[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CFVEPPADDF61NC3MC4KCE5":3,"skill-same:01M6CFVEPPADDF61NC3MC4KCE5":178},{"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":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":60,"ownerHtmlUrl":61,"ownerBlogUrl":62,"ownerDescription":6,"updatedAt":63,"install":64,"resources":77},"01M6CFVEPPADDF61NC3MC4KCE5","runpod-templates",null,"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.","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-templates\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,9,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"templates","runpod templates","for","repair","png","troubleshoot","scripts","port","template","Bash","image","workflow","MCP","inventory","model","official","python3","projects","runpodctl","2026-11-10 10:12:30",false,"---\nname: runpod-templates\ndescription: >-\n  Find, use, and troubleshoot official Runpod Pod templates, including ComfyUI\n  workflow model metadata repair. For creating or optimizing Dockerfiles and\n  application template projects use runpod-build-template; deploy through runpod-mcp\n  or runpodctl.\nallowed-tools: Bash(python3 -B ${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Frunpod-templates\u002Fscripts\u002Fextract_png_workflow.py:*) Bash(python3 -B ${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Frunpod-templates\u002Fscripts\u002Finventory_workflow_models.py:*) Bash(python3 -B ${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Frunpod-templates\u002Fscripts\u002Fapply_model_metadata.py:*)\nmetadata:\n  author: runpod\n  version: \"2.0.0\" # x-release-please-version\n  concepts: [template, container-image, pod, exposed-port]\nlicense: Apache-2.0\n---\n\n# Official Runpod templates\n\nFor explicit source packaging or template optimization, use\n[runpod-build-template](..\u002Frunpod-build-template\u002FSKILL.md). For ordinary workload\ndeployment, **prefer an official template over building an image.** Runpod maintains prebuilt\nimages for common workloads; deploying one is a create + poll, with no SSH install\nstep. This skill is the reference for *what those images actually are*. It does not\nmanage infrastructure — deploy with **runpod-mcp** (if connected) or **runpodctl**.\n\n## Terms — \"template\" vs the Hub\n\nTwo different products share the word \"Hub\", and conflating them derails discovery:\n\n| Term | What it is | Runs as | Discover with |\n| --- | --- | --- | --- |\n| **Pod template** (this skill) | A saved pod config — image + ports + disk + env. The official ones appear on Console **Hub template pages** (`console.runpod.io\u002Fhub\u002Ftemplate\u002F\u003Cid>`) | a **pod** | `runpodctl template list --type official` \u002F `template search` · REST `GET \u002Fv2\u002Fcatalog\u002Ftemplates` |\n| **Hub repo \u002F listing** | A packaged **serverless worker** (e.g. `runpod-workers\u002Fworker-comfyui`) with a handler, deployed as an endpoint | **serverless** | `runpodctl hub list` \u002F `hub search` · MCP `list-hub-repos` \u002F `deploy-hub-repo` |\n\nSame word, disjoint catalogs: `hub search comfyui` returns only the serverless worker\nand none of the official ComfyUI **pod** templates, and `template search` returns no\nHub repos. In the REST v2 catalog, pod vs serverless templates are told apart by each\nentry's `serverless` flag.\n\n## What \"official\" means, and how to find them\n\nA template is Runpod-maintained when it reports `isRunpod: true`. Anything else in search\nresults is community-published: usable, but not covered by this skill and not\nversion-guaranteed.\n\n```bash\nrunpodctl template list --type official   # the whole official set (14 as of 2026-08-25)\nrunpodctl template search \u003Cname>          # by name; check isRunpod: true\nrunpodctl template get \u003Ctemplate-id>      # image, ports, portsConfig, disk + full readme\n```\n\n`template get` returns the template's **readme** — the description maintained alongside\nthe image, and the authoritative answer when it disagrees with this skill. Take image\ntags, ports, and env from these commands, not from these files: the templates ship on\ntheir own release train and move faster than this repo. The reference files record the\n**shape and the gotchas**, which is the expensive part to rediscover.\n\n⚠️ **`runpodctl hub ...` is not how you find pod templates** — see [Terms](#terms--template-vs-the-hub).\n\nTo hand a user a Console link, use `https:\u002F\u002Fconsole.runpod.io\u002Fhub\u002Ftemplate\u002F\u003Ctemplate-id>`.