[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PP8AXSVKY35S3MVJQR4TW9":3,"skill-same:01M6PP8AXSVKY35S3MVJQR4TW9":81},{"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":58,"commitSha":59,"skillDirectory":60,"forksCount":61,"repositoryHtmlUrl":62,"repositoryHomepageUrl":63,"ownerHtmlUrl":64,"ownerBlogUrl":65,"ownerDescription":6,"updatedAt":66,"install":67,"resources":80},"01M6PP8AXSVKY35S3MVJQR4TW9","runpod-cost-audit",null,"Read-only Runpod spend audit: find idle spend, explain serverless billing when nothing seems to run, break spend down by resource type and by resource, and give a whole-account snapshot. Every figure comes from the MCP billing and list reads; it recommends actions and never stops or changes anything. Use when the user asks about their bill, what is costing money, what is running on the account, or tells you to stop or delete idle resources it did not name by id: the audit with ids and the user's own next steps is the answer. A resource the user names by id goes to runpod-pod-doctor or runpod-endpoint-ops, and the change is made.","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-cost-audit\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],"audit","cost audit","cost","runpod cost audit","when","next","delete","change","you","autoscaling","MCP","only","next steps","actions","ids","never","resources","volume","billing","2026-11-10 10:12:30",false,"---\nname: runpod-cost-audit\ndescription: 'Read-only Runpod spend audit: find idle spend, explain serverless billing when nothing seems\n  to run, break spend down by resource type and by resource, and give a whole-account snapshot. Every\n  figure comes from the MCP billing and list reads; it recommends actions and never stops or changes anything.\n  Use when the user asks about their bill, what is costing money, what is running on the account, or tells\n  you to stop or delete idle resources it did not name by id: the audit with ids and the user''s own next\n  steps is the answer. A resource the user names by id goes to runpod-pod-doctor or runpod-endpoint-ops, and the change\n  is made.'\nmetadata:\n  author: runpod\n  version: \"2.1.0\" # x-release-please-version\n  concepts: [billing-record, pod-billing, serverless-billing, network-volume-billing, public-endpoint, credit-balance, endpoint-autoscaling]\nlicense: Apache-2.0\n---\n\n# Cost audit\n\nYou answer where the money goes on a Runpod account and how to stop a leak. This skill is strictly read-only: it discovers, scores, and explains spend, then leaves the decision to the user. It **never** stops, deletes, or reconfigures a resource on its own. Any apply is handed off (a Pod stop to `runpod-pod-doctor`, dropping serverless min-workers to 0 to `runpod-endpoint-ops`), and only after the user explicitly approves it.\n\nEvery figure comes from a read: hourly rates from the resource list, spend-to-date from the billing reads. Never invent or estimate a number you did not read; a monthly projection is allowed only as `read_hourly × hours`, with the hourly quoted.\n\nThe raw billing and list reads are `runpod-mcp` tool calls; this skill is the *audit journey* on top of them: the idle-scoring, the idle-worker-vs-idle-pod disambiguation, and the per-resource attribution the plain reads don't do.\n\n## Tool binding\n\nAll are reads. If a tool named here is missing from the session's tool list, say so and use the nearest read instead of inventing a result.\n\n| Capability | Tool |\n|---|---|\n| List Pods (with cost) | `list-pods` |\n| Inspect one Pod | `get-pod` |\n| List \u002F inspect endpoints, for min\u002Fmax workers config | `list-endpoints`, `get-endpoint` |\n| Endpoint worker config \u002F counts | `list-endpoint-workers`, `endpoint-health` |\n| List network volumes | `list-network-volumes` |\n| Aggregate billing (per type, one call) | `list-billing` |\n| Per-resource billing | `list-pod-billing`, `list-serverless-billing` (serverless endpoints), `list-endpoint-billing` (Public Endpoints), `list-network-volume-billing`, `list-cluster-billing` |\n\n## The four journeys\n\nRead first, always. Match the prompt to one journey; do not run all four unasked.\n\n- **Whole-account view.** List Pods, endpoints, network volumes, and pull aggregate billing for the recent window. Report the count and running-state of each category, the current burn, and the spend-to-date from the billing read. Report an empty category as empty (\"no network volumes\") rather than padding the picture.\n- **Idle Pods.** List Pods. On the pod record `status` is the state field and `cost` is the pod's hourly rate in USD (those exact names, from the read). For each `status=RUNNING` pod, quote `cost` and project `cost × 730` as \"$\u002Fmo at this rate\"; sort by projected cost, present one table (name, GPU, $\u002Fhr, up-for, $\u002Fmo), and name the costliest. When every pod is stopped\u002FEXITED, don't stop at \"nothing is running\". State that no GPU is burning AND that stopped pods still bill their volume disk until terminated, then still give the per-pod table. A stopped pod's `cost` reads 0, so the rate it would resume at comes from the GPU catalog price for its type, labelled as such. If `cost` is missing on a row, render `?