[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M699WMG5R8P6SMTDAS1TKF9E":3,"skill-same:01M699WMG5R8P6SMTDAS1TKF9E":62},{"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":18,"publishedAt":26,"linkOnly":27,"markdownContent":28,"markdownBody":29,"frontMatter":30,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":37,"ownerHtmlUrl":38,"ownerBlogUrl":39,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M699WMG5R8P6SMTDAS1TKF9E","compare-cohorts",null,"Use when comparing process cohorts, departments, periods or before-and-after results under matched definitions.","microsoft\u002Fpower-platform-skills","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M699JVYJFB75D9JM70BN4H0Q",1149,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fpower-platform-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fprocess-intelligence\u002Fskills\u002Fcompare-cohorts\u002FSKILL.md",[],[19,20,21,22,23,24,25],"compare cohorts","compare","read","results","process","use","when","2026-11-10 10:12:30",false,"---\nname: compare-cohorts\ndescription: Use when comparing process cohorts, departments, periods or before-and-after results under matched definitions.\nallowed-tools: Read, AskUserQuestion\n---\n\n# Matched cohort comparisons\n\nUse the [shared contract](..\u002F..\u002Freferences\u002Fanalysis-contract.md) and\n[filters\u002Funits](..\u002F..\u002Freferences\u002Ffilters-and-units.md).\nFix the outcome definition\u002Fprovenance, metric, aggregation, units, timezone and one selector S.\nFreeze the user's agreed baseline F, separately from current exploratory filters.\nReuse metadata versions and exact typed cohort values. Use the\n[investigation method](..\u002F..\u002Freferences\u002Finvestigation-method.md) for findings\u002Fstatus.\n\n## Ordered trace\n\n1. Copy baseline F twice. For attribute cohorts append\n   `{attributeName:A,dataType:T,attributeValues:[X],isInclusive:true}` to\n   `attributeValueFilters` for A's cohort value, and the same shape with Y for B.\n   Preserve other agreed baseline conditions; retain rework restrictions only if part of that\n   baseline. Do not leak an exploratory\u002Foutcome-only subset into a full-population comparison.\n   Change only the intended cohort condition. If values are unknown, request\n   `get_attribute_values_v2 {S,attributeName:A,itemsPerPage:20,itemsToSkip:0,filterOptions:F}`;\n   it returns values, not frequencies.\n2. `get_process_overall_metrics_v2 {S,filterOptions:F_A}` ->\n   `get_process_overall_metrics_v2 {S,filterOptions:F_B}`.\n   No `metrics`, `groupBy` or aggregation parameter exists. Use the same returned metric definitions;\n   native `CaseDuration`\u002F`CaseWaitingTime` are means.\n3. Only if a grouped explanation is needed and statistics is advertised, make a **matched pair**:\n   `get_attribute_statistics {S,attributeName:A,filterOptions:F_A,itemsPerPage:5,itemsToSkip:0,metricToSortBy:\"TotalDuration\",sortOrder:\"Descending\"}`,\n   then exactly the same call with F_B. Do not treat independent top-five pages as a complete aligned population.\n\nContinue relevant value\u002Fgroup pages or matched follow-ups when needed, without fixed call quotas.\nStop at sufficient evidence, no new information or a capability\u002Ferror boundary; no blind sweeps.\nDo not create views or use two inclusive timeframes in one query as an A\u002FB comparison.\n\n## Time and reproducibility\n\nFor periods, change only one explicit `timeframeFilters` start\u002Fend pair in each copied F.\nCase windows mean **Contained**, not cases Started\u002FCompleted\u002FIntersecting or all events during the period.\nIf completed-only membership including earlier starts is essential, stop\u002Freframe or route\nto derive-metric\u002Fa user-confirmed existing matching view. Never invent a date-mode field\nor promise unknown end-boundary behavior.\n\nIf refresh is reported or reproducibility is at risk, recheck details.\nChanged PV\u002FPMV invalidates the pair: mark **inconclusive**, stop or deliberately rerun both,\nnot just the second.\nProcess selection resolves latest; no direct version selector or atomic comparison snapshot exists.\nViews pin version context but their configuration is mutable\u002Fcached.\n\nReport A\u002FB counts, mean metrics, absolute delta and relative change only for a nonzero baseline.\nEmpty cohorts mean insufficient evidence, not zero duration\u002Finfinite improvement.\nState scope\u002Fversion and unmatched-group coverage; at most five headline rows.