visualization-choice-reporting_skill

This skill helps you select the right visualization for your data and generate a narrated report with actionable recommendations.

30

GitHub Stars

1

Bundled Files

3 weeks ago

Catalog Refreshed

2 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstart where the catalogue uses aiagentskills.

npx veilstart add skill lyndonkl/claude --skill visualization-choice-reporting

  • SKILL.md14.4 KB

Overview

This skill helps you pick the right visualization for your question and data, then produces a narrated report that highlights key insights and recommends actions. It combines chart selection, perceptual best practices, and a concise narrative framework to turn data into actionable stories. Use it to design dashboards, stakeholder slides, or exploratory analyses with clear next steps.

How this skill works

I clarify the question and profile the data (type, granularity, size, dimensions). I map the question to an appropriate chart family (trend → line, comparison → bar, distribution → histogram, relationship → scatter, composition → treemap) and design the visualization with accessibility and perception principles. I then write a narrative using Headline → Pattern → Context → Meaning → Action and validate results against a simple rubric. The output is a visualization spec plus a short narrated report with recommended actions.

When to use it

  • When you ask “what chart should I use?” or “visualize this” for a dataset
  • When building dashboards or presentation slides for stakeholders
  • When exploring data for trends, distributions, relationships, or composition
  • When monitoring KPIs or preparing a recurring report (weekly/monthly)
  • When you need a clear recommendation based on metrics (growth, churn, ROI)

Best practices

  • Start with a one-line insight headline, not a descriptive title
  • Match question type to chart family and prefer position over angle/area for accuracy
  • Keep Y-axis choices sensible (start at zero for bar/column) and pick appropriate scales
  • Use colorblind-safe palettes, limit hues to 5–7, and add patterns if needed
  • Annotate key points, mute non-data ink, and include source/date and alt text
  • Prefer small multiples or aggregation over cluttered multi-series charts

Example use cases

  • Monthly revenue trend by segment → multi-line chart with annotations and action plan
  • Product A/B test performance → scatter/bubble chart showing effect size and sample size plus recommendation
  • Marketing channel ROI comparison → horizontal bar chart ranked with benchmark lines
  • Customer churn distribution by tenure → histogram or survival curve and retention actions
  • Geographic sales hotspots → choropleth or bubble map with prioritized sales regions

FAQ

Prefer a bar chart for accurate comparison; use a pie only for simple part-to-whole with 2–5 categories and when share intuition is primary.

What if I have many series to show?

Use small multiples, aggregated summaries, or interactive filters; avoid plotting 10+ series on a single static chart.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational