[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7185MSSK4R4TJK4FDPEXYNS":3,"skill-same:01M7185MSSK4R4TJK4FDPEXYNS":127},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":60,"ownerHtmlUrl":61,"ownerBlogUrl":62,"ownerDescription":63,"updatedAt":64,"install":65,"resources":78},"01M7185MSSK4R4TJK4FDPEXYNS","viva-insights-process-analysis",null,"Analyse collaboration around a named business process, such as an annual audit, financial close, planning cycle or review programme, using Viva Insights Meeting Query and optional purpose-specific Person Query exports. Use when defining which process meetings count, reviewing title\u002Fdate rules, comparing matched cycles, explaining changes in volume or meeting format, or refreshing a process report. Owns scope discovery, approved reporting, reconciliation and descriptive interpretation. Do not trigger for Purview audit-log parsing, compliance certification, event-log process mining, generic Copilot dashboards or an unrelated software audit.","microsoft\u002Fviva-insights-sample-code","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M71857T5ED5KEB81YK82QV07",15,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fviva-insights-sample-code\u002Fblob\u002Fmain\u002Ffrontier-analytics\u002Fskills\u002Fviva-insights-process-analysis\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000037","律师与法务",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"insights","analysis","viva insights","process","process analysis","viva insights process analysis","programme","review","log","query","when","process meetings","purview","copilot","cycle","scope","interpretation","volume","which","reconciliation","2026-11-10 10:12:30",false,"---\nname: viva-insights-process-analysis\ndescription: >\n  Analyse collaboration around a named business process, such as an annual\n  audit, financial close, planning cycle or review programme, using Viva\n  Insights Meeting Query and optional purpose-specific Person Query exports.\n  Use when defining which process meetings count, reviewing title\u002Fdate rules,\n  comparing matched cycles, explaining changes in volume or meeting format,\n  or refreshing a process report. Owns scope discovery, approved reporting,\n  reconciliation and descriptive interpretation. Do not trigger for Purview\n  audit-log parsing, compliance certification, event-log process mining,\n  generic Copilot dashboards or an unrelated software audit.\nmetadata:\n  version: \"1.0.0\"\n---\n\n# Collaboration around a business process\n\nHelp the analyst establish what qualifies, how much collaboration is observed,\nwhere it is organised and how comparable periods differ. Meeting titles are\nproxies for process activity. They do not prove process completion, quality,\nownership or intervention impact.\n\nThis is an agent-guided local R\u002FPython workflow. The bundled Python rehearsal\nand R classifier checks use fabricated audit events. They are not universal\nreal-export adapters, a process-mining engine or an inference\u002Freport renderer.\n\n## Shared contracts and installation\n\nInstall alongside `viva-insights-analysis` from the same repository revision.\nRead its [analysis policy](..\u002Fviva-insights-analysis\u002Freference\u002Fanalysis-policy.md),\n[Meeting Query reference](..\u002Fviva-insights-analysis\u002Freference\u002Fmeeting-query.md),\n[analysis conventions](..\u002Fviva-insights-analysis\u002Freference\u002Fanalysis-conventions.md)\nand [report verification](..\u002Fviva-insights-analysis\u002Freference\u002Freport-verification.md).\nUse its package discovery and installed-API checks for imports and analysis.\nRead the [workflow support](..\u002Fviva-insights-analysis\u002Freference\u002Fworkflow-support.md)\nbefore claiming a maintained execution path.\n\nIf paired files are unavailable, ask for the installed core folder or a local\nsample-code checkout. Stop the affected execution if neither is supplied.\nDo not silently substitute personal skills or private services. No telemetry,\ncredentials or live-product connector is required. Do not install dependencies,\ndownload data or publish files without the user's approval.\n\n## 1. Agree the question and reporting contract\n\nRecover supplied decisions before asking for the process definition, audience,\nR\u002FPython preference, local inputs, output location, scope approver and comparison.\nDistinguish descriptive footprint\u002Fmonitoring from an intervention-effect question.\nRecord unknown intervention dates or participation without blocking a useful\ndescriptive assessment.