[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71B370WF27RE1GD5SRGFQJZ":3,"skill-same:01M71B370WF27RE1GD5SRGFQJZ":69},{"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":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":40,"install":41,"resources":54},"01M71B370WF27RE1GD5SRGFQJZ","cellxgene-census-summary-and-mean",null,"Read Census summary counts and compute a zero-filled overall raw-matrix mean with the correct denominator.","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\u002Fcellxgene-census-summary-and-mean\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Frepaired\u002Fskills\u002Fby-category\u002Fscience-research-data-analysis\u002Flatest-release-community\u002Fcellxgene-census-summary-and-mean\u002FSKILL.md",[],[20,21,22,23,24,25,26,27,28],"cellxgene census","summary","cellxgene census summary and mean","ZeRO","correct","read","compute","with","matrix","2026-11-10 10:12:30",false,"---\nname: cellxgene-census-summary-and-mean\ndescription: Read Census summary counts and compute a zero-filled overall raw-matrix mean with the correct denominator.\nlicense: MIT\n---\n\n# CELLxGENE Census summary and raw-matrix mean\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\nPin the Census build and record the chosen organism, measurement, filters and\nlayer. This focused repair covers summary counts and one descriptive matrix\nmean; it does not validate other workflows in the source skill.\n\n## Read a summary count\n\nFor an open Census collection `census`, the summary is a table of `label` and\n`value` rows. Convert the selected count to an integer:\n\n```python\nsummary = census[\"census_info\"][\"summary\"].read().concat().to_pandas()\nsummary_values = summary.set_index(\"label\")[\"value\"]\ntotal_cell_count = int(summary_values.loc[\"total_cell_count\"])\n```\n\n## Describe the selected raw matrix\n\nFor an open RNA `ExperimentAxisQuery` named `query`, this computes one overall\nmean across all selected cell-by-feature positions, including implicit zero\nfill values. It is not a per-gene mean. Reject an empty query rather than\nreporting a misleading zero:\n\n```python\nimport math\nimport numpy as np\n\nn_positions = query.n_obs * query.n_vars\nif not n_positions:\n    raise ValueError(\"Cannot average an empty cell-by-feature selection\")\ntotal = math.fsum(\n    float(np.sum(batch[\"soma_data\"].to_numpy(), dtype=np.float64))\n    for batch in query.X(\"raw\").tables()\n)\nmean_expression = total \u002F n_positions\n```\n\nRaw matrices use sparse zero fill: averaging only returned entries computes a\nnonzero-entry mean instead. This matrix-wide zero-filled mean is a descriptive\nchoice, not automatically a biological expression estimate. Genes absent from\nsource datasets can be represented as zero in the combined matrix. Use the\nfeature dataset presence information and an appropriate measured-cell\ndenominator for a per-gene analysis; do not silently treat unmeasured genes as\nmeasured zeros. When grouping per gene, map SOMA join IDs to query positions\nusing the query indexer rather than treating join IDs as array offsets.\n\nSee the [Census schema](https:\u002F\u002Fchanzuckerberg.github.io\u002Fcellxgene-census\u002Fcellxgene_census_schema.html)\nand the [incremental computation tutorial](https:\u002F\u002Fchanzuckerberg.github.io\u002Fcellxgene-census\u002Fnotebooks\u002Fapi_demo\u002Fcensus_compute_over_X.html).\n","# CELLxGENE Census summary and raw-matrix mean\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\nPin the Census build and record the chosen organism, measurement, filters and\nlayer. This focused repair covers summary counts and one descriptive matrix\nmean; it does not validate other workflows in the source skill.\n\n## Read a summary count\n\nFor an open Census collection `census`, the summary is a table of `label` and\n`value` rows. Convert the selected count to an integer:\n\n```python\nsummary = census[\"census_info\"][\"summary\"].read().concat().to_pandas()\nsummary_values = summary.set_index(\"label\")[\"value\"]\ntotal_cell_count = int(summary_values.loc[\"total_cell_count\"])\n```\n\n## Describe the selected raw matrix\n\nFor an open RNA `ExperimentAxisQuery` named `query`, this computes one overall\nmean across all selected cell-by-feature positions, including implicit zero\nfill values. It is not a per-gene mean. Reject an empty query rather than\nreporting a misleading zero:\n\n```python\nimport math\nimport numpy as np\n\nn_positions = query.n_obs * query.n_vars\nif not n_positions:\n    raise ValueError(\"Cannot average an empty cell-by-feature selection\")\ntotal = math.fsum(\n    float(np.sum(batch[\"soma_data\"].to_numpy(), dtype=np.float64))\n    for batch in query.X(\"raw\").tables()\n)\nmean_expression = total \u002F n_positions\n```\n\nRaw matrices use sparse zero fill: averaging only returned entries computes a\nnonzero-entry mean instead. This matrix-wide zero-filled mean is a descriptive\nchoice, not automatically a biological expression estimate. Genes absent from\nsource datasets can be represented as zero in the combined matrix. Use the\nfeature dataset presence information and an appropriate measured-cell\ndenominator for a per-gene analysis; do not silently treat unmeasured genes as\nmeasured zeros. When grouping per gene, map SOMA join IDs to query positions\nusing the query indexer rather than treating join IDs as array offsets.