\nRecorded means do not establish closure, equal maturity or complete lifecycles. Report those\nas unknown unless supported; qualify the comparison, not an assumed causal improvement.\nRetain baseline\u002Fcohort filters, evidence references, status and alternatives. Overlapping groups\ncannot be added as unique-case totals.\nObject-centric comparisons belong in analyze-objects, not case-filter fallbacks.\n","# Matched cohort comparisons\n\nUse the [shared contract](..\u002F..\u002Freferences\u002Fanalysis-contract.md) and\n[filters\u002Funits](..\u002F..\u002Freferences\u002Ffilters-and-units.md).\nFix the outcome definition\u002Fprovenance, metric, aggregation, units, timezone and one selector S.\nFreeze the user's agreed baseline F, separately from current exploratory filters.\nReuse metadata versions and exact typed cohort values. Use the\n[investigation method](..\u002F..\u002Freferences\u002Finvestigation-method.md) for findings\u002Fstatus.\n\n## Ordered trace\n\n1. Copy baseline F twice. For attribute cohorts append\n   `{attributeName:A,dataType:T,attributeValues:[X],isInclusive:true}` to\n   `attributeValueFilters` for A's cohort value, and the same shape with Y for B.\n   Preserve other agreed baseline conditions; retain rework restrictions only if part of that\n   baseline. Do not leak an exploratory\u002Foutcome-only subset into a full-population comparison.\n   Change only the intended cohort condition. If values are unknown, request\n   `get_attribute_values_v2 {S,attributeName:A,itemsPerPage:20,itemsToSkip:0,filterOptions:F}`;\n   it returns values, not frequencies.\n2. `get_process_overall_metrics_v2 {S,filterOptions:F_A}` ->\n   `get_process_overall_metrics_v2 {S,filterOptions:F_B}`.\n   No `metrics`, `groupBy` or aggregation parameter exists. Use the same returned metric definitions;\n   native `CaseDuration`\u002F`CaseWaitingTime` are means.\n3. Only if a grouped explanation is needed and statistics is advertised, make a **matched pair**:\n   `get_attribute_statistics {S,attributeName:A,filterOptions:F_A,itemsPerPage:5,itemsToSkip:0,metricToSortBy:\"TotalDuration\",sortOrder:\"Descending\"}`,\n   then exactly the same call with F_B. Do not treat independent top-five pages as a complete aligned population.\n\nContinue relevant value\u002Fgroup pages or matched follow-ups when needed, without fixed call quotas.\nStop at sufficient evidence, no new information or a capability\u002Ferror boundary; no blind sweeps.\nDo not create views or use two inclusive timeframes in one query as an A\u002FB comparison.\n\n## Time and reproducibility\n\nFor periods, change only one explicit `timeframeFilters` start\u002Fend pair in each copied F.\nCase windows mean **Contained**, not cases Started\u002FCompleted\u002FIntersecting or all events during the period.\nIf completed-only membership including earlier starts is essential, stop\u002Freframe or route\nto derive-metric\u002Fa user-confirmed existing matching view. Never invent a date-mode field\nor promise unknown end-boundary behavior.\n\nIf refresh is reported or reproducibility is at risk, recheck details.\nChanged PV\u002FPMV invalidates the pair: mark **inconclusive**, stop or deliberately rerun both,\nnot just the second.\nProcess selection resolves latest; no direct version selector or atomic comparison snapshot exists.\nViews pin version context but their configuration is mutable\u002Fcached.\n\nReport A\u002FB counts, mean metrics, absolute delta and relative change only for a nonzero baseline.\nEmpty cohorts mean insufficient evidence, not zero duration\u002Finfinite improvement.\nState scope\u002Fversion and unmatched-group coverage; at most five headline rows.\nRecorded means do not establish closure, equal maturity or complete lifecycles. Report those\nas unknown unless supported; qualify the comparison, not an assumed causal improvement.\nRetain baseline\u002Fcohort filters, evidence references, status and alternatives. Overlapping groups\ncannot be added as unique-case totals.\nObject-centric comparisons belong in analyze-objects, not case-filter fallbacks.