\n\nRead [scope contract](reference\u002Fscope-contract.md). Record source fingerprints,\nquery purpose\u002Fconfiguration, grain, fields\u002Funits, population, dates, cycle-year\nlabels, coverage evidence, organisational lens, privacy and optional event-base\nrules. Keep raw coverage, complete months, complete weeks and process phases\ndistinct. A filename or latest event is not completeness evidence.\n\n**Output:** a short contract, open questions and readiness per requested result.\nConfirm material scope and comparison choices before publishing headline totals.\n\n## 2. Explore scope, then freeze an approved definition\n\nRead [scope contract](reference\u002Fscope-contract.md) and\n[review and precedence](reference\u002Freview-and-precedence.md).\nApply the core's reviewed quality profile and shared exclusions before topical\nanalysis, keeping raw exports unchanged. Inspect fields locally and keep\nsensitive subjects\u002Fidentifiers out of prompts and shared examples.\n\nCreate separate candidate and approved flags. Review positive, negative and\nborderline examples across years, languages, periods and organisational cuts.\nMake keywords, aliases, supported year codes, exclusions and annual gates\nexplicit. Do not assume a generic word has the same business meaning everywhere.\nVerify Unicode\u002Fword-boundary behaviour in the actual R\u002FPython regex backends.\n\nAgree exact decision precedence. An occurrence-level decision never becomes a\ntitle-wide rule without approval. Preserve pending states and unmatched or\nambiguous reviews. Never let a Keep bypass mandatory quality\u002Fdate gates.\nRecord whether a change applies retrospectively and show its membership impact.\n\n**Gate:** unresolved scope permits diagnostics, not an approved process total.\nRetain an approved rule version and test worked examples before report building.\n\n## 3. Build comparable analytical evidence\n\nRead [comparisons](reference\u002Fcomparisons.md). Reconcile duplicate keys and source\nvintages under an explicitly approved policy. Use matched observed dates\u002Fphases\nacross years. Compute each standalone category and an exact event-ID union,\nretaining intersections and outside-scope reconciliation privately.\n\nDescribe event count, attendee hours, hours per meeting, seasonality and supported\nformat\u002Fbehaviour measures. Use exported attendee hours. State the valid base and\nweighting for every metric. Separate count from time per event using the exact\nvolume identity in the shared conventions.\n\nOrganisational fields in MQ describe the organiser's recorded reporting line.\nReport missing attribution, changed labels and unavailable comparisons. Do not\ninfer attendee composition, headcount or a process owner from those fields.\nApply the stricter organisational rule and a floor of **10 distinct people** for\nthis workflow. Verify the applicable person base; meeting counts and summed\nattendance cannot establish it. Apply any event-count stability threshold separately.\n\nA purpose-specific PQ provides a separate employee-side lens with its own scope,\nwindow, eligibility and weighting. Do not sum it with MQ or assert that a custom\nprocess-hour metric implements the subject classifier. Joining needs a verified\nkey, compatible definition and cardinality audit.\n\n**Output:** reusable aggregate evidence, valid bases, coverage and reconciliations.\n\n## 4. Challenge the conclusion\n\nSeparate source revision, scope revision, period changes and organisational\ncomposition from observed activity changes. Run agreed scope\u002Fwindow sensitivities.\nShow effect sizes and practical importance before significance labels.\n\nIf inference is requested, choose independent units, temporal dependence,\ntest family and compatible methods first. Do not inherit a particular estimator,\nblock width or significance threshold from the example. There is no bundled\nMeeting Query inferential engine.\n\nFor an intervention-effect request, require an identifying design and exposure\ninformation. A supported Person Query exposure-outcome design belongs to\n`viva-insights-causal-analysis`. A Meeting Query event-level design needs its\nown inspected plan and implementation. Descriptive before\u002Fafter differences,\nfixed effects or significant tests alone do not establish impact.\n\n## 5. Report, review and refresh\n\nUse the shared report-verification workflow. Maintain a claim-level evidence\nledger and concise commentary-led views, with visible dates, bases, denominator\nand caveats. Retain complete eligible supporting detail. Reconcile category\noverlaps and keep unavailable values distinct from observed zero.\n\nKeep the analytical evidence fixed during editorial changes. Preserve manual\nedits when revising a publication, verify the candidate and source drift, remove\nonly resolved comments, and publish only to the authorised target with rollback.\nWhen data\u002Fscope\u002Fwindows change, rebuild dependent views and produce a reconciled\nbridge against the previous approved evidence.\n\n## References and rehearsal\n\n| Read | When |\n|---|---|\n| [Scope contract](reference\u002Fscope-contract.md) | Intake, readiness and discovery-to-approved reporting |\n| [Review and precedence](reference\u002Freview-and-precedence.md) | Keywords, review packs, exact decisions and rule changes |\n| [Comparisons](reference\u002Fcomparisons.md) | Matched cycles, denominators, organisational\u002FPQ lenses and refreshes |\n| [Evaluation scenarios](reference\u002Fevaluation.md) | Checking routing, safeguards and publication boundaries |\n| [Fabricated audit rehearsal](examples\u002FREADME.md) | Exercising classification, reconciliation, privacy and partial periods locally |\n\nNever transfer an engagement's aliases, dates, targets, exclusions, personal\nnames or data into the public skill. The example's vocabulary and calendar are\nfictional choices that must not become defaults for another organisation.\n","# Collaboration around a business process\n\nHelp the analyst establish what qualifies, how much collaboration is observed,\nwhere it is organised and how comparable periods differ. Meeting titles are\nproxies for process activity. They do not prove process completion, quality,\nownership or intervention impact.\n\nThis is an agent-guided local R\u002FPython workflow. The bundled Python rehearsal\nand R classifier checks use fabricated audit events. They are not universal\nreal-export adapters, a process-mining engine or an inference\u002Freport renderer.\n\n## Shared contracts and installation\n\nInstall alongside `viva-insights-analysis` from the same repository revision.\nRead its [analysis policy](..\u002Fviva-insights-analysis\u002Freference\u002Fanalysis-policy.md),\n[Meeting Query reference](..\u002Fviva-insights-analysis\u002Freference\u002Fmeeting-query.md),\n[analysis conventions](..\u002Fviva-insights-analysis\u002Freference\u002Fanalysis-conventions.md)\nand [report verification](..\u002Fviva-insights-analysis\u002Freference\u002Freport-verification.md).\nUse its package discovery and installed-API checks for imports and analysis.\nRead the [workflow support](..\u002Fviva-insights-analysis\u002Freference\u002Fworkflow-support.md)\nbefore claiming a maintained execution path.\n\nIf paired files are unavailable, ask for the installed core folder or a local\nsample-code checkout. Stop the affected execution if neither is supplied.\nDo not silently substitute personal skills or private services. No telemetry,\ncredentials or live-product connector is required. Do not install dependencies,\ndownload data or publish files without the user's approval.\n\n## 1. Agree the question and reporting contract\n\nRecover supplied decisions before asking for the process definition, audience,\nR\u002FPython preference, local inputs, output location, scope approver and comparison.\nDistinguish descriptive footprint\u002Fmonitoring from an intervention-effect question.\nRecord unknown intervention dates or participation without blocking a useful\ndescriptive assessment.\n\nRead [scope contract](reference\u002Fscope-contract.md). Record source fingerprints,\nquery purpose\u002Fconfiguration, grain, fields\u002Funits, population, dates, cycle-year\nlabels, coverage evidence, organisational lens, privacy and optional event-base\nrules. Keep raw coverage, complete months, complete weeks and process phases\ndistinct. A filename or latest event is not completeness evidence.\n\n**Output:** a short contract, open questions and readiness per requested result.\nConfirm material scope and comparison choices before publishing headline totals.\n\n## 2. Explore scope, then freeze an approved definition\n\nRead [scope contract](reference\u002Fscope-contract.md) and\n[review and precedence](reference\u002Freview-and-precedence.md).\nApply the core's reviewed quality profile and shared exclusions before topical\nanalysis, keeping raw exports unchanged. Inspect fields locally and keep\nsensitive subjects\u002Fidentifiers out of prompts and shared examples.\n\nCreate separate candidate and approved flags. Review positive, negative and\nborderline examples across years, languages, periods and organisational cuts.\nMake keywords, aliases, supported year codes, exclusions and annual gates\nexplicit. Do not assume a generic word has the same business meaning everywhere.\nVerify Unicode\u002Fword-boundary behaviour in the actual R\u002FPython regex backends.