\n\n### REST v2 has no template search — only slices you filter yourself\n\nREST v2 has no query\u002Fsearch parameter for templates, so every \"search\" is a client-side\nfilter over a fetched slice:\n\n| Endpoint | Params | Returns |\n| --- | --- | --- |\n| `GET \u002Fv2\u002Fcatalog\u002Ftemplates` | `source=official\\|verified\\|community` (default `official`) | the public catalog slice |\n| `GET \u002Fv2\u002Ftemplates` | none | only templates **you own** |\n| `GET \u002Fv2\u002Ftemplates\u002F{id}` | — | one template, owned or catalog |\n\n**`official` (14) and `verified` (3) are fully enumerable; `community` is capped at 100\nwith pagination explicitly unsupported.** A community template past that cap never\nenters a slice the API can return, and `runpodctl template search` reads those same\nserver-side slices — so it has no view past the cap either. If a user names one you\ncannot find, ask them for the template id rather than concluding it does not exist.\n\n`isRunpod` is a GraphQL\u002Fv1 field with **no v2 equivalent** — in v2, \"official\" is the\n`source` slice you requested, not a flag on the record.\n\nCatalog entries carry **`allowedCudaVersions`**, which is the reliable way to pick between\nCUDA-line variants of the same template — pair it with `runpodctl pod create\n--min-cuda-version` instead of inferring from the GPU name.\n\n## The templates\n\n| Workload | Reference | Deploy walkthrough |\n| --- | --- | --- |\n| **ComfyUI** — image generation UI at a URL | [`reference\u002Fcomfyui.md`](reference\u002Fcomfyui.md) | [golden path 02, variant B](..\u002Frunpod\u002Fgolden-paths\u002F02-comfyui-pod\u002Fvariant-b-prebuilt.md) |\n| **PyTorch** — general GPU base \u002F dev box (2.1 → 2.9, incl. cluster + ROCm builds) | [`reference\u002Fpytorch.md`](reference\u002Fpytorch.md) | [golden path 06](..\u002Frunpod\u002Fgolden-paths\u002F06-dev-pod.md) |\n| **Ubuntu** — bare 20.04 \u002F 22.04 \u002F 24.04 (**CPU** category) | TODO | — |\n| **Network storage file browser** (GPU + CPU) | TODO | [golden path 07](..\u002Frunpod\u002Fgolden-paths\u002F07-network-volume-handoff.md) |\n\nAdd a template by adding one file here and one row above. Do not create a new skill\nper template — the task shape is identical and every registered skill costs context in\nevery session.\n\n## How to use a template reference\n\nEach file under `reference\u002F` answers the same questions in the same order, so an agent\ncan skim to the one it needs:\n\n1. **Identity** — template name, id, image, upstream source repo.\n2. **Variants** — CUDA\u002Farch\u002FGPU-generation splits and which to pick.\n3. **Ports and credentials** — what is exposed and any default login.\n4. **Autostart** — what is already running on boot, with the exact command.\n5. **Paths** — where the app, its config, and its data live (and what a network\n   volume mount changes).\n6. **Readiness** — how long first boot takes and the exact signal for \"actually\n   serving\". `Running` is never the signal.\n7. **What does not ship** — the gap between \"booted\" and \"usable\", and how to close\n   it programmatically rather than by clicking.\n8. **Sizing** — container disk and minimum VRAM.\n9. **Version pinning** — how to hold a known-good version.\n\nOne file is the exception: [`reference\u002Fcomfyui-model-repair.md`](reference\u002Fcomfyui-model-repair.md)\nis a **usage guide** — a ComfyUI workflow repair procedure that drives the scripts in\n[`scripts\u002F`](scripts\u002F) — not a 9-question template reference.\n\n## Routing onward — this skill is the hub, not the destination\n\nA user asking about a template rarely wants the reference file itself; they want a\ntemplate deployed, fixed, or replaced. Land here, identify which, and hand off:\n\n| The user wants to… | Send them to |\n| --- | --- |\n| **Deploy** a template end to end | the matching golden path in the table above ([index](..\u002Frunpod\u002Fgolden-paths\u002FREADME.md)) — live-verified runs with real commands |\n| **Fix a pod that won't serve** (\"Running\" but URL dead, 404\u002F502) | the template's reference file, §Readiness — then [`runpod-usage\u002Freference\u002Fgotchas.md`](..\u002Frunpod-usage\u002Freference\u002Fgotchas.md) |\n| **Fix a ComfyUI workflow whose models won't download** (missing\u002Fbroken model metadata, imported workflow or PNG) | [the repair guide](reference\u002Fcomfyui-model-repair.md) — it drives the repair scripts in [`scripts\u002F`](scripts\u002F). The official ComfyUI templates ship ComfyUI-RunpodDirect, so its automatic-download path applies |\n| **Add models \u002F files** to a running template pod | the template's reference file (§What does not ship), or `runpod-companion-clis` for generic Hugging Face transfers |\n| **Customize beyond what the template ships** (pinned versions, extra nodes, lighter image) or **author a template project \u002F Hub listing** | [`runpod-build-template`](..