data-visualization · 101-skills — Claude Code skill: charts, colors, install
data-visualization picks the right chart for your data, sets a palette and axis labels, then renders the figure through the belt CLI.
no license 255 installs ★ 31 updated 2026-08-31
npx skills add 101-skills/superpowers --skill data-visualization -a claude-codeWhat data-visualization does
The skill starts with one question: which chart fits the data. Change over time goes to a line, category comparison to bars, correlation to a scatter, distribution to a histogram. A lookup table inside maps each relationship to a chart and names the ones to avoid. Axis rules follow: bars start at zero, both axes carry labels, spare gridlines come off. Titles should state the finding, not describe the table.
Color gets its own section. Five to seven shades at most, one series highlighted, the rest grey. Separate ramps cover sequential and diverging scales, plus a set that stays readable for colorblind viewers. Rendering happens away from your machine: matplotlib code is sent to belt app run infsh/python-executor and a PNG comes back. So you need the belt CLI, added with npx skills add belt-sh/cli, and a belt login session. The skill's allowed tools cover Bash(belt *) only.
Pie charts get called out and mostly rejected: slices are hard to compare, more than five or six categories stop fitting, exact values cannot be read off them. Horizontal bars sorted by value, a stacked bar, or a plain table when precision matters.
What it helps with
- pick a chart type for a table of monthly revenue
- build a palette that colorblind readers can separate
- label axes and annotate the peak value on the figure
- replace a pie chart with sorted horizontal bars
- render a matplotlib PNG through
belt app run
Example prompts for the agent
- Chart revenue by month, highlight the last point and label its value.
- I have six traffic channels, suggest something better than a pie chart and draw it.
- Make a horizontal bar chart of conversion by channel, sorted by value, with numbers on each bar.
How to install data-visualization
1Skills CLI (Vercel)
npx skills add 101-skills/superpowers --skill data-visualization -a claude-code2Manually: put the files in place
~/.claude/skills/data-visualization/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/data-visualization/
1Skills CLI (Vercel)
npx skills add 101-skills/superpowers --skill data-visualization -a codex2Manually: put the files in place
.agents/skills/data-visualization/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add 101-skills/superpowers --skill data-visualization -a cursor2Manually: put the files in place
.cursor/skills/data-visualization/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install 101-skills/superpowers guides/design/data-visualization2Manually: put the files in place
.github/skills/data-visualization/SKILL.md1Skills CLI (Vercel)
npx skills add 101-skills/superpowers --skill data-visualization -a gemini-cli2Platform CLI
gemini skills install https://github.com/101-skills/superpowers --path guides/design/data-visualizationManually: put the files in place
.devin/skills/data-visualization/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add 101-skills/superpowers --skill data-visualization -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about data-visualization
How do I install data-visualization in Claude Code?
Run npx skills add 101-skills/superpowers --skill data-visualization -a claude-code. The skill lands at ~/.claude/skills/data-visualization/SKILL.md.
What does data-visualization do?
It guides chart choice, palette and annotation for data figures, then renders them with matplotlib through the belt CLI.
What do I need before it works?
The belt CLI, installed with npx skills add belt-sh/cli, and a belt login session. Nothing gets drawn until both are in place.
Similar skills
All skills for Design →data-visualization by other authors comes first.