Related Skills

Use $create-data-context only when the dashboard work explicitly asks to save data context or create, update, inspect, or repair a semantic layer.

Use $analyze-data-quality when dashboard metrics disagree or source freshness, grain, joins, or definitions could affect trust.

Dashboard Building

Use this skill when the user needs a dashboard rather than a report, notebook-only analysis, spreadsheet, or transient chat summary. A good dashboard is summary-first, chart-led, scannable, and organized around what the audience needs to monitor, understand, or act on.

Clarify with the user when a missing input would materially change the dashboard brief, analysis, or recommendation. Otherwise make a reasonable assumption, state it, and proceed.

This skill owns the dashboard brief, delivery-mode selection, metric definitions, source expectations, layout logic, dashboard QA, and handoff. Delivery-specific mechanics belong in the selected dashboard specification.

Skill Configuration

Runtime Delivery Routing

If surface = chatgpt_web and mode = work_mode are both positively identified, do not select the Data Analytics MCP artifact app and do not load its dashboard specification. If mode = work_mode is positive and surface is unknown or otherwise not positively codex_desktop, apply the same non-MCP delivery rule for safety. Use a connected BI destination when the user selected one or it clearly owns the requested dashboard; otherwise build portable HTML. Use Streamlit only when the user explicitly asks for it. MCP servers and other callable tools remain valid data sources.