\u002Frunpod-build-template\u002FSKILL.md) — author the project, using the official base when it fits |\n| **A serverless worker**, not a pod | not a pod template — Hub workers via `runpodctl` \u002F `runpod-mcp` |\n\nReference files here answer *what is in the image*; they never duplicate a walkthrough or\na repair procedure — they point at the owner.\n","# Official Runpod templates\n\nFor explicit source packaging or template optimization, use\n[runpod-build-template](..\u002Frunpod-build-template\u002FSKILL.md). For ordinary workload\ndeployment, **prefer an official template over building an image.** Runpod maintains prebuilt\nimages for common workloads; deploying one is a create + poll, with no SSH install\nstep. This skill is the reference for *what those images actually are*. It does not\nmanage infrastructure — deploy with **runpod-mcp** (if connected) or **runpodctl**.\n\n## Terms — \"template\" vs the Hub\n\nTwo different products share the word \"Hub\", and conflating them derails discovery:\n\n| Term | What it is | Runs as | Discover with |\n| --- | --- | --- | --- |\n| **Pod template** (this skill) | A saved pod config — image + ports + disk + env. The official ones appear on Console **Hub template pages** (`console.runpod.io\u002Fhub\u002Ftemplate\u002F\u003Cid>`) | a **pod** | `runpodctl template list --type official` \u002F `template search` · REST `GET \u002Fv2\u002Fcatalog\u002Ftemplates` |\n| **Hub repo \u002F listing** | A packaged **serverless worker** (e.g. `runpod-workers\u002Fworker-comfyui`) with a handler, deployed as an endpoint | **serverless** | `runpodctl hub list` \u002F `hub search` · MCP `list-hub-repos` \u002F `deploy-hub-repo` |\n\nSame word, disjoint catalogs: `hub search comfyui` returns only the serverless worker\nand none of the official ComfyUI **pod** templates, and `template search` returns no\nHub repos. In the REST v2 catalog, pod vs serverless templates are told apart by each\nentry's `serverless` flag.\n\n## What \"official\" means, and how to find them\n\nA template is Runpod-maintained when it reports `isRunpod: true`. Anything else in search\nresults is community-published: usable, but not covered by this skill and not\nversion-guaranteed.\n\n```bash\nrunpodctl template list --type official   # the whole official set (14 as of 2026-08-25)\nrunpodctl template search \u003Cname>          # by name; check isRunpod: true\nrunpodctl template get \u003Ctemplate-id>      # image, ports, portsConfig, disk + full readme\n```\n\n`template get` returns the template's **readme** — the description maintained alongside\nthe image, and the authoritative answer when it disagrees with this skill. Take image\ntags, ports, and env from these commands, not from these files: the templates ship on\ntheir own release train and move faster than this repo. The reference files record the\n**shape and the gotchas**, which is the expensive part to rediscover.\n\n⚠️ **`runpodctl hub ...` is not how you find pod templates** — see [Terms](#terms--template-vs-the-hub).\n\nTo hand a user a Console link, use `https:\u002F\u002Fconsole.runpod.io\u002Fhub\u002Ftemplate\u002F\u003Ctemplate-id>`.\n\n### REST v2 has no template search — only slices you filter yourself\n\nREST v2 has no query\u002Fsearch parameter for templates, so every \"search\" is a client-side\nfilter over a fetched slice:\n\n| Endpoint | Params | Returns |\n| --- | --- | --- |\n| `GET \u002Fv2\u002Fcatalog\u002Ftemplates` | `source=official\\|verified\\|community` (default `official`) | the public catalog slice |\n| `GET \u002Fv2\u002Ftemplates` | none | only templates **you own** |\n| `GET \u002Fv2\u002Ftemplates\u002F{id}` | — | one template, owned or catalog |\n\n**`official` (14) and `verified` (3) are fully enumerable; `community` is capped at 100\nwith pagination explicitly unsupported.** A community template past that cap never\nenters a slice the API can return, and `runpodctl template search` reads those same\nserver-side slices — so it has no view past the cap either. If a user names one you\ncannot find, ask them for the template id rather than concluding it does not exist.\n\n`isRunpod` is a GraphQL\u002Fv1 field with **no v2 equivalent** — in v2, \"official\" is the\n`source` slice you requested, not a flag on the record.\n\nCatalog entries carry **`allowedCudaVersions`**, which is the reliable way to pick between\nCUDA-line variants of the same template — pair it with `runpodctl pod create\n--min-cuda-version` instead of inferring from the GPU name.\n\n## The templates\n\n| Workload | Reference | Deploy walkthrough |\n| --- | --- | --- |\n| **ComfyUI** — image generation UI at a URL | [`reference\u002Fcomfyui.md`](reference\u002Fcomfyui.md) | [golden path 02, variant B](..\u002Frunpod\u002Fgolden-paths\u002F02-comfyui-pod\u002Fvariant-b-prebuilt.md) |\n| **PyTorch** — general GPU base \u002F dev box (2.1 → 2.9, incl. cluster + ROCm builds) | [`reference\u002Fpytorch.md`](reference\u002Fpytorch.md) | [golden path 06](..\u002Frunpod\u002Fgolden-paths\u002F06-dev-pod.md) |\n| **Ubuntu** — bare 20.04 \u002F 22.04 \u002F 24.04 (**CPU** category) | TODO | — |\n| **Network storage file browser** (GPU + CPU) | TODO | [golden path 07](..\u002Frunpod\u002Fgolden-paths\u002F07-network-volume-handoff.md) |\n\nAdd a template by adding one file here and one row above. Do not create a new skill\nper template — the task shape is identical and every registered skill costs context in\nevery session.\n\n## How to use a template reference\n\nEach file under `reference\u002F` answers the same questions in the same order, so an agent\ncan skim to the one it needs:\n\n1. **Identity** — template name, id, image, upstream source repo.\n2. **Variants** — CUDA\u002Farch\u002FGPU-generation splits and which to pick.\n3. **Ports and credentials** — what is exposed and any default login.\n4. **Autostart** — what is already running on boot, with the exact command.\n5. **Paths** — where the app, its config, and its data live (and what a network\n   volume mount changes).\n6. **Readiness** — how long first boot takes and the exact signal for \"actually\n   serving\". `Running` is never the signal.\n7. **What does not ship** — the gap between \"booted\" and \"usable\", and how to close\n   it programmatically rather than by clicking.\n8. **Sizing** — container disk and minimum VRAM.\n9. **Version pinning** — how to hold a known-good version.\n\nOne file is the exception: [`reference\u002Fcomfyui-model-repair.md`](reference\u002Fcomfyui-model-repair.md)\nis a **usage guide** — a ComfyUI workflow repair procedure that drives the scripts in\n[`scripts\u002F`](scripts\u002F) — not a 9-question template reference.\n\n## Routing onward — this skill is the hub, not the destination\n\nA user asking about a template rarely wants the reference file itself; they want a\ntemplate deployed, fixed, or replaced. Land here, identify which, and hand off:\n\n| The user wants to… | Send them to |\n| --- | --- |\n| **Deploy** a template end to end | the matching golden path in the table above ([index](..\u002Frunpod\u002Fgolden-paths\u002FREADME.md)) — live-verified runs with real commands |\n| **Fix a pod that won't serve** (\"Running\" but URL dead, 404\u002F502) | the template's reference file, §Readiness — then [`runpod-usage\u002Freference\u002Fgotchas.md`](..\u002Frunpod-usage\u002Freference\u002Fgotchas.md) |\n| **Fix a ComfyUI workflow whose models won't download** (missing\u002Fbroken model metadata, imported workflow or PNG) | [the repair guide](reference\u002Fcomfyui-model-repair.md) — it drives the repair scripts in [`scripts\u002F`](scripts\u002F). The official ComfyUI templates ship ComfyUI-RunpodDirect, so its automatic-download path applies |\n| **Add models \u002F files** to a running template pod | the template's reference file (§What does not ship), or `runpod-companion-clis` for generic Hugging Face transfers |\n| **Customize beyond what the template ships** (pinned versions, extra nodes, lighter image) or **author a template project \u002F Hub listing** | [`runpod-build-template`](..\u002Frunpod-build-template\u002FSKILL.md) — author the project, using the official base when it fits |\n| **A serverless worker**, not a pod | not a pod template — Hub workers via `runpodctl` \u002F `runpod-mcp` |\n\nReference files here answer *what is in the image*; they never duplicate a walkthrough or\na repair procedure — they point at the owner.\n",{"name":5,"license":15,"metadata":48,"description":7,"allowed-tools":54},{"author":9,"version":49,"concepts":50},"2.0.0",[32,51,52,53],"container-image","pod","exposed-port","Bash(python3 -B ${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Frunpod-templates\u002Fscripts\u002Fextract_png_workflow.py:*) Bash(python3 -B ${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Frunpod-templates\u002Fscripts\u002Finventory_workflow_models.py:*) Bash(python3 -B ${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Frunpod-templates\u002Fscripts\u002Fapply_model_metadata.py:*)","main","91b9f9671af0f15186420ec466fe6e80c1b13f25","plugins\u002Frunpod\u002Fskills\u002Frunpod-templates",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":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add runpod\u002Frunpod-plugins-official --skill runpod-templates",{"tool":70,"command":71},"bunx","bunx skills add runpod\u002Frunpod-plugins-official --skill