MetaClaw visualization-selection

Use this skill when creating charts, plots, or dashboards. Choose the visualization type that best communicates the data relationship before writing any plotting code.

install
source · Clone the upstream repo
git clone https://github.com/aiming-lab/MetaClaw
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/aiming-lab/MetaClaw "$T" && mkdir -p ~/.claude/skills && cp -r "$T/memory_data/skills/visualization-selection" ~/.claude/skills/aiming-lab-metaclaw-visualization-selection && rm -rf "$T"
manifest: memory_data/skills/visualization-selection/SKILL.md
source content

Visualization Selection Guide

GoalChart Type
Compare categoriesBar chart (horizontal if many labels)
Show distributionHistogram, box plot, violin plot
Show trend over timeLine chart
Show correlationScatter plot, heatmap
Show part-to-wholePie (<=5 slices), stacked bar

Principles:

  • Label axes and include units.
  • Use color purposefully — not just for decoration.
  • Avoid 3D charts; they distort perception.
  • Start y-axis at 0 for bar charts (truncated bars mislead).
  • Use a colorblind-safe palette (e.g.,
    viridis
    ,
    colorbrewer
    ).