` and exclude it from any total; do not fabricate it. Recommend stopping (or terminating the long-dead) ones; do not mutate anything.\n- **Serverless idle-worker spend.** A serverless endpoint with **min workers ≥ 1** keeps an always-on worker that bills even at zero traffic. That is serverless idle-worker spend, and it is *not* the same as an idle Pod. Inspect the endpoint's worker config to confirm min-workers ≥ 1, quote the serverless billing read for that endpoint, and explain the mechanism. The fix is min-workers 0 (cold-start trade-off): recommend it and hand the apply to `runpod-endpoint-ops`; do not change it here. **If no endpoint has min-workers ≥ 1**, the charge is worker run time on scale-to-zero endpoints. A worker bills from the moment it starts running until it fully stops, rounded up to the second (model loading, the job itself, and the idle timeout after the last request), whether the job completed, failed, or the worker crash-looped without finishing anything. Attribute it from the per-endpoint serverless billing rows plus the worker\u002Fjob states, and name the responsible endpoint. Say explicitly that this is worker run time on a live scale-to-zero endpoint (start-up, execution and idle timeout), not an always-on worker and not a phantom charge.\n- **Where the spend went.** Get the per-TYPE totals from the aggregate `list-billing` read first; it answers the breakdown directly. Drill into a type only as needed, and **always size-safely**: on the serverless read pass `lastN: 1` (or a `bucketSize` covering the whole window) so each endpoint yields ONE record. The default per-endpoint-per-bucket dump on a many-endpoint account overflows the tool-result limit, and an oversized result comes back truncated, which dead-ends the audit. Attribute spend to each named resource, sort descending, and name the single costliest. Present figures as coming from the billing read. If a category returned nothing, list it as $0 \u002F empty rather than dropping it silently. **When every category returns zero** (no spend anywhere), say so. Give the per-type table with $0 for each and a $0 total, and cross-check it against the live lists (`list-pods` \u002F `list-endpoints` \u002F `list-network-volumes` all empty confirms it). State directly that there is no costliest type because nothing has billed and nothing is currently costing money. The reads are authoritative for the window used; re-pull only when the user names a different period.\n- **Commit the attribution (all spend questions).** When the billing reads show real spend, name its source from the data you have, even when the responsible resource has since been deleted (\"$X from serverless jobs on endpoints that no longer exist, run at \u003Ctimes from the billing rows>\"). That attribution IS the answer: deliver it as the verdict, then at most one sentence of follow-up the user could choose. Lead with the attribution the reads support instead of deflecting the question back at the user. Never reach for tools you were not given (no shell, no web): every figure you need is in the billing reads and lists you already have, so analyze them directly in your reply. The per-endpoint serverless drill-down is `list-serverless-billing`; `list-endpoint-billing` is Public Endpoint spend (the pay-per-use model APIs), a different product. Deliver the verdict first: state the finding, then at most one recommended next step or follow-up question.\n\n## Hard rules\n\n- Read-only. This skill never calls a mutating tool: no stop, no delete, no update.\n- For resources the user did not name: that holds however urgently the change is ordered: an instruction changes the urgency, not the authority. The audit plus the exact ids and actions for the USER to run IS the complete answer to that order. Deliver it as such, not as a permission question, and never attempt the mutation to \"try anyway\".\n- Work with the tools you were granted. In an MCP-only session never reach for a shell, a script, a web-fetch tool, or anything else you do not have: a tool you do not have cannot be called, and the audit ends with nothing delivered. Every figure this skill needs is in the MCP billing and list reads.\n- When a read's result comes back truncated, the recovery is a NARROWER RE-READ (smaller page, one endpoint at a time, `lastN: 1`, a tighter bucket). Do not try to recover the dropped output, parse it with an external script, or ask for extra tool access.\n- Any recommended apply is a handoff to `runpod-pod-doctor` (stop) or `runpod-endpoint-ops` (min-workers-0), and only after the user says yes. Name the handoff; do not perform it.