md)).\n\n- **Always build `--platform=linux\u002Famd64`** — Runpod runs on x86 Linux.\n- **Always use explicit semantic tags; never `latest`** — `latest` doesn't track the newest push, so workers can silently pull the wrong image.\n- Docker Hub auth uses a **personal access token**, not your password. For private images, register the credential once in Console → Container Registry Settings.\n\n## AWS CLI\n\nAccess network-volume storage over Runpod's S3-compatible API (bucket name = network volume ID). Credentials, region rules, and commands: **[reference\u002Faws.md](reference\u002Faws.md)** (install: [reference\u002Faws-setup.md](reference\u002Faws-setup.md)).\n\n- Runpod's S3 API, **not AWS**: access key = Runpod **user id** (`user_...`), secret = S3 API key (`rps_...`).\n- **S3 API keys are Console-only.** No `runpodctl`\u002FREST\u002FGraphQL creates them — if they're not already in `~\u002F.aws\u002Fcredentials`\u002Fenv and S3 access is needed, **stop and ask the user** to generate them (Settings > S3 API Keys).\n- Every command needs `--region DATACENTER --endpoint-url https:\u002F\u002Fs3api-DATACENTER.runpod.io\u002F` (datacenter = the volume's DC, not an AWS region).\n- For large\u002Fmany-file transfers with resume, prefer `runpodctl network-volume upload`\u002F`download` (v3.1.0+, same S3 API keys; see the `runpodctl` skill). On an older runpodctl, see [reference\u002Faws.md → optional resumable volume transfers](reference\u002Faws.md#optional-resumable-volume-transfers-community-tool).\n",{"name":5,"license":15,"metadata":49,"description":7,"compatibility":55},{"author":9,"version":50,"concepts":51},"2.1.0",[52,53,54],"container-image","network-volume","hub-repo","Linux, macOS, Windows","main","78415a3cd1084678bba59a6e3b045f56f2e114c0","plugins\u002Frunpod\u002Fskills\u002Frunpod-companion-clis",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","2026-11-12 09:58:55",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add runpod\u002Frunpod-plugins-official --skill runpod-companion-clis",{"tool":71,"command":72},"bunx","bunx skills add runpod\u002Frunpod-plugins-official --skill runpod-companion-clis",{"tool":74,"command":75},"pnpm","pnpm dlx skills add runpod\u002Frunpod-plugins-official --skill runpod-companion-clis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-companion-clis\u002FSKILL.md",true,[79,85,89,93,97,101,105,109],{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"reference\u002Faws-setup.md","REFERENCE","参考文档",369,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-companion-clis\u002Freference\u002Faws-setup.md",{"path":86,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":87,"sourceHtmlUrl":88},"reference\u002Faws.md",6696,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-companion-clis\u002Freference\u002Faws.md",{"path":90,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":91,"sourceHtmlUrl":92},"reference\u002Fdocker-setup.md",2078,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-companion-clis\u002Freference\u002Fdocker-setup.md",{"path":94,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":95,"sourceHtmlUrl":96},"reference\u002Fdocker.md",3754,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-companion-clis\u002Freference\u002Fdocker.md",{"path":98,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":99,"sourceHtmlUrl":100},"reference\u002Fgithub-setup.md",2406,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-companion-clis\u002Freference\u002Fgithub-setup.md",{"path":102,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":103,"sourceHtmlUrl":104},"reference\u002Fgithub.md",2139,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-companion-clis\u002Freference\u002Fgithub.md",{"path":106,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":107,"sourceHtmlUrl":108},"reference\u002Fhuggingface-setup.md",602,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-companion-clis\u002Freference\u002Fhuggingface-setup.md",{"path":110,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":111,"sourceHtmlUrl":112},"reference\u002Fhuggingface.md",2324,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-companion-clis\u002Freference\u002Fhuggingface.md",[114,139,160,176,196,214],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":124,"publishedAt":44},"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",[120,121],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":122,"categoryName":123,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[125,9,126,43,42,127,39,128,129,130,131,36,132,133,134,135,136,137,138,30],"runpod vllm","vLLM","worker","log","port","request","release","verified","hugging face","openai","face","endpoint","availability","load-balancing",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":148,"publishedAt":44},"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",[145],{"categoryNo":146,"categoryName":147,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[141,149,42,150,151,152,153,38,43,154,155,36,9,156,157,33,136,158,32,159],"doctor","ci","MCP","Bash","cli","CPU","terminal","ssh setup","Tools","send","when",{"skillNo":161,"name":9,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":166,"publishedAt":44},"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",[165],{"categoryNo":146,"categoryName":147,"taxonomyType":21,"taxonomyTypeDesc":22},[9,151,167,38,36,168,43,169,24,170,171,172,136,173,174,157,175,141,149,159],"migrate","start","end","paths","flash","golden","journey","audit","path",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":183,"publishedAt":44},"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",[182],{"categoryNo":146,"categoryName":147,"taxonomyType":21,"taxonomyTypeDesc":22},[184,9,185,141,186,187,188,151,189,39,190,191,192,193,43,30,41,194,127,195],"runpod usage","usage","development","container","design","use","code","explain","architecture","disk","complete","vram",{"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":203,"publishedAt":44},"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",[202],{"categoryNo":146,"categoryName":147,"taxonomyType":21,"taxonomyTypeDesc":22},[204,205,9,141,206,207,208,42,209,151,210,39,152,38,129,211,212,213,31,30],"runpod templates","templates","projects","python3","official","inventory","workflow","scripts","troubleshoot","png",{"skillNo":215,"name":216,"nameZh":6,"description":217,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":218,"categories":219,"keywords":223,"publishedAt":44},"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",[220,221,222],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":122,"categoryName":123,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":146,"categoryName":147,"taxonomyType":21,"taxonomyTypeDesc":22},[224,9,225,226,227,228,229,230,43,231,232,42,233,127,151,234,235,210,39,159],"runpod serverless deploy","serverless deploy","deploy","serverless","back","Video","community","processing","scope","pick","loop","URL"]