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, person-to-person or group-to-group network queries) or the vivainsights packages: importing and validating a query, computing metrics, segmenting Copilot usage, 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/A" 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.

インストールへ移動

リポジトリ: microsoft/viva-insights-sample-code
ソースの最終更新活動: 2026年8月6日 16:10
検出された SKILL.md の言語: 英語
スター: 14
フォーク: 3

インストール方法

デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。

npx skills add https://github.com/microsoft/viva-insights-sample-code --skill viva-insights-analysis

コマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。

ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。

ソースファイルを確認

インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。

ファイルエクスプローラー

19 ファイル

SKILL.md

ソースの指示 · 読み取り専用プレビュー

検索に戻るインストールに戻る

name

viva-insights-analysis

description

What this skill is for

Microsoft Viva Insights lets analysts export "flexible queries" as CSVs from the Analyst portal. The open-source vivainsights packages (R and Python) read, validate, analyse, and visualise those exports in a consistent, best-practice way.

Use this skill when a task involves any of:

Importing or validating a Viva Insights query export.
Computing or visualising collaboration, meeting, email, focus, after-hours, or Copilot metrics.
Segmenting a licensed population by Copilot usage.
Person-to-person or group-to-group network analysis.
Information Value / driver analysis, key-metrics scans, interrupted time-series.
Debugging why a Viva Insights export loaded or aggregated strangely.
Building a common deliverable such as an adoption dashboard, an executive summary memo, or an ROI estimate, when no Frontier Analytics prompt card is being used for the task. See "How to use the reference files" below.

This skill is customer-agnostic. It contains no organisation-specific paths, scopes, or dates. Adapt column lists, populations, and time windows to the data in front of you.

	R	Python
Package	`vivainsights`	`vivainsights`
Docs	https://microsoft.github.io/vivainsights/	https://microsoft.github.io/vivainsights-py/
Source	`microsoft/vivainsights`	`microsoft/vivainsights-py`
Install	`install.packages("vivainsights")`	`pip install vivainsights`
Coverage	Fuller API (metric-family wrappers, text mining, ITSA, survival)	Core subset (import, identify, viz, IV, network)
Return arg	`return = "plot"` / `"table"` / `"data"`	`return_type = "plot"` / `"table"` / `"data"`

	R	Python
`llms.txt` (machine-readable, task -> function -> privacy note)	https://microsoft.github.io/vivainsights/llms.txt	https://microsoft.github.io/vivainsights-py/llms.txt
Function-discovery guide (human-readable task index)	https://microsoft.github.io/vivainsights/articles/function-discovery.html	https://microsoft.github.io/vivainsights-py/function-discovery.html

File	Read it when you need
`reference/packages.md`	The function inventory, grouped by purpose, with R/Python parity and verified signatures. A curated complement to the live `llms.txt` (see above).
`reference/query-schemas.md`	The shape of each query type (grain, key columns, raw vs imported column names) and the meeting quality filter.
`reference/data-pitfalls.md`	To diagnose or pre-empt a loading / aggregation problem (IsManager, "#N/A", locales, privacy threshold, trailing windows, holidays).
`reference/analysis-conventions.md`	To write honest, defensible claims (association vs causation), segment definitions, and period framing.
`reference/deliverables.md`	To build a standard deliverable (adoption dashboard, executive summary, ROI estimate, usage segmentation) when there is no Frontier Analytics prompt card for the task, or the user wants a faster first pass.
`reference/ecosystem.md`	The canonical upstream: package docs, the sample-code repo, and the Frontier Analytics toolkit to defer to.
`reference/environment.md`	Practical run tips: performant loads, headless plotting, script-file vs inline execution.

viva-insights-analysis

インストール方法

ソースファイルを確認

What this skill is for

The packages at a glance

What this skill is for

The packages at a glance

Find the right function before writing custom code

How to use the reference files

Worked examples

Minimal workflow

Guardrails

viva-insights-analysis

ソース情報

インストール方法

ソースファイルを確認

What this skill is for

The packages at a glance

What this skill is for

The packages at a glance

Find the right function before writing custom code

How to use the reference files

Worked examples

Minimal workflow

Guardrails