[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M699WDK4V7G121TSCY17PD7Y":3,"skill-same:01M699WDK4V7G121TSCY17PD7Y":58},{"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":28,"linkOnly":29,"markdownContent":30,"markdownBody":31,"frontMatter":32,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":39,"ownerHtmlUrl":40,"ownerBlogUrl":41,"ownerDescription":42,"updatedAt":43,"install":44,"resources":57},"01M699WDK4V7G121TSCY17PD7Y","analyze-drivers",null,"Use when seeking explanatory attributes or hypotheses for differences in process duration, waiting, utilization or rework.","microsoft\u002Fpower-platform-skills","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M699JVYJFB75D9JM70BN4H0Q",1143,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fpower-platform-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fprocess-intelligence\u002Fskills\u002Fanalyze-drivers\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27],"analyze drivers","analyze","read","process","utilization","use","attributes","for","when","2026-11-10 10:12:30",false,"---\nname: analyze-drivers\ndescription: Use when seeking explanatory attributes or hypotheses for differences in process duration, waiting, utilization or rework.\nallowed-tools: Read, AskUserQuestion\n---\n\n# Drivers: association before explanation\n\nUse the [shared contract](..\u002F..\u002Freferences\u002Fanalysis-contract.md) and\n[filter\u002Funit reference](..\u002F..\u002Freferences\u002Ffilters-and-units.md).\nReuse metadata and frozen baseline scope; choose a specific defined outcome and relevant case-level\nattributes from the user's context, without a candidate quota. If none is known, ask; do not sweep.\nState a testable hypothesis, possible competing explanation and what would distinguish them.\nLoad the [investigation method](..\u002F..\u002Freferences\u002Finvestigation-method.md) for evidence\u002Fstatus tracking.\nFor utilization, first check timestamp imports and the zero-duration convention in the unit\nreference. A cohort-mix convention is not resource efficiency or measured productive time.\n\n## Ordered trace\n\n1. Check A's metadata level before correlation. Reuse a cached signal instead of repeating it.\n   `get_correlation_v2 {S,attributeName:A,influenceFormula:I,sortOrder:\"Descending\",filterOptions:F}`.\n\n   | Outcome | I |\n   |---|---|\n   | Duration \u002F waiting \u002F active time | DurationInfluence \u002F WaitingTimeInfluence \u002F ActiveTimeInfluence |\n   | Utilization \u002F event count | CaseUtilizationInfluence \u002F EventCountInfluence |\n   | Rework \u002F loops \u002F self-loops | ReworkCountInfluence \u002F LoopCountInfluence \u002F SelfloopCountInfluence |\n\n   Use the advertised enum and exact spelling. There are **no** `itemsPerPage`, `itemsToSkip`,\n   `top`, `metrics` or `limit` arguments. The service ranks at most 20 groups.\n2. Only if prevalence or mean evidence is needed and statistics is advertised:\n   `get_attribute_statistics {S,attributeName:A,filterOptions:F,itemsPerPage:5,itemsToSkip:0,metricToSortBy:\"CaseFrequency\",sortOrder:\"Descending\"}`.\n   Match returned values explicitly. Influence-ranked groups may differ from\n   frequency-ranked groups; an absent match is unknown, not zero.\n3. For a remaining hypothesis, use a discriminating matched comparison via compare-cohorts,\n   focused statistics\u002Fcases, or another relevant candidate. Derive each test from frozen F,\n   never an outcome-only exploratory subset. A cached signal can go directly to its test.\n   Continue needed checks\u002Fpages without fixed analytical-call or candidate quotas.\n   If matched evidence contradicts the proposed direction, mark it **contradicted** within that\n   scope; do not privilege the earlier influence score or claim it proves a cause.\n\n## Non-case branch\n\nAn event-level Resource cannot be sent to correlation. If useful and advertised, use the\nstatistics call above for that attribute, but describe grouped **event** duration\u002Ffrequencies,\nnot case-duration drivers. Otherwise ask for a case-level candidate or report the capability gap.\nDo not silently substitute a different causal analysis.\n\n## Report and stop\n\nInfluence is a prevalence-weighted descriptive score, **not Pearson correlation, significance,\ncausal effect or confidence**. Its formula already scales by 100; do not multiply again.\nReturn at most five useful signals with available counts\u002Fmeans, units, scope and partial coverage.\nLabel explanations as hypotheses, note selection\u002Fconfounding, and state one falsifiable evidence check.\nRecord tested versus merely observed claims, alternatives and missing evidence; revise or stop\nwhen the next check cannot discriminate. No assumed outcome maturity or closure.\nStop when no discriminating evidence remains; do not paginate correlations or invent sample sizes.\n","# Drivers: association before explanation\n\nUse the [shared contract](..\u002F..\u002Freferences\u002Fanalysis-contract.md) and\n[filter\u002Funit reference](..\u002F..\u002Freferences\u002Ffilters-and-units.md).\nReuse metadata and frozen baseline scope; choose a specific defined outcome and relevant case-level\nattributes from the user's context, without a candidate quota. If none is known, ask; do not sweep.\nState a testable hypothesis, possible competing explanation and what would distinguish them.\nLoad the [investigation method](..\u002F..\u002Freferences\u002Finvestigation-method.md) for evidence\u002Fstatus tracking.\nFor utilization, first check timestamp imports and the zero-duration convention in the unit\nreference. A cohort-mix convention is not resource efficiency or measured productive time.\n\n## Ordered trace\n\n1. Check A's metadata level before correlation. Reuse a cached signal instead of repeating it.\n   `get_correlation_v2 {S,attributeName:A,influenceFormula:I,sortOrder:\"Descending\",filterOptions:F}`.\n\n   | Outcome | I |\n   |---|---|\n   | Duration \u002F waiting \u002F active time | DurationInfluence \u002F WaitingTimeInfluence \u002F ActiveTimeInfluence |\n   | Utilization \u002F event count | CaseUtilizationInfluence \u002F EventCountInfluence |\n   | Rework \u002F loops \u002F self-loops | ReworkCountInfluence \u002F LoopCountInfluence \u002F SelfloopCountInfluence |\n\n   Use the advertised enum and exact spelling. There are **no** `itemsPerPage`, `itemsToSkip`,\n   `top`, `metrics` or `limit` arguments. The service ranks at most 20 groups.\n2. Only if prevalence or mean evidence is needed and statistics is advertised:\n   `get_attribute_statistics {S,attributeName:A,filterOptions:F,itemsPerPage:5,itemsToSkip:0,metricToSortBy:\"CaseFrequency\",sortOrder:\"Descending\"}`.\n   Match returned values explicitly. Influence-ranked groups may differ from\n   frequency-ranked groups; an absent match is unknown, not zero.\n3. For a remaining hypothesis, use a discriminating matched comparison via compare-cohorts,\n   focused statistics\u002Fcases, or another relevant candidate. Derive each test from frozen F,\n   never an outcome-only exploratory subset. A cached signal can go directly to its test.\n   Continue needed checks\u002Fpages without fixed analytical-call or candidate quotas.\n   If matched evidence contradicts the proposed direction, mark it **contradicted** within that\n   scope; do not privilege the earlier influence score or claim it proves a cause.\n\n## Non-case branch\n\nAn event-level Resource cannot be sent to correlation. If useful and advertised, use the\nstatistics call above for that attribute, but describe grouped **event** duration\u002Ffrequencies,\nnot case-duration drivers. Otherwise ask for a case-level candidate or report the capability gap.\nDo not silently substitute a different causal analysis.\n\n## Report and stop\n\nInfluence is a prevalence-weighted descriptive score, **not Pearson correlation, significance,\ncausal effect or confidence**. Its formula already scales by 100; do not multiply again.\nReturn at most five useful signals with available counts\u002Fmeans, units, scope and partial coverage.\nLabel explanations as hypotheses, note selection\u002Fconfounding, and state one falsifiable evidence check.\nRecord tested versus merely observed claims, alternatives and missing evidence; revise or stop\nwhen the next check cannot discriminate. No assumed outcome maturity or closure.\nStop when no discriminating evidence remains; do not paginate correlations or invent sample sizes.\n",{"name":5,"description":7,"allowed-tools":33},"Read, AskUserQuestion","main","0a55a88fa2855404029d1e5450faf92878baf763","plugins\u002Fprocess-intelligence\u002Fskills\u002Fanalyze-drivers",229,"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","2026-11-13 01:33:52",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add microsoft\u002Fpower-platform-skills --skill analyze-drivers",{"tool":50,"command":51},"bunx","bunx skills add microsoft\u002Fpower-platform-skills --skill analyze-drivers",{"tool":53,"command":54},"pnpm","pnpm dlx skills add microsoft\u002Fpower-platform-skills --skill analyze-drivers","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fpower-platform-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fprocess-intelligence\u002Fskills\u002Fanalyze-drivers\u002FSKILL.md",true,[],[59,77,99,117,131,141],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":28},"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",[],[61,21,27,66,67,68,69,70,24,22,71,72,73,74,75,76],"connection","error","sign","intelligence","configuration","diagnostics","environment","authentication","cloud","recovery","Bash",{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":88,"publishedAt":28},"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",[83],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[89,90,91,92,93,22,24,94,95,69,96,97,26,27,98],"report issue","report","issue","support","user","bug","summary","draft","operation","bug-report",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":28},"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",[],[22,106,107,108,27,109,110,111,112,21,113,24,114,115,116],"investigate","investigate process","mining","process mining","investigation","perspectives","question","business","pattern","across","analytical",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":28},"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",[],[124,125,21,24,126,127,128,129,130,27],"metric","derive metric","formula","missing","reuse","saved","custom",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":28},"01M699WMG5R8P6SMTDAS1TKF9E","compare-cohorts","Use when comparing process cohorts, departments, periods or before-and-after results under matched definitions.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fpower-platform-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fprocess-intelligence\u002Fskills\u002Fcompare-cohorts\u002FSKILL.md",[],[138,139,27,24,22,140,21],"compare","compare cohorts","results",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":28},"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",[],[20,148,149,109,27,108,150,151,24,22,21,152,153],"variants","analyze variants","case","paths","work","common"]