[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DCERCAD18W418A53TDVBD8":3,"skill-same:01M6DCERCAD18W418A53TDVBD8":75},{"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":29,"publishedAt":50,"linkOnly":51,"markdownContent":52,"markdownBody":53,"frontMatter":54,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":14,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":60,"install":61,"resources":74},"01M6DCERCAD18W418A53TDVBD8","cloud-infra-toolchain",null,"Use when working with the user's cloud-infrastructure MCP stack fronted by the cloud-hub multiplexer - RunPod, Azure, Google Cloud, Kaggle, rclone, Modal, Lightning AI, and OVHcloud behind one lazy MCP slot. Covers which platform does what, adopt-vs-build-vs-vendor status, per-platform auth + the account-switch\u002Fcycle multi-account layer (incl. OVH region rotation ca\u002Feu\u002Fus), the workflows (train on Kaggle, rent a GPU on RunPod\u002FModal\u002FLightning\u002FOVH, deploy to Cloud Run\u002FAKS, move data with rclone), the rclone rcd daemon prereq, the Windows `cmd \u002Fc npx` note, GPU cost-awareness + read-before-destroy operating rules, and the per-backend tool inventory. Multi-accounting can breach a platform's ToS - flag it.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fplatform\u002Frouting\u002Ffixtures\u002Fhome\u002F.agents\u002Fskills\u002Fcloud-infra-toolchain\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49],"cloud infra toolchain","infra","cloud","aks","kaggle","adopt","cycle","runpod","read","stack","inventory","MCP","data","run","infrastructure","status","auth","workflows","google cloud","google","2026-11-10 10:12:30",false,"---\nname: cloud-infra-toolchain\ndescription: \"Use when working with the user's cloud-infrastructure MCP stack fronted by the cloud-hub multiplexer - RunPod, Azure, Google Cloud, Kaggle, rclone, Modal, Lightning AI, and OVHcloud behind one lazy MCP slot. Covers which platform does what, adopt-vs-build-vs-vendor status, per-platform auth + the account-switch\u002Fcycle multi-account layer (incl. OVH region rotation ca\u002Feu\u002Fus), the workflows (train on Kaggle, rent a GPU on RunPod\u002FModal\u002FLightning\u002FOVH, deploy to Cloud Run\u002FAKS, move data with rclone), the rclone rcd daemon prereq, the Windows `cmd \u002Fc npx` note, GPU cost-awareness + read-before-destroy operating rules, and the per-backend tool inventory. Multi-accounting can breach a platform's ToS - flag it.\"\n---\n\n# Cloud Infrastructure MCP Toolchain\n\n## Overview\n\nThe user's cloud-infra MCP servers are fronted by **`cloud-hub`** — one lazy,\nname-preserving multiplexer (`tools\u002Fmcp\u002Fcloud-hub\u002F`) that answers `tools\u002Flist`\nfrom committed caches **without spawning** and lazily spawns **only** the owning\nbackend on a `tools\u002Fcall`. Ten platforms, **324 backend tools + 54 account\ntools = 378**, behind a single MCP registration. Five servers are **adopted**\n(existing MCP packages), four are **built** thin FastMCP wrappers, and one\n(OVHcloud) is a **vendored** TS server built from source.\n\n| Platform | pkg \u002F runtime | Auth | Adopt\u002FBuild | Tools | Hard limits |\n|---|---|---|---|---:|---|\n| **RunPod** | `npx @runpod\u002Fmcp-server@latest` (Node) | `RUNPOD_API_KEY` | adopt | 50 | GPU billed per-second; pods\u002Fendpoints cost money while running |\n| **Azure** | `npx @azure\u002Fmcp@latest server start` (.NET) | `az login` | adopt | 14* | *hand-authored cache (the .NET server didn't enumerate under piped stdio); `--refresh azure` upgrades it |\n| **Google Cloud** | `npx @google-cloud\u002Fgcloud-mcp` (Node) | gcloud ADC + `GOOGLE_CLOUD_PROJECT` | adopt | 1 | single `run_gcloud_command` passthrough — full gcloud surface, full gcloud risk |\n| **Kaggle** | `uvx kaggle-mcp-server` (Python) | `KAGGLE_USERNAME`+`KAGGLE_KEY` \u002F `~\u002F.kaggle\u002Fkaggle.json` | adopt | 51 | free-tier GPU\u002FTPU quota (~30h\u002Fwk); kernels are public unless set private |\n| **rclone** | `npx rclone-mcp` over `rclone rcd` | RC daemon :5572 | adopt | 56 | **needs the rcd daemon** (auto-started); `sync`\u002F`move`\u002F`delete` are destructive |\n\n### Multi-account + cycling (cswap-style)\n### Auth-setup runbook\n### Workflows\n### Train on Kaggle (free GPU\u002FTPU)\n### Rent a GPU (options — pick by workload)\n### Deploy an app\n### Move data (rclone)\n### rclone `rcd` daemon prereq\n### Windows launch note\n### Operating rules\n### Per-backend tool inventory\n### Databricks as a Codex agent host (not just Spark)\n","# Cloud Infrastructure MCP Toolchain\n\n## Overview\n\nThe user's cloud-infra MCP servers are fronted by **`cloud-hub`** — one lazy,\nname-preserving multiplexer (`tools\u002Fmcp\u002Fcloud-hub\u002F`) that answers `tools\u002Flist`\nfrom committed caches **without spawning** and lazily spawns **only** the owning\nbackend on a `tools\u002Fcall`. Ten platforms, **324 backend tools + 54 account\ntools = 378**, behind a single MCP registration. Five servers are **adopted**\n(existing MCP packages), four are **built** thin FastMCP wrappers, and one\n(OVHcloud) is a **vendored** TS server built from source.