\n\nAgree exact decision precedence. An occurrence-level decision never becomes a\ntitle-wide rule without approval. Preserve pending states and unmatched or\nambiguous reviews. Never let a Keep bypass mandatory quality\u002Fdate gates.\nRecord whether a change applies retrospectively and show its membership impact.\n\n**Gate:** unresolved scope permits diagnostics, not an approved process total.\nRetain an approved rule version and test worked examples before report building.\n\n## 3. Build comparable analytical evidence\n\nRead [comparisons](reference\u002Fcomparisons.md). Reconcile duplicate keys and source\nvintages under an explicitly approved policy. Use matched observed dates\u002Fphases\nacross years. Compute each standalone category and an exact event-ID union,\nretaining intersections and outside-scope reconciliation privately.\n\nDescribe event count, attendee hours, hours per meeting, seasonality and supported\nformat\u002Fbehaviour measures. Use exported attendee hours. State the valid base and\nweighting for every metric. Separate count from time per event using the exact\nvolume identity in the shared conventions.\n\nOrganisational fields in MQ describe the organiser's recorded reporting line.\nReport missing attribution, changed labels and unavailable comparisons. Do not\ninfer attendee composition, headcount or a process owner from those fields.\nApply the stricter organisational rule and a floor of **10 distinct people** for\nthis workflow. Verify the applicable person base; meeting counts and summed\nattendance cannot establish it. Apply any event-count stability threshold separately.\n\nA purpose-specific PQ provides a separate employee-side lens with its own scope,\nwindow, eligibility and weighting. Do not sum it with MQ or assert that a custom\nprocess-hour metric implements the subject classifier. Joining needs a verified\nkey, compatible definition and cardinality audit.\n\n**Output:** reusable aggregate evidence, valid bases, coverage and reconciliations.\n\n## 4. Challenge the conclusion\n\nSeparate source revision, scope revision, period changes and organisational\ncomposition from observed activity changes. Run agreed scope\u002Fwindow sensitivities.\nShow effect sizes and practical importance before significance labels.\n\nIf inference is requested, choose independent units, temporal dependence,\ntest family and compatible methods first. Do not inherit a particular estimator,\nblock width or significance threshold from the example. There is no bundled\nMeeting Query inferential engine.\n\nFor an intervention-effect request, require an identifying design and exposure\ninformation. A supported Person Query exposure-outcome design belongs to\n`viva-insights-causal-analysis`. A Meeting Query event-level design needs its\nown inspected plan and implementation. Descriptive before\u002Fafter differences,\nfixed effects or significant tests alone do not establish impact.\n\n## 5. Report, review and refresh\n\nUse the shared report-verification workflow. Maintain a claim-level evidence\nledger and concise commentary-led views, with visible dates, bases, denominator\nand caveats. Retain complete eligible supporting detail. Reconcile category\noverlaps and keep unavailable values distinct from observed zero.\n\nKeep the analytical evidence fixed during editorial changes. Preserve manual\nedits when revising a publication, verify the candidate and source drift, remove\nonly resolved comments, and publish only to the authorised target with rollback.\nWhen data\u002Fscope\u002Fwindows change, rebuild dependent views and produce a reconciled\nbridge against the previous approved evidence.\n\n## References and rehearsal\n\n| Read | When |\n|---|---|\n| [Scope contract](reference\u002Fscope-contract.md) | Intake, readiness and discovery-to-approved reporting |\n| [Review and precedence](reference\u002Freview-and-precedence.md) | Keywords, review packs, exact decisions and rule changes |\n| [Comparisons](reference\u002Fcomparisons.md) | Matched cycles, denominators, organisational\u002FPQ lenses and refreshes |\n| [Evaluation scenarios](reference\u002Fevaluation.md) | Checking routing, safeguards and publication boundaries |\n| [Fabricated audit rehearsal](examples\u002FREADME.md) | Exercising classification, reconciliation, privacy and partial periods locally |\n\nNever transfer an engagement's aliases, dates, targets, exclusions, personal\nnames or data into the public skill. The example's vocabulary and calendar are\nfictional choices that must not become defaults for another organisation.