\n\nSee the [Census schema](https:\u002F\u002Fchanzuckerberg.github.io\u002Fcellxgene-census\u002Fcellxgene_census_schema.html)\nand the [incremental computation tutorial](https:\u002F\u002Fchanzuckerberg.github.io\u002Fcellxgene-census\u002Fnotebooks\u002Fapi_demo\u002Fcensus_compute_over_X.html).\n",{"name":5,"license":15,"description":7},"main","5c95bcac4646c5aed06bd9aed5235cfc7985aafc","included\u002Frepaired\u002Fskills\u002Fby-category\u002Fscience-research-data-analysis\u002Flatest-release-community\u002Fcellxgene-census-summary-and-mean",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":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add strmt7\u002Fai_skills_collection_benchmarked --skill cellxgene-census-summary-and-mean",{"tool":47,"command":48},"bunx","bunx skills add strmt7\u002Fai_skills_collection_benchmarked --skill cellxgene-census-summary-and-mean",{"tool":50,"command":51},"pnpm","pnpm dlx skills add strmt7\u002Fai_skills_collection_benchmarked --skill cellxgene-census-summary-and-mean","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\u002Fcellxgene-census-summary-and-mean\u002FSKILL.md",true,[55,59,65],{"path":56,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":16},"LICENSE","许可证",1068,{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"provenance\u002Foriginal.SKILL.md","REFERENCE","参考文档",15438,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Frepaired\u002Fskills\u002Fby-category\u002Fscience-research-data-analysis\u002Flatest-release-community\u002Fcellxgene-census-summary-and-mean\u002Fprovenance\u002Foriginal.SKILL.md",{"path":66,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":67,"sourceHtmlUrl":68},"repair.json",1591,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Frepaired\u002Fskills\u002Fby-category\u002Fscience-research-data-analysis\u002Flatest-release-community\u002Fcellxgene-census-summary-and-mean\u002Frepair.json",[70,103,133,157,183,211],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":75,"sourceHtmlUrl":76,"categories":77,"keywords":86,"publishedAt":29},"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",[78,83],{"categoryNo":79,"categoryName":80,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":84,"categoryName":85,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000009","前端开发",[87,88,89,90,91,92,93,94,95,96,97,27,98,99,100,101,102],"webapp","testing","webapp testing","for","applications","local","frontend","debugging","toolkit","logs","browser","playwright","web","behavior","ui","screenshots",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":107,"sourceHtmlUrl":108,"categories":109,"keywords":113,"publishedAt":29},"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",[110],{"categoryNo":111,"categoryName":112,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000023","Skill与智能体开发",[114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,90,132],"skill creator","creator","performance","improve","run evals","new","when","analysis","create","optimize","variance analysis","run","edit","benchmark","a skill","existing skill","evals","modify","accuracy",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":141,"publishedAt":29},"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",[139,140],{"categoryNo":79,"categoryName":80,"taxonomyType":81,"taxonomyTypeDesc":82},{"categoryNo":111,"categoryName":112,"taxonomyType":81,"taxonomyTypeDesc":82},[98,142,143,144,88,145,146,120,147,97,148,149,150,151,25,152,153,154,155,156],"playwright skill","browser automation","flows","auto","access","Bash","website","ux","login","scripts","write","node","install","network","responsive",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":161,"sourceHtmlUrl":162,"categories":163,"keywords":165,"publishedAt":29},"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",[164],{"categoryNo":84,"categoryName":85,"taxonomyType":81,"taxonomyTypeDesc":82},[166,167,168,99,169,170,171,90,172,173,93,174,175,176,177,178,179,180,181,182],"builder","artifacts builder","artifacts","web artifacts builder","single-file","css","Tailwind","ui components","single","use","file","components","react","multi","state","routing","state management",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":187,"sourceHtmlUrl":188,"categories":189,"keywords":199,"publishedAt":29},"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",[190,191,194],{"categoryNo":84,"categoryName":85,"taxonomyType":81,"taxonomyTypeDesc":82},{"categoryNo":192,"categoryName":193,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":195,"categoryName":196,"taxonomyType":197,"taxonomyTypeDesc":198},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[93,200,201,171,202,203,204,91,205,206,175,120,168,207,177,208,178,209,210,27],"design","frontend design","ui design","generic","aesthetics","landing","pages","code","web ui","react components","examples",{"skillNo":212,"name":213,"nameZh":6,"description":214,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":215,"categories":216,"keywords":217,"publishedAt":29},"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",[],[218,219,220,221,222,223,224,225,226,90,227,228,229,230,231,232,233,234],"zarr python","python","zarr","arrays","Cloud Storage","scientific","storage","parallel","dask","numpy","gcs","s3","integration","scientific computing","cloud","scale","pipelines"]