\n\n| Platform | pkg \u002F runtime | Auth | Adopt\u002FBuild | Tools | Hard limits |\n|---|---|---|---|---:|---|\n| **RunPod** | `npx @runpod\u002Fmcp-server@latest` (Node) | `RUNPOD_API_KEY` | adopt | 50 | GPU billed per-second; pods\u002Fendpoints cost money while running |\n| **Azure** | `npx @azure\u002Fmcp@latest server start` (.NET) | `az login` | adopt | 14* | *hand-authored cache (the .NET server didn't enumerate under piped stdio); `--refresh azure` upgrades it |\n| **Google Cloud** | `npx @google-cloud\u002Fgcloud-mcp` (Node) | gcloud ADC + `GOOGLE_CLOUD_PROJECT` | adopt | 1 | single `run_gcloud_command` passthrough — full gcloud surface, full gcloud risk |\n| **Kaggle** | `uvx kaggle-mcp-server` (Python) | `KAGGLE_USERNAME`+`KAGGLE_KEY` \u002F `~\u002F.kaggle\u002Fkaggle.json` | adopt | 51 | free-tier GPU\u002FTPU quota (~30h\u002Fwk); kernels are public unless set private |\n| **rclone** | `npx rclone-mcp` over `rclone rcd` | RC daemon :5572 | adopt | 56 | **needs the rcd daemon** (auto-started); `sync`\u002F`move`\u002F`delete` are destructive |\n\n### Multi-account + cycling (cswap-style)\n### Auth-setup runbook\n### Workflows\n### Train on Kaggle (free GPU\u002FTPU)\n### Rent a GPU (options — pick by workload)\n### Deploy an app\n### Move data (rclone)\n### rclone `rcd` daemon prereq\n### Windows launch note\n### Operating rules\n### Per-backend tool inventory\n### Databricks as a Codex agent host (not just Spark)\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","platform\u002Frouting\u002Ffixtures\u002Fhome\u002F.agents\u002Fskills\u002Fcloud-infra-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill cloud-infra-toolchain",{"tool":67,"command":68},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill cloud-infra-toolchain",{"tool":70,"command":71},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill cloud-infra-toolchain","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fplatform\u002Frouting\u002Ffixtures\u002Fhome\u002F.agents\u002Fskills\u002Fcloud-infra-toolchain\u002FSKILL.md",true,[],[76,98,123,150,163,179],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":50},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[83,84,85,86,87,88,89,90,91,92,93,94,95,96,97],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","use","context","repo","injection","execution","file",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":105,"publishedAt":50},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[104],{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},[106,107,108,109,110,111,112,39,113,114,115,116,117,118,92,119,120,121,122,41],"openmm md","how","decision","pick","linux","analyze","tool","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":135,"publishedAt":50},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[129,132],{"categoryNo":130,"categoryName":131,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":133,"categoryName":134,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[136,137,138,139,140,141,142,143,144,145,107,146,147,148,149],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":151,"name":45,"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":155,"publishedAt":50},"01M6DF73AQVCBZKEN0YXEX9FXP","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[45,156,157,158,159,160,161,162],"setup","report","project","installation","project setup","issues","state",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":170,"publishedAt":50},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[169],{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},[165,171,88,172,173,174,92,175,176,177,178],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":180,"name":156,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":184,"publishedAt":50},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[156,158,121,185,160,186],"files","interactive"]