runpod-templates",{"tool":73,"command":74},"pnpm","pnpm dlx skills add runpod\u002Frunpod-plugins-official --skill runpod-templates","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002FSKILL.md",true,[78,84,88,92,96,100,104,108,112,116,120,124,128,132,136,140,144,148,152,158,162,166,170,174],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"evals\u002Falways-output-workflow.eval.md","REFERENCE","参考文档",2568,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Fevals\u002Falways-output-workflow.eval.md",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"evals\u002Fambiguous-filename.eval.md",1515,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Fevals\u002Fambiguous-filename.eval.md",{"path":89,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":90,"sourceHtmlUrl":91},"evals\u002Fapi-inventory-only.eval.md",1238,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Fevals\u002Fapi-inventory-only.eval.md",{"path":93,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":94,"sourceHtmlUrl":95},"evals\u002Fgated-model.eval.md",1718,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Fevals\u002Fgated-model.eval.md",{"path":97,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":98,"sourceHtmlUrl":99},"evals\u002Fmixed-resolved-ambiguous-output.eval.md",1336,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Fevals\u002Fmixed-resolved-ambiguous-output.eval.md",{"path":101,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":102,"sourceHtmlUrl":103},"evals\u002Fnontechnical-handoff.eval.md",1436,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Fevals\u002Fnontechnical-handoff.eval.md",{"path":105,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":106,"sourceHtmlUrl":107},"evals\u002Fpng-output-extraction.eval.md",1889,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Fevals\u002Fpng-output-extraction.eval.md",{"path":109,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":110,"sourceHtmlUrl":111},"evals\u002Frepair-and-handoff.eval.md",3067,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Fevals\u002Frepair-and-handoff.eval.md",{"path":113,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":114,"sourceHtmlUrl":115},"evals\u002Frunpoddirect-required-handoff.eval.md",1627,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Fevals\u002Frunpoddirect-required-handoff.eval.md",{"path":117,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":118,"sourceHtmlUrl":119},"evals\u002Fsupport-intake.eval.md",1555,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Fevals\u002Fsupport-intake.eval.md",{"path":121,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":122,"sourceHtmlUrl":123},"evals\u002Ftemplate-recommendation.eval.md",1679,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Fevals\u002Ftemplate-recommendation.eval.md",{"path":125,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":126,"sourceHtmlUrl":127},"evals\u002Funsafe-download-url.eval.md",2154,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Fevals\u002Funsafe-download-url.eval.md",{"path":129,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":130,"sourceHtmlUrl":131},"reference\u002Fcomfyui-model-repair.md",6907,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Freference\u002Fcomfyui-model-repair.md",{"path":133,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":134,"sourceHtmlUrl":135},"reference\u002Fcomfyui-repair\u002Fmetadata.md",14534,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Freference\u002Fcomfyui-repair\u002Fmetadata.md",{"path":137,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":138,"sourceHtmlUrl":139},"reference\u002Fcomfyui-repair\u002Fresolution.md",7504,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Freference\u002Fcomfyui-repair\u002Fresolution.md",{"path":141,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":142,"sourceHtmlUrl":143},"reference\u002Fcomfyui-repair\u002Frunpoddirect.md",9640,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Freference\u002Fcomfyui-repair\u002Frunpoddirect.md",{"path":145,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":146,"sourceHtmlUrl":147},"reference\u002Fcomfyui.md",9266,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Freference\u002Fcomfyui.md",{"path":149,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":150,"sourceHtmlUrl":151},"reference\u002Fpytorch.md",5667,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Freference\u002Fpytorch.md",{"path":153,"resourceType":154,"resourceTypeDesc":155,"sizeBytes":156,"sourceHtmlUrl":157},"scripts\u002Fapply_model_metadata.py","SCRIPT","脚本",26132,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Fscripts\u002Fapply_model_metadata.py",{"path":159,"resourceType":154,"resourceTypeDesc":155,"sizeBytes":160,"sourceHtmlUrl":161},"scripts\u002Fextract_png_workflow.py",15255,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Fscripts\u002Fextract_png_workflow.py",{"path":163,"resourceType":154,"resourceTypeDesc":155,"sizeBytes":164,"sourceHtmlUrl":165},"scripts\u002Finventory_workflow_models.py",34300,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Fscripts\u002Finventory_workflow_models.py",{"path":167,"resourceType":154,"resourceTypeDesc":155,"sizeBytes":168,"sourceHtmlUrl":169},"tests\u002Ftest_extracted_helpers.py",35678,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Ftests\u002Ftest_extracted_helpers.py",{"path":171,"resourceType":154,"resourceTypeDesc":155,"sizeBytes":172,"sourceHtmlUrl":173},"tests\u002Ftest_model_metadata_scripts.py",56974,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Ftests\u002Ftest_model_metadata_scripts.py",{"path":175,"resourceType":154,"resourceTypeDesc":155,"sizeBytes":176,"sourceHtmlUrl":177},"tests\u002Ftest_png_workflow_extractor.py",16914,"https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-templates\u002Ftests\u002Ftest_png_workflow_extractor.py",[179,207,225,242,263,285],{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":191,"publishedAt":43},"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",[185,188],{"categoryNo":186,"categoryName":187,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":189,"categoryName":190,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[192,9,193,194,38,195,34,196,31,197,198,199,200,201,202,203,204,205,206,26],"runpod vllm","vLLM","volume","worker","log","request","release","network","verified","hugging face","openai","face","endpoint","availability","load-balancing",{"skillNo":208,"name":42,"nameZh":6,"description":209,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":210,"categories":211,"keywords":213,"publishedAt":43},"01M6CFW2PPRQZ006AVQXGMWPH1","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",[212],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[42,214,38,215,36,33,216,32,194,217,218,199,9,219,220,221,204,222,223,224],"doctor","ci","cli","CPU","terminal","ssh setup","Tools","macos","send","windows","when",{"skillNo":226,"name":9,"nameZh":6,"description":227,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":228,"categories":229,"keywords":231,"publishedAt":43},"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",[230],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[9,36,232,32,199,233,194,234,235,236,237,238,204,239,240,220,241,42,214,224],"migrate","start","end","companion","paths","flash","golden","journey","audit","path",{"skillNo":243,"name":244,"nameZh":6,"description":245,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":246,"categories":247,"keywords":249,"publishedAt":43},"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",[248],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[250,9,251,42,252,253,254,36,255,34,256,257,258,259,194,26,260,261,195,262],"runpod usage","usage","development","container","design","use","code","explain","architecture","disk","project","complete","vram",{"skillNo":264,"name":265,"nameZh":6,"description":266,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":267,"categories":268,"keywords":272,"publishedAt":43},"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",[269,270,271],{"categoryNo":186,"categoryName":187,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":189,"categoryName":190,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[273,9,274,275,276,277,278,279,194,280,281,38,282,195,36,283,284,35,34,224],"runpod serverless deploy","serverless deploy","deploy","serverless","back","Video","community","processing","scope","pick","loop","URL",{"skillNo":286,"name":287,"nameZh":6,"description":288,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":289,"categories":290,"keywords":292,"publishedAt":43},"01M6PP9PRZJJHNF10N95P2C10J","runpod-pod-doctor","Diagnose a Runpod Pod that is unreachable, GPU-blind or stuck, and perform a recovery action only when the user authorizes one. Use when an existing Pod misbehaves, through the Runpod MCP tools: its proxy URL answers 502, CUDA is not available inside the container, a restarted Pod has no GPU, the user wants a Pod's logs read, an account-wide check for stuck Pods, or the stop-versus-terminate decision for a Pod they already have. Read-only until the user asks for an action.","https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-pod-doctor\u002FSKILL.md",[291],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[293,9,214,294,194,295,296,36,297,284,259,298,196,31,299,300,220,301,205,224],"runpod pod doctor","pod doctor","decision","only","unreachable","logs","read","action","stop"]