\n",{"name":5,"description":7,"allowed-tools":31},"Read, AskUserQuestion","main","0a55a88fa2855404029d1e5450faf92878baf763","plugins\u002Fprocess-intelligence\u002Fskills\u002Fcompare-cohorts",232,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fpower-platform-skills","https:\u002F\u002Fmicrosoft.github.io\u002Fpower-platform-skills\u002F","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-14 21:46:39",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add microsoft\u002Fpower-platform-skills --skill compare-cohorts",{"tool":48,"command":49},"bunx","bunx skills add microsoft\u002Fpower-platform-skills --skill compare-cohorts",{"tool":51,"command":52},"pnpm","pnpm dlx skills add microsoft\u002Fpower-platform-skills --skill compare-cohorts","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fpower-platform-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fprocess-intelligence\u002Fskills\u002Fcompare-cohorts\u002FSKILL.md",true,[56],{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"scripts\u002Fextract_frontmatter.py","SCRIPT","脚本",640,"https:\u002F\u002Fgithub.com\u002FNakul-Kumar\u002FAgentDevOps\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Flocal\u002Fyaml-frontmatter-extractor\u002Fscripts\u002Fextract_frontmatter.py",[63,71,89,112,130,144],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":70},"01M78JN2BFRRV1J54Q6WKZQ08D","compare-site-configurations","Compare Power Pages site configurations between two environments, such as dev, test and production, or between a local download and the live site, and explain which differences change site behavior. Use when a site works in one environment but not another (for example, works in dev but fails in test), to check configuration drift before promoting or deploying, or to see what changed between two sites. Produces a shareable HTML report and a JSON file that VS Code can import.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fpower-platform-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fpower-pages\u002Fskills\u002Fcompare-site-configurations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":26},"01M699WVHX0XN59EPBTTPEKYPG","setup","Use when Process Intelligence needs building, explicit cloud\u002Faccount\u002Fenvironment configuration, sign-in, connection diagnostics, or recovery from an authentication error.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fpower-platform-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fprocess-intelligence\u002Fskills\u002Fsetup\u002FSKILL.md",[],[73,78,25,79,80,81,82,83,84,85,24,86,87,21,88,23],"configuration","diagnostics","sign","cloud","connection","error","environment","authentication","Bash","intelligence","recovery",{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":100,"publishedAt":26},"01M699WSR9EX55YY1WD9J22FEG","report-issue","Use when the user wants a Process Intelligence bug-report draft or support summary for a failed operation.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fpower-platform-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fprocess-intelligence\u002Fskills\u002Freport-issue\u002FSKILL.md",[95],{"categoryNo":96,"categoryName":97,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[101,102,103,104,105,106,24,25,107,108,23,109,87,110,111],"report issue","report","issue","support","for","bug-report","operation","draft","bug","summary","user",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":26},"01M699WR26YQ9Q21KE6MJF5B2G","investigate-process","Use when a broad Process Mining business question, observed pattern or competing explanation needs investigation across analytical perspectives.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fpower-platform-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fprocess-intelligence\u002Fskills\u002Finvestigate-process\u002FSKILL.md",[],[23,119,120,121,122,24,123,124,25,125,126,127,21,128,129],"investigate","investigate process","analytical","question","process mining","business","across","perspectives","mining","pattern","investigation",{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":26},"01M699WP9SDG5ZR12P8VYNXKTN","derive-metric","Use when a requested measure is missing, a saved custom metric needs reuse, or an ephemeral formula or derived scalar is needed.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fpower-platform-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fprocess-intelligence\u002Fskills\u002Fderive-metric\u002FSKILL.md",[],[137,138,24,139,140,141,142,25,143,21],"metric","derive metric","missing","formula","custom","reuse","saved",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":150,"publishedAt":26},"01M699WJWNVTMP9XK3NCJHV14D","analyze-variants","Use when investigating common or slow variants, repeated work, unusual paths, or a specific Process Mining case.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fpower-platform-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fprocess-intelligence\u002Fskills\u002Fanalyze-variants\u002FSKILL.md",[],[151,152,153,24,123,25,154,155,156,127,23,21,157],"variants","analyze","analyze variants","common","case","work","paths"]