Back to Skills Marketplace
Skill pack

Data Visualization Designer

Create evidence-backed charts, graphs, chart specs, and presentation-ready visual artifacts from tables, CSV/XLSX data, and Deep Research evidence.

v0.1.0 1 skill By Kendr chartsgraphsvisualizationdatapresentationpowerpointresearchevidence
Publisher docsHosted archive

How to use it

  1. Open Kendr Desktop.
  2. Go to Skills, then Marketplace.
  3. Search for Data Visualization Designer or data-visualization-designer.
  4. Install the pack, then enable the pack or individual skills you want available in agentic mode.

Kendr Desktop compares the installed version with the hosted catalog version and offers an update when this pack changes.

Install source

Use this hosted archive when installing or updating the pack from Kendr Desktop.

https://api.kendr.org/api/skills/packs/data-visualization-designer/archive

Data Visualization Designer

Create evidence-backed charts, graphs, chart specs, and presentation-ready visuals from research evidence, markdown tables, CSV/XLSX data, or structured numeric data.

Data Visualization Designer

Use this skill when the user asks for charts, graphs, plots, visualizations, dashboards, presentation visuals, chart specs, or visual summaries of numeric or structured data.

Workflow:

  • Identify the exact evidence table, CSV/XLSX range, markdown table, or structured data that supports the visual.
  • Choose the chart type by comparison task:
    • Bar chart for category comparisons and rankings.
    • Line chart for time series.
    • Scatter plot for relationships between two numeric variables.
    • Heatmap for matrix comparison.
    • Funnel for staged conversion/drop-off.
    • Timeline for dated events.
  • Keep charts evidence-first: do not invent missing numbers, units, dates, categories, or labels.
  • Preserve the source data used to render the chart as CSV or JSON next to the visual artifact.
  • Include title, subtitle or note, axis labels, units, source/provenance, and accessible colors.
  • Prefer PNG for PowerPoint/DOCX compatibility, SVG for scalable web/report output, and JSON/Vega-Lite-style specs for reproducibility.
  • For slide decks, use one high-signal chart per slide and pair it with a short interpretation, not a dense report paragraph.

Quality checks:

  • Confirm every plotted value is traceable to a provided table, source, or explicit calculation.
  • Avoid truncated axes unless the chart explicitly labels the baseline choice.
  • Avoid 3D effects, decorative gradients, unlabeled axes, tiny legends, and overloaded series.
  • If data is too thin or qualitative, produce a table, timeline, or evidence matrix instead of forcing a numeric chart.

When deterministic rendering is needed, use scripts/render_chart.py with a JSON chart spec containing title, chart_type, x_field, y_fields, and data.