\n- Every dollar figure traces to a tool read. Quote the hourly \u002F billing source. A projection is `read_hourly × hours`, never a bare invented number.\n- Report empty categories as empty. Absence is a finding, not a gap to fill.\n- Never flag a Pod that has been up under an hour as idle; it is too fresh to call.\n- Distinguish Pod idle spend from serverless idle-worker spend explicitly whenever both could be in play.\n\n## Error handling\n\n- A `401` on any list means the API key is invalid. Say so and stop; there is nothing to audit without it.\n- A `429` mid-audit: report the partial picture and note it is incomplete; do not retry in a tight loop.\n- A missing `cost` on a pod row, or an empty billing bucket, is data, not an error. Render `?` \u002F $0 and keep going.\n\n## Report template — cost summary\n\nEvery cost answer ships as: per-type table (Pods \u002F Serverless \u002F Public\nEndpoints \u002F Network volumes \u002F Clusters \u002F storage, with every type present even at $0.00) with figures only from\nbilling reads made this turn · a total line · the named costliest item (or the\nexplicit statement that nothing billed) · the one-sentence verdict answering\nthe user's question. Attribution follows the commit rule above.\n\nFigure format:\n- Figures are exact dollar amounts from the billing and list reads.\n- Table rows sum to the stated total.\n\n## Contract\n\nThe cross-journey answer contract (definite facts from reads, commit-don't-hedge, mutations bind to this conversation's creations, a standalone final message, honest failure, granted tools only) is defined in the `runpod-mcp` skill and applies to every reply from this journey. If the `runpod-mcp` skill has not been loaded in this conversation, load it now, before the next tool call: its rules on which resources you may change, when a request is the go, and when to stop for the user are not repeated here.\n","# Cost audit\n\nYou answer where the money goes on a Runpod account and how to stop a leak. This skill is strictly read-only: it discovers, scores, and explains spend, then leaves the decision to the user. It **never** stops, deletes, or reconfigures a resource on its own. Any apply is handed off (a Pod stop to `runpod-pod-doctor`, dropping serverless min-workers to 0 to `runpod-endpoint-ops`), and only after the user explicitly approves it.\n\nEvery figure comes from a read: hourly rates from the resource list, spend-to-date from the billing reads. Never invent or estimate a number you did not read; a monthly projection is allowed only as `read_hourly × hours`, with the hourly quoted.\n\nThe raw billing and list reads are `runpod-mcp` tool calls; this skill is the *audit journey* on top of them: the idle-scoring, the idle-worker-vs-idle-pod disambiguation, and the per-resource attribution the plain reads don't do.\n\n## Tool binding\n\nAll are reads. If a tool named here is missing from the session's tool list, say so and use the nearest read instead of inventing a result.\n\n| Capability | Tool |\n|---|---|\n| List Pods (with cost) | `list-pods` |\n| Inspect one Pod | `get-pod` |\n| List \u002F inspect endpoints, for min\u002Fmax workers config | `list-endpoints`, `get-endpoint` |\n| Endpoint worker config \u002F counts | `list-endpoint-workers`, `endpoint-health` |\n| List network volumes | `list-network-volumes` |\n| Aggregate billing (per type, one call) | `list-billing` |\n| Per-resource billing | `list-pod-billing`, `list-serverless-billing` (serverless endpoints), `list-endpoint-billing` (Public Endpoints), `list-network-volume-billing`, `list-cluster-billing` |\n\n## The four journeys\n\nRead first, always. Match the prompt to one journey; do not run all four unasked.\n\n- **Whole-account view.** List Pods, endpoints, network volumes, and pull aggregate billing for the recent window. Report the count and running-state of each category, the current burn, and the spend-to-date from the billing read. Report an empty category as empty (\"no network volumes\") rather than padding the picture.\n- **Idle Pods.** List Pods. On the pod record `status` is the state field and `cost` is the pod's hourly rate in USD (those exact names, from the read). For each `status=RUNNING` pod, quote `cost` and project `cost × 730` as \"$\u002Fmo at this rate\"; sort by projected cost, present one table (name, GPU, $\u002Fhr, up-for, $\u002Fmo), and name the costliest. When every pod is stopped\u002FEXITED, don't stop at \"nothing is running\". State that no GPU is burning AND that stopped pods still bill their volume disk until terminated, then still give the per-pod table. A stopped pod's `cost` reads 0, so the rate it would resume at comes from the GPU catalog price for its type, labelled as such. If `cost` is missing on a row, render `?` and exclude it from any total; do not fabricate it. Recommend stopping (or terminating the long-dead) ones; do not mutate anything.\n- **Serverless idle-worker spend.** A serverless endpoint with **min workers ≥ 1** keeps an always-on worker that bills even at zero traffic. That is serverless idle-worker spend, and it is *not* the same as an idle Pod. Inspect the endpoint's worker config to confirm min-workers ≥ 1, quote the serverless billing read for that endpoint, and explain the mechanism. The fix is min-workers 0 (cold-start trade-off): recommend it and hand the apply to `runpod-endpoint-ops`; do not change it here. **If no endpoint has min-workers ≥ 1**, the charge is worker run time on scale-to-zero endpoints. A worker bills from the moment it starts running until it fully stops, rounded up to the second (model loading, the job itself, and the idle timeout after the last request), whether the job completed, failed, or the worker crash-looped without finishing anything. Attribute it from the per-endpoint serverless billing rows plus the worker\u002Fjob states, and name the responsible endpoint. Say explicitly that this is worker run time on a live scale-to-zero endpoint (start-up, execution and idle timeout), not an always-on worker and not a phantom charge.\n- **Where the spend went.** Get the per-TYPE totals from the aggregate `list-billing` read first; it answers the breakdown directly. Drill into a type only as needed, and **always size-safely**: on the serverless read pass `lastN: 1` (or a `bucketSize` covering the whole window) so each endpoint yields ONE record. The default per-endpoint-per-bucket dump on a many-endpoint account overflows the tool-result limit, and an oversized result comes back truncated, which dead-ends the audit. Attribute spend to each named resource, sort descending, and name the single costliest. Present figures as coming from the billing read. If a category returned nothing, list it as $0 \u002F empty rather than dropping it silently. **When every category returns zero** (no spend anywhere), say so. Give the per-type table with $0 for each and a $0 total, and cross-check it against the live lists (`list-pods` \u002F `list-endpoints` \u002F `list-network-volumes` all empty confirms it). State directly that there is no costliest type because nothing has billed and nothing is currently costing money. The reads are authoritative for the window used; re-pull only when the user names a different period.\n- **Commit the attribution (all spend questions).** When the billing reads show real spend, name its source from the data you have, even when the responsible resource has since been deleted (\"$X from serverless jobs on endpoints that no longer exist, run at \u003Ctimes from the billing rows>\"). That attribution IS the answer: deliver it as the verdict, then at most one sentence of follow-up the user could choose. Lead with the attribution the reads support instead of deflecting the question back at the user. Never reach for tools you were not given (no shell, no web): every figure you need is in the billing reads and lists you already have, so analyze them directly in your reply. The per-endpoint serverless drill-down is `list-serverless-billing`; `list-endpoint-billing` is Public Endpoint spend (the pay-per-use model APIs), a different product. Deliver the verdict first: state the finding, then at most one recommended next step or follow-up question.\n\n## Hard rules\n\n- Read-only. This skill never calls a mutating tool: no stop, no delete, no update.\n- For resources the user did not name: that holds however urgently the change is ordered: an instruction changes the urgency, not the authority. The audit plus the exact ids and actions for the USER to run IS the complete answer to that order. Deliver it as such, not as a permission question, and never attempt the mutation to \"try anyway\".\n- Work with the tools you were granted. In an MCP-only session never reach for a shell, a script, a web-fetch tool, or anything else you do not have: a tool you do not have cannot be called, and the audit ends with nothing delivered. Every figure this skill needs is in the MCP billing and list reads.\n- When a read's result comes back truncated, the recovery is a NARROWER RE-READ (smaller page, one endpoint at a time, `lastN: 1`, a tighter bucket). Do not try to recover the dropped output, parse it with an external script, or ask for extra tool access.\n- Any recommended apply is a handoff to `runpod-pod-doctor` (stop) or `runpod-endpoint-ops` (min-workers-0), and only after the user says yes. Name the handoff; do not perform it.\n- Every dollar figure traces to a tool read. Quote the hourly \u002F billing source. A projection is `read_hourly × hours`, never a bare invented number.\n- Report empty categories as empty. Absence is a finding, not a gap to fill.\n- Never flag a Pod that has been up under an hour as idle; it is too fresh to call.\n- Distinguish Pod idle spend from serverless idle-worker spend explicitly whenever both could be in play.\n\n## Error handling\n\n- A `401` on any list means the API key is invalid. Say so and stop; there is nothing to audit without it.\n- A `429` mid-audit: report the partial picture and note it is incomplete; do not retry in a tight loop.\n- A missing `cost` on a pod row, or an empty billing bucket, is data, not an error. Render `?` \u002F $0 and keep going.\n\n## Report template — cost summary\n\nEvery cost answer ships as: per-type table (Pods \u002F Serverless \u002F Public\nEndpoints \u002F Network volumes \u002F Clusters \u002F storage, with every type present even at $0.00) with figures only from\nbilling reads made this turn · a total line · the named costliest item (or the\nexplicit statement that nothing billed) · the one-sentence verdict answering\nthe user's question. Attribution follows the commit rule above.\n\nFigure format:\n- Figures are exact dollar amounts from the billing and list reads.\n- Table rows sum to the stated total.\n\n## Contract\n\nThe cross-journey answer contract (definite facts from reads, commit-don't-hedge, mutations bind to this conversation's creations, a standalone final message, honest failure, granted tools only) is defined in the `runpod-mcp` skill and applies to every reply from this journey. If the `runpod-mcp` skill has not been loaded in this conversation, load it now, before the next tool call: its rules on which resources you may change, when a request is the go, and when to stop for the user are not repeated here.\n",{"name":5,"license":15,"metadata":48,"description":7},{"author":9,"version":49,"concepts":50},"2.1.0",[51,52,53,54,55,56,57],"billing-record","pod-billing","serverless-billing","network-volume-billing","public-endpoint","credit-balance","endpoint-autoscaling","main","78415a3cd1084678bba59a6e3b045f56f2e114c0","plugins\u002Frunpod\u002Fskills\u002Frunpod-cost-audit",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":68,"prompt":78,"zipAvailable":79},[69,72,75],{"tool":70,"command":71},"npx","npx skills add runpod\u002Frunpod-plugins-official --skill runpod-cost-audit",{"tool":73,"command":74},"bunx","bunx skills add runpod\u002Frunpod-plugins-official --skill runpod-cost-audit",{"tool":76,"command":77},"pnpm","pnpm dlx skills add runpod\u002Frunpod-plugins-official --skill runpod-cost-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frunpod\u002Frunpod-plugins-official\u002Fblob\u002Fmain\u002Fplugins\u002Frunpod\u002Fskills\u002Frunpod-cost-audit\u002FSKILL.md",true,[],[82,113,133,149,170,189],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":94,"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",[88,91],{"categoryNo":89,"categoryName":90,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":92,"categoryName":93,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[95,9,96,41,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112],"runpod vllm","vLLM","model","worker","image","log","port","request","release","network","verified","hugging face","openai","face","endpoint","availability","load-balancing","for",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":120,"publishedAt":43},"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",[119],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[115,121,97,122,34,123,124,125,41,126,127,104,9,128,129,130,109,131,132,28],"doctor","ci","Bash","cli","template","CPU","terminal","ssh setup","Tools","macos","send","windows",{"skillNo":134,"name":9,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":139,"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",[138],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[9,34,140,125,104,141,41,142,143,144,145,146,109,147,24,129,148,115,121,28],"migrate","start","end","companion","paths","flash","golden","journey","path",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":156,"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",[155],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[157,9,158,115,159,160,161,34,162,99,163,164,165,166,41,112,167,168,98,169],"runpod usage","usage","development","container","design","use","code","explain","architecture","disk","project","complete","vram",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":177,"publishedAt":43},"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",[176],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[178,179,9,115,180,181,182,97,183,34,184,99,123,125,101,185,186,187,188,112],"runpod templates","templates","projects","python3","official","inventory","workflow","scripts","troubleshoot","png","repair",{"skillNo":190,"name":191,"nameZh":6,"description":192,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":193,"categories":194,"keywords":198,"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",[195,196,197],{"categoryNo":89,"categoryName":90,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":92,"categoryName":93,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[199,9,200,201,202,203,204,205,41,206,207,97,208,98,34,209,210,184,99,28],"runpod serverless deploy","serverless deploy","deploy","serverless","back","Video","community","processing","scope","pick","loop","URL"]