[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71B3TZ92V3CAFPYV2HP97P5":3,"skill-same:01M71B3TZ92V3CAFPYV2HP97P5":72},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":43,"install":44,"resources":57},"01M71B3TZ92V3CAFPYV2HP97P5","scvi-model-inputs",null,"Register appropriate input data for scVI or SysVI and run a configurable model fit without treating every scvi-tools model as count-based.","strmt7\u002Fai_skills_collection_benchmarked","strmt7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F28989754?v=4","01M71929P914SWKQ7QJV24NBBY","Stratos","01M71929Q9VGKQ7PWYR95VSQQQ",1,"MIT","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Frepaired\u002Fskills\u002Fby-category\u002Fscience-research-data-analysis\u002Flatest-release-community\u002Fscvi-model-inputs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Frepaired\u002Fskills\u002Fby-category\u002Fscience-research-data-analysis\u002Flatest-release-community\u002Fscvi-model-inputs\u002FSKILL.md",[],[20,21,22,23,24,25,26,27,28,29,30,31],"model","scvi","scvi model inputs","run","data","Tools","as","input","fit","register","for","count","2026-11-10 10:12:30",false,"---\nname: scvi-model-inputs\ndescription: Register appropriate input data for scVI or SysVI and run a configurable model fit without treating every scvi-tools model as count-based.\nlicense: MIT\n---\n\n# scvi-tools model inputs\n\nFor every task, apply Caveman. Before broad repository navigation, use\nCocoIndex Code; for web-page research, use Crawl4AI. Read and follow the\nrepository-root `docs\u002Fagent-tools.md` and its linked skills, and retain the\nrequired execution evidence.\n\nThe pinned skill says that all scvi-tools models require raw counts. Input\nrequirements are model-specific: SCVI uses count data, while SysVI is designed\nfor approximately normal data. Confirm the model's current documentation and\nthe data's provenance before registration. This focused overlay does not\nreview the other models or validate biological conclusions.\n\n## SCVI: registered counts\n\nChoose a count layer that contains the intended measured counts and, if needed,\na technical `batch_key` that exists in `adata.obs`. `None` uses no batch key.\nDo not automatically register donor, condition or other biological variables as\nnuisance covariates. Complete filtering and feature selection before setup.\nSupply a chosen integer `seed`, latent dimension `n_latent` and dictionary of\n`training_options` appropriate to the data and available hardware:\n\n```python\nimport scvi\n\nif \"counts\" not in adata.layers:\n    raise ValueError(\"Provide the intended count layer before SCVI setup\")\nscvi.settings.seed = seed\nscvi.model.SCVI.setup_anndata(adata, layer=\"counts\", batch_key=batch_key)\nmodel = scvi.model.SCVI(adata, n_latent=n_latent)\nmodel.train(**training_options)\nlatent = model.get_latent_representation()\n```\n\nCount-like values alone do not establish provenance. Setup registers the given\nfields; it does not create a missing count layer or normalize data. If the\ntraining object or its feature ordering changes, use the model's documented\nregistration and query-mapping procedures instead of assuming the old registry\nis still valid.\n\n## SysVI: approximately normal input\n\nSysVI's intended input is approximately normally distributed; its documentation\nuses normalized, `log1p`-transformed RNA data as an example. Prepare the data\nappropriate to the experiment, preserve its provenance, and select an existing\ntechnical `batch_key`. The caller supplies `seed`, `n_latent`, `prior` and\n`training_options`:\n\n```python\nimport scvi\n\nscvi.settings.seed = seed\nscvi.external.SysVI.setup_anndata(adata, batch_key=batch_key)\nmodel = scvi.external.SysVI(adata, n_latent=n_latent, prior=prior)\nmodel.train(**training_options)\nlatent = model.get_latent_representation()\n```\n\nThe examples are API starting points, not prescribed hyperparameters. Check\ntraining and validation behavior, sensitivity to seeds and model choices, and\nretention of relevant biology. A short synthetic fit does not establish model\nconvergence or biological validity. Normalized expression can be dense and\nlarge; request only what the task needs.\n\nSee the [SCVI API](https:\u002F\u002Fdocs.scvi-tools.org\u002Fen\u002Fstable\u002Fapi\u002Freference\u002Fscvi.model.SCVI.html),\n[SysVI model guide](https:\u002F\u002Fdocs.scvi-tools.org\u002Fen\u002Fstable\u002Fuser_guide\u002Fmodels\u002Fsysvi.html)\nand [scvi-tools overview](https:\u002F\u002Fdocs.scvi-tools.org\u002Fen\u002Flatest\u002Ftutorials\u002Fnotebooks\u002Fquick_start\u002Fapi_overview.html).\nThe preserved source entrypoint is in `provenance\u002F`; the control is not an agent\nbenchmark.\n","# scvi-tools model inputs\n\nFor every task, apply Caveman. Before broad repository navigation, use\nCocoIndex Code; for web-page research, use Crawl4AI. Read and follow the\nrepository-root `docs\u002Fagent-tools.md` and its linked skills, and retain the\nrequired execution evidence.