\n",{"name":5,"metadata":52,"description":54},{"version":53},"1.0.0","Analyse collaboration around a named business process, such as an annual audit, financial close, planning cycle or review programme, using Viva Insights Meeting Query and optional purpose-specific Person Query exports. Use when defining which process meetings count, reviewing title\u002Fdate rules, comparing matched cycles, explaining changes in volume or meeting format, or refreshing a process report. Owns scope discovery, approved reporting, reconciliation and descriptive interpretation. Do not trigger for Purview audit-log parsing, compliance certification, event-log process mining, generic Copilot dashboards or an unrelated software audit.\n","main","b89c0b14fb73bb1bef2e20a87b4deb16d7b6644a","frontier-analytics\u002Fskills\u002Fviva-insights-process-analysis",2,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fviva-insights-sample-code","https:\u002F\u002Fmicrosoft.github.io\u002Fviva-insights-sample-code\u002F","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-12 22:07:59",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add microsoft\u002Fviva-insights-sample-code --skill viva-insights-process-analysis",{"tool":71,"command":72},"bunx","bunx skills add microsoft\u002Fviva-insights-sample-code --skill viva-insights-process-analysis",{"tool":74,"command":75},"pnpm","pnpm dlx skills add microsoft\u002Fviva-insights-sample-code --skill viva-insights-process-analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fviva-insights-sample-code\u002Fblob\u002Fmain\u002Ffrontier-analytics\u002Fskills\u002Fviva-insights-process-analysis\u002FSKILL.md",true,[79,85,91,95,101,107,111,115,119,123],{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"examples\u002Ffixtures\u002Fsynthetic-audit-cases.csv","ASSET","资产文件",1336,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fviva-insights-sample-code\u002Fblob\u002Fmain\u002Ffrontier-analytics\u002Fskills\u002Fviva-insights-process-analysis\u002Fexamples\u002Ffixtures\u002Fsynthetic-audit-cases.csv",{"path":86,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":89,"sourceHtmlUrl":90},"examples\u002Ffixtures\u002Fsynthetic-audit-policy.json","REFERENCE","参考文档",509,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fviva-insights-sample-code\u002Fblob\u002Fmain\u002Ffrontier-analytics\u002Fskills\u002Fviva-insights-process-analysis\u002Fexamples\u002Ffixtures\u002Fsynthetic-audit-policy.json",{"path":92,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":93,"sourceHtmlUrl":94},"examples\u002FREADME.md",2217,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fviva-insights-sample-code\u002Fblob\u002Fmain\u002Ffrontier-analytics\u002Fskills\u002Fviva-insights-process-analysis\u002Fexamples\u002FREADME.md",{"path":96,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":99,"sourceHtmlUrl":100},"examples\u002Frun_classifier.R","OTHER","其他",2489,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fviva-insights-sample-code\u002Fblob\u002Fmain\u002Ffrontier-analytics\u002Fskills\u002Fviva-insights-process-analysis\u002Fexamples\u002Frun_classifier.R",{"path":102,"resourceType":103,"resourceTypeDesc":104,"sizeBytes":105,"sourceHtmlUrl":106},"examples\u002Frun_example.py","SCRIPT","脚本",7342,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fviva-insights-sample-code\u002Fblob\u002Fmain\u002Ffrontier-analytics\u002Fskills\u002Fviva-insights-process-analysis\u002Fexamples\u002Frun_example.py",{"path":108,"resourceType":103,"resourceTypeDesc":104,"sizeBytes":109,"sourceHtmlUrl":110},"examples\u002Ftest_examples.py",3595,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fviva-insights-sample-code\u002Fblob\u002Fmain\u002Ffrontier-analytics\u002Fskills\u002Fviva-insights-process-analysis\u002Fexamples\u002Ftest_examples.py",{"path":112,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":113,"sourceHtmlUrl":114},"reference\u002Fcomparisons.md",4680,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fviva-insights-sample-code\u002Fblob\u002Fmain\u002Ffrontier-analytics\u002Fskills\u002Fviva-insights-process-analysis\u002Freference\u002Fcomparisons.md",{"path":116,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":117,"sourceHtmlUrl":118},"reference\u002Fevaluation.md",4038,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fviva-insights-sample-code\u002Fblob\u002Fmain\u002Ffrontier-analytics\u002Fskills\u002Fviva-insights-process-analysis\u002Freference\u002Fevaluation.md",{"path":120,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":121,"sourceHtmlUrl":122},"reference\u002Freview-and-precedence.md",3478,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fviva-insights-sample-code\u002Fblob\u002Fmain\u002Ffrontier-analytics\u002Fskills\u002Fviva-insights-process-analysis\u002Freference\u002Freview-and-precedence.md",{"path":124,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":125,"sourceHtmlUrl":126},"reference\u002Fscope-contract.md",3703,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fviva-insights-sample-code\u002Fblob\u002Fmain\u002Ffrontier-analytics\u002Fskills\u002Fviva-insights-process-analysis\u002Freference\u002Fscope-contract.md",[128,153,174],{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":137,"publishedAt":47},"01M7185J2TZH96E9QHEJ543QNQ","viva-insights-copilot-dashboards","Reproduce