build-dashboard

Create source-backed analytical dashboards with metric definitions and validation.

488|76|Updated Jun 2, 2026
One-click install
npx skills add https://github.com/openai/role-specific-plugins --skill build-dashboard-openai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: build-dashboard
Source: https://github.com/openai/role-specific-plugins/tree/main/plugins/data-analytics/skills/build-dashboard
Command: npx skills add https://github.com/openai/role-specific-plugins --skill build-dashboard-openai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Build source-backed analytical dashboards that help teams monitor performance, explore drivers, and act on product or business metrics. Use when the user needs a dashboard, scorecard, monitoring view, BI dashboard, MCP artifact dashboard, or Streamlit dashboard with clear metrics, filters, validation, and handoff.

Core Features & Use Cases

  • Define dashboards that present a concise, action-oriented overview for stakeholders.
  • Integrate sources and maintain a consistent data model to support reliable handoffs and repeatable deployments.
  • Provide validation, provenance, and clear handoff artifacts to enable easy collaboration and publishing across BI platforms and in-Codex surfaces.

Quick Start

Create a dashboard brief using the user context, then generate a prototype dashboard layout that answers the primary business questions.

Frequently Asked Questions about build-dashboard

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a source-backed BI dashboard for monitoring performance metrics?▼

A source-backed analytical dashboard is a monitoring view that integrates validated data sources to present a concise, action-oriented overview of performance metrics for stakeholders.

What is the best way to define metrics and layout logic for a Streamlit dashboard?▼

To build a source-backed dashboard, you create a dashboard brief defining metric definitions, layout logic, and data sources, then generate a prototype monitoring view with validation and handoff artifacts.

Can I use this approach to create MCP artifacts and scorecards for stakeholder handoffs?▼

The best way to define metrics and layout logic for a Streamlit dashboard is to start with a dashboard brief that maps primary business questions to specific metric definitions and prototype visualizations.

Does the dashboard generation process include data validation and source provenance checks?▼

Yes, this approach supports creating MCP artifacts, scorecards, and Streamlit apps by providing clear metric definitions, provenance validation, and handoff artifacts for repeatable deployments across BI platforms.

How do I ensure reliable handoffs when sharing analytical dashboards across different BI platforms?▼

Yes, the dashboard generation process explicitly includes data validation and source provenance checks to ensure reliable handoffs and maintain a consistent data model for repeatable deployments.