Claude Skills by nodal-data

Capture analytics knowledge from an analyst who is changing roles, leaving, or transferring domain ownership, producing governed ACF context and eval seeds through context-interview. Use only for an intentional knowledge-transfer or analyst-transition request.

Plan and answer business analytics questions against read-only data, grounding interpretations in available ACF, KTX, dbt, documentation, and warehouse evidence. Use for metrics, reports, trends, comparisons, or warehouse questions. Do not use to author context, modify data, or write dbt models.

Challenge a completed analytics answer when the user disputes it or requests a second opinion, testing alternative interpretations and failure hypotheses before upholding it, escalating uncertainty, or handing a correction to analytics-plan. Do not use for routine first-pass verification.

Interview an analyst to build or improve an ACF analytics-context repo, including metrics, entities, caveats, eval seeds, and a five-question test drive. Use for context-layer creation or correction. Do not use for dbt code or continuous eval-harness operation.

Verify answers against a named BI dashboard in the user's local browser, capturing widget values and active filters with extraction tiers. Use for dashboard checks and context-interview Stage 5. Not for general browsing, credentials, or warehouse queries.

Configure Nodal's project-local warehouse, context sources, and optional browser bindings. Use only when the user explicitly asks to set up, configure, reconnect, or diagnose Nodal. Do not invoke for ordinary interviews or analytics questions.

Review analytics SQL and results against an approved plan for metric, filter, grain, join, and time fidelity, then assess plausibility and escalation needs. Use after analytics execution or when asked to audit a query/result. Do not use to define metrics or modify data.