and customise the Viva Insights Consumption and Ways of Working or Developer Experience and Copilot reference dashboards with reusable R code. Use for building either demo, adapting Consumption or GitHub query exports into these dashboards, or changing their layout, grouping or periods. Do not use for general Person Query analysis, unrelated dashboards, direct GitHub API analytics, or causal impact estimation.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fviva-insights-sample-code\u002Fblob\u002Fmain\u002Ffrontier-analytics\u002Fskills\u002Fviva-insights-copilot-dashboards\u002FSKILL.md",[134],{"categoryNo":135,"categoryName":136,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师",[138,27,40,29,139,140,141,142,143,144,145,146,147,148,149,36,28,150,151,152],"dashboards","viva insights copilot dashboards","with","do","for","general","grouping","estimation","impact","use","either","reusable","code","api","demo",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":47},"01M7185DF5PSDCP8JCM8W1Q39K","viva-insights-causal-analysis","Assess and analyse exposure-outcome relationships in Viva Insights Person Query exports using design-first panel diagnostics. Use when an analyst asks whether a workplace behaviour, Copilot metric or intervention affects another metric or a supplied organisational outcome, or requests within-person, prior-outcome, placebo or sensitivity comparisons. Verify actual outcome measurement frequency before using repeated organisational attributes as panel outcomes. Supports R and Python guidance with bounded synthetic examples. Do not use for routine descriptive dashboards, prediction-only tasks, arbitrary metric-pair scans or pipeline validation. An explicit request for the existing Copilot Causal Toolkit follows that toolkit's workflow.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fviva-insights-sample-code\u002Fblob\u002Fmain\u002Ffrontier-analytics\u002Fskills\u002Fviva-insights-causal-analysis\u002FSKILL.md",[],[160,27,28,29,161,162,163,164,165,166,167,168,169,40,170,171,172,37,173,36],"viva insights causal analysis","routine","request","outcome","analyst","analyse","synthetic","tasks","attributes","pipeline","prediction","design","only","workflow",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":191,"publishedAt":47},"01M718599CJA70YB2VYD5NXTV9","viva-insights-analysis","Analyze Microsoft Viva Insights data with the open-source vivainsights R and Python packages. Use this skill whenever working with Viva Insights query exports (Person Query, Meeting Query, Consumption query, GitHub query, person-to-person or group-to-group network queries) or the vivainsights packages: importing and validating a query, computing metrics, segmenting Copilot usage (including experimental usage archetypes), building the standard visualisations, running network or information-value analysis, building a common deliverable (adoption dashboard, executive summary memo, ROI estimate), and avoiding the well-known export data pitfalls (IsManager strings, \"#N\u002FA\" text, non-English locales, privacy thresholds, trailing-window metric plateaus, holiday weeks). It also points to the viva-insights-sample-code repo and its Frontier Analytics toolkit for ready-made prompts, starter kits, and schema docs.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fviva-insights-sample-code\u002Fblob\u002Fmain\u002Ffrontier-analytics\u002Fskills\u002Fviva-insights-analysis\u002FSKILL.md",[180,185,188],{"categoryNo":181,"categoryName":182,"taxonomyType":183,"taxonomyTypeDesc":184},"01JBSEEDCAT000000000000013","分析与可视化","SCENARIO","使用场景",{"categoryNo":186,"categoryName":187,"taxonomyType":183,"taxonomyTypeDesc":184},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":189,"categoryName":190,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000033","数据分析师",[27,192,29,28,193,194,195,196,40,197,198,199,36,150,200,201,202,203,204,205],"viva insights analysis","text","ready","strings","executive summary","open","archetypes","information","common","analyze","english","packages","sample","dashboard"]