\n\nThe pinned skill says that all scvi-tools models require raw counts. Input\nrequirements are model-specific: SCVI uses count data, while SysVI is designed\nfor approximately normal data. Confirm the model's current documentation and\nthe data's provenance before registration. This focused overlay does not\nreview the other models or validate biological conclusions.\n\n## SCVI: registered counts\n\nChoose a count layer that contains the intended measured counts and, if needed,\na technical `batch_key` that exists in `adata.obs`. `None` uses no batch key.\nDo not automatically register donor, condition or other biological variables as\nnuisance covariates. Complete filtering and feature selection before setup.\nSupply a chosen integer `seed`, latent dimension `n_latent` and dictionary of\n`training_options` appropriate to the data and available hardware:\n\n```python\nimport scvi\n\nif \"counts\" not in adata.layers:\n    raise ValueError(\"Provide the intended count layer before SCVI setup\")\nscvi.settings.seed = seed\nscvi.model.SCVI.setup_anndata(adata, layer=\"counts\", batch_key=batch_key)\nmodel = scvi.model.SCVI(adata, n_latent=n_latent)\nmodel.train(**training_options)\nlatent = model.get_latent_representation()\n```\n\nCount-like values alone do not establish provenance. Setup registers the given\nfields; it does not create a missing count layer or normalize data. If the\ntraining object or its feature ordering changes, use the model's documented\nregistration and query-mapping procedures instead of assuming the old registry\nis still valid.\n\n## SysVI: approximately normal input\n\nSysVI's intended input is approximately normally distributed; its documentation\nuses normalized, `log1p`-transformed RNA data as an example. Prepare the data\nappropriate to the experiment, preserve its provenance, and select an existing\ntechnical `batch_key`. The caller supplies `seed`, `n_latent`, `prior` and\n`training_options`:\n\n```python\nimport scvi\n\nscvi.settings.seed = seed\nscvi.external.SysVI.setup_anndata(adata, batch_key=batch_key)\nmodel = scvi.external.SysVI(adata, n_latent=n_latent, prior=prior)\nmodel.train(**training_options)\nlatent = model.get_latent_representation()\n```\n\nThe examples are API starting points, not prescribed hyperparameters. Check\ntraining and validation behavior, sensitivity to seeds and model choices, and\nretention of relevant biology. A short synthetic fit does not establish model\nconvergence or biological validity. Normalized expression can be dense and\nlarge; request only what the task needs.\n\nSee the [SCVI API](https:\u002F\u002Fdocs.scvi-tools.org\u002Fen\u002Fstable\u002Fapi\u002Freference\u002Fscvi.model.SCVI.html),\n[SysVI model guide](https:\u002F\u002Fdocs.scvi-tools.org\u002Fen\u002Fstable\u002Fuser_guide\u002Fmodels\u002Fsysvi.html)\nand [scvi-tools overview](https:\u002F\u002Fdocs.scvi-tools.org\u002Fen\u002Flatest\u002Ftutorials\u002Fnotebooks\u002Fquick_start\u002Fapi_overview.html).\nThe preserved source entrypoint is in `provenance\u002F`; the control is not an agent\nbenchmark.\n",{"name":5,"license":15,"description":7},"main","5c95bcac4646c5aed06bd9aed5235cfc7985aafc","included\u002Frepaired\u002Fskills\u002Fby-category\u002Fscience-research-data-analysis\u002Flatest-release-community\u002Fscvi-model-inputs",0,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked","https:\u002F\u002Fgithub.com\u002Fstrmt7","2026-11-11 04:18:12",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add strmt7\u002Fai_skills_collection_benchmarked --skill scvi-model-inputs",{"tool":50,"command":51},"bunx","bunx skills add strmt7\u002Fai_skills_collection_benchmarked --skill scvi-model-inputs",{"tool":53,"command":54},"pnpm","pnpm dlx skills add strmt7\u002Fai_skills_collection_benchmarked --skill scvi-model-inputs","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Frepaired\u002Fskills\u002Fby-category\u002Fscience-research-data-analysis\u002Flatest-release-community\u002Fscvi-model-inputs\u002FSKILL.md",true,[58,62,68],{"path":59,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":16},"LICENSE","许可证",1068,{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"provenance\u002Foriginal.SKILL.md","REFERENCE","参考文档",7238,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Frepaired\u002Fskills\u002Fby-category\u002Fscience-research-data-analysis\u002Flatest-release-community\u002Fscvi-model-inputs\u002Fprovenance\u002Foriginal.SKILL.md",{"path":69,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":70,"sourceHtmlUrl":71},"repair.json",1774,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Frepaired\u002Fskills\u002Fby-category\u002Fscience-research-data-analysis\u002Flatest-release-community\u002Fscvi-model-inputs\u002Frepair.json",[73,106,135,160,186,214],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":77,"licenseFileUrl":78,"sourceHtmlUrl":79,"categories":80,"keywords":89,"publishedAt":32},"01M71D4H3T6M57DFKN8HENAWRV","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Ftesting-qa-benchmarking\u002Fofficial-reference\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Ftesting-qa-benchmarking\u002Fofficial-reference\u002Fwebapp-testing\u002FSKILL.md",[81,86],{"categoryNo":82,"categoryName":83,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":87,"categoryName":88,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000009","前端开发",[90,91,92,30,93,94,95,96,97,98,99,100,101,102,103,104,105],"webapp","testing","webapp testing","applications","local","frontend","debugging","toolkit","logs","browser","with","playwright","web","behavior","ui","screenshots",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":77,"licenseFileUrl":110,"sourceHtmlUrl":111,"categories":112,"keywords":116,"publishedAt":32},"01M71D4CQR2A2TB7GASCR5ZBG3","skill-creator","Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Ftesting-qa-benchmarking\u002Fofficial-reference\u002Fskill-creator-anthropics\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Ftesting-qa-benchmarking\u002Fofficial-reference\u002Fskill-creator-anthropics\u002FSKILL.md",[113],{"categoryNo":114,"categoryName":115,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000023","Skill与智能体开发",[117,118,119,120,121,122,123,124,125,126,127,23,128,129,130,131,132,133,30,134],"skill creator","creator","performance","improve","run evals","new","when","analysis","create","optimize","variance analysis","edit","benchmark","a skill","existing skill","evals","modify","accuracy",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":143,"publishedAt":32},"01M71D488XHEZVXXSXFYP8ENMH","playwright-skill","Complete browser automation with Playwright. Auto-detects dev servers, writes reusable test scripts, and supports screenshots, responsive checks, UX validation, login flows, link checks, and arbitrary browser automation. Use when the user wants to test a website, automate browser interactions, validate web functionality, or perform browser-based testing.","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Ftesting-qa-benchmarking\u002Flatest-release-browser-automation\u002Fplaywright-skill\u002FSKILL.md",[141,142],{"categoryNo":82,"categoryName":83,"taxonomyType":84,"taxonomyTypeDesc":85},{"categoryNo":114,"categoryName":115,"taxonomyType":84,"taxonomyTypeDesc":85},[101,144,145,146,91,147,148,123,149,99,150,151,152,153,154,155,156,157,158,159],"playwright skill","browser automation","flows","auto","access","Bash","website","ux","login","scripts","read","write","node","install","network","responsive",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":77,"licenseFileUrl":164,"sourceHtmlUrl":165,"categories":166,"keywords":168,"publishedAt":32},"01M71CY25GM939M6RES91QSG3T","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fsearch-retrieval-web-automation\u002Fofficial-reference\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fsearch-retrieval-web-automation\u002Fofficial-reference\u002Fweb-artifacts-builder\u002FSKILL.md",[167],{"categoryNo":87,"categoryName":88,"taxonomyType":84,"taxonomyTypeDesc":85},[169,170,171,102,172,173,174,30,175,176,95,177,178,179,180,181,182,183,184,185],"builder","artifacts builder","artifacts","web artifacts builder","single-file","css","Tailwind","ui components","single","use","file","components","react","multi","state","routing","state management",{"skillNo":187,"name":188,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":77,"licenseFileUrl":190,"sourceHtmlUrl":191,"categories":192,"keywords":202,"publishedAt":32},"01M71CXZB60QJJ1H4S3NN94WMZ","frontend-design","Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML\u002FCSS layouts, or when styling\u002Fbeautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fsearch-retrieval-web-automation\u002Fofficial-reference\u002Ffrontend-design\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fsearch-retrieval-web-automation\u002Fofficial-reference\u002Ffrontend-design\u002FSKILL.md",[193,194,197],{"categoryNo":87,"categoryName":88,"taxonomyType":84,"taxonomyTypeDesc":85},{"categoryNo":195,"categoryName":196,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":198,"categoryName":199,"taxonomyType":200,"taxonomyTypeDesc":201},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[95,203,204,174,205,206,207,93,208,209,178,123,171,210,180,211,181,212,213,100],"design","frontend design","ui design","generic","aesthetics","landing","pages","code","web ui","react components","examples",{"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":220,"publishedAt":32},"01M71CVZ54WFBTVA7R16PFY1ZE","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fscience-research-data-analysis\u002Flatest-release-community\u002Fzarr-python\u002FSKILL.md",[],[221,222,223,224,225,226,227,228,229,30,230,231,232,233,234,235,236,237],"zarr python","python","zarr","arrays","Cloud Storage","scientific","storage","parallel","dask","numpy","gcs","s3","integration","scientific computing","cloud","scale","pipelines"]