Frontier

Frontier — Agent Skills

Choose a Viva Insights agent Skill for analysis, query dashboards, or Person Query causal diagnostics.

Agent Skills for Viva Insights

An agent Skill is a folder containing a SKILL.md file and supporting references. A compatible coding agent can load the Skill when your request matches its description, applying its guidance without you pasting instructions each time. The Skills in this library are for working with Viva Insights exports in R or Python. They are separate from People Skills data analysis.

For a single task without installation, use the Prompt Library. Check your agent’s documentation for Skill support and installation locations.

Choose a Skill

Skill	Use it for	What to expect
Viva Insights analysis	Importing and checking exports, computing and visualising metrics, Copilot usage segmentation, network analysis, and common R or Python deliverables.	Shared analytical conventions and references. Start here for general Viva Insights work.
Copilot query dashboards	Reproducing or customising the Consumption and Developer Experience reference dashboards, or assessing whether real query exports support them.	An optional R-first workflow. Install it alongside Viva Insights analysis from the same checkout revision. The demos are synthetic; real Consumption support is scoped to documented credits, and a real GitHub adapter is not yet verified.
Person Query causal analysis	Checking whether a selected exposure and outcome support within-person analysis and diagnostics.	An optional design-first workflow. Install it alongside Viva Insights analysis from the same checkout revision. Its R and Python examples use fabricated data and are not a general real-data modelling engine.

The two optional Skills read references from the shared analysis Skill. Keep the paired folders intact and from the same revision. For the full list of files and installation instructions, see the Skills guide on GitHub.

Get started

1. Choose the Skill that matches your task and check the installation guide for your agent’s skills directory. For either optional Skill, follow its dashboard or causal-analysis pairing instructions.
2. Keep a local checkout of the sample-code repository when using a workflow that reads its runner or reference assets. Installing a Skill does not install R, Python, or their packages.
3. Open your coding agent and describe your task, data, and intended output. For example: “Assess whether my Person Query and quarterly outcome can support within-person analysis before running models.” Review the agent’s proposed approach and check its results against your actual export.

For one-off dashboard or causal-diagnostics work, you can instead use the dashboard prompts or the Person Query prompt with a local checkout, without installing a Skill. If your agent does not support Skills, the context file is another starting point.

🔒 Responsible use & data privacy

• Suppress small groups. Apply a minimum group-size threshold to every breakdown, segment, and chart — Viva Insights typically uses 5–10. Raise it for smaller organizations.
• Never expose individuals. Do not print raw UPNs or email addresses; hash, truncate, or report only aggregates. Person query PersonId is already de-identified, but Purview UserId is not.
• Analyze groups, not individuals. These outputs are for understanding cohorts and trends — not for evaluating, ranking, or monitoring named employees.
• Keep data in approved environments. Don't paste sensitive HR data into cloud agents unless your organization's policies allow it; prefer local or enterprise-hosted tools. Validate every agent output before sharing.

Back to Frontier · Browse the Skills source