Skip to main content
skill CX Codex GP ChatGPT official · OpenAI

visualize-data — Codex skill: what it does, how to install

This skill designs, revises, and checks quantitative charts. Use it when an analytical answer needs a clear, defensible visual.

Install into Codex · Skills CLI (Vercel) All methods and platforms ↓
npx skills add openai/plugins --skill visualize-data -a codex
Open on GitHub

What visualize-data does

visualize-data helps choose a chart for the analytical question, define the takeaway, and check whether the visual supports that takeaway. It covers charts used in reports, dashboards, notebooks, slides, widgets, and HTML artifacts.

The skill includes guidance for line, bar, scatter, histogram, boxPlot, heatmap, waterfall, funnel, stackedArea, and other chart families. Before implementation, it calls for a chart contract covering the question, takeaway, data sufficiency, palette, output surface, and fallback. Work Mode inline delivery follows native rendering rules; HTML visuals use native charts in artifact.json.

Install it when Codex or ChatGPT regularly needs to create or review analytical graphics. For a one-off basic plot with no visual QA, the extra workflow may be more than you need.

What it helps with

  • choose a chart for a data relationship
  • check whether a visual supports its conclusion
  • revise a chart that is hard to interpret
  • prepare a visual for a report, dashboard, or HTML artifact
  • test whether the data is sufficient for a chart type

Example prompts for the agent

  • Build a trend chart from `sales.csv` and explain the chart choice.
  • Review this `scatter` chart for hidden patterns or misleading presentation.
  • Prepare a visual for an HTML report and write its chart contract.

How to install visualize-data

1Skills CLI (Vercel)

npx skills add openai/plugins --skill visualize-data -a codex

2Manually: put the files in place

.agents/skills/visualize-data/SKILL.md

For all projects use ~/.agents/skills/

From the same set201

The whole set →
supabase official supabase Guides the agent through database configuration and strict RLS policies in Supabase. CX Codex GP ChatGPT 8installs remotion-render official Remotion Exports videos and static stills from Remotion projects using CLI commands. CX Codex GP ChatGPT 3installs figma-create-new-file official Figma Creates blank Figma, FigJam, or Slides files inside draft folders. It resolves planKey and editor types before invoking Figma MCP tools. CX Codex GP ChatGPT 6installs swiftui-performance-audit official OpenAI Pinpoints SwiftUI runtime issues like frame drops, unresponsive taps, and excessive view body computations. Works code-first and guides Instruments profiling. CX Codex GP ChatGPT 109installs swiftui-liquid-glass official OpenAI This skill helps build and review SwiftUI Liquid Glass interfaces for iOS 26+. Use it when adopting the API or checking fallbacks, interaction, and design fit. CX Codex GP ChatGPT 121installs swiftui-ui-patterns official OpenAI This skill helps build and refactor SwiftUI interfaces, from navigation and state to layouts and controls. Use it for new screens or changes to an existing project. CX Codex GP ChatGPT 114installs swiftui-view-refactor official OpenAI Refactors SwiftUI view files into clean, testable structures with dedicated subview types and proper Observation ownership. CX Codex GP ChatGPT 113installs ios-memgraph-leaks official OpenAI Captures and inspects iOS leaks from a simulator process or .memgraph. Useful for tracing retained objects and checking a fix with before-and-after evidence. CX Codex GP ChatGPT 1,054installs

Similar

Questions about visualize-data

How do I install visualize-data in Codex?

Run npx skills add openai/plugins --skill visualize-data. The skill file is placed at .agents/skills/visualize-data/SKILL.md.

What does visualize-data do?

It selects a quantitative chart for the analytical question, helps define the takeaway, and checks whether the visual is readable and analytically sound.

Which chart types does visualize-data cover?

Its guidance covers line, bar, pie, scatter, histogram, boxPlot, heatmap, waterfall, funnel, stackedArea, and leaderboard. The choice depends on the data relationship and visual task.

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor