Visualization Builder
Picks the right chart for what you're trying to say, then strips out every element that doesn't serve that one message.
Overview
Visualization Builder helps you choose the right chart type for a message, fix a chart that's cluttered or misleading, or build consistent, branded, accessible visuals for a report or dashboard.
What it covers
- Classifies the chart's message type (comparison, trend, composition, distribution, or relationship) since that determines the chart type.
- Confirms the data is aggregated at the right grain before it ever reaches the chart library.
- Builds the base chart with pre-set professional styling and deliberate axis, tick, and scale choices.
- Applies visual hierarchy so the most important element is dominant, and removes anything that doesn't serve the message.
- Titles the chart with the actual finding, annotates key points directly, and exports at the right resolution for print or web.
Part of Data Analytics Skills
This is one of 31 skills in the Data Analytics Skills library, in the Data Storytelling & Visualization group.
Installation
- Clone the repo once:
git clone https://github.com/nimrodfisher/data-analytics-skills.git - Copy just this skill:
cp -r data-analytics-skills/04-data-storytelling-visualization/visualization-builder ~/.claude/skills/(or~/.agents/skills/for Codex) - Ask your agent something like "build a chart that shows mobile churn is twice desktop" and it activates on its own.
See the Data Analytics Skills entry for the full library.
Related assets
Frontend Design
Generates distinctive, production-grade UI that avoids generic "AI slop," with bold typography, cohesive color, and precise motion, implemented as real code.
Graphify
Turns a codebase, plus its docs, PDFs, images, and video, into a queryable knowledge graph that a coding agent can traverse instead of grepping raw files, and never guesses silently: every edge is tagged EXTRACTED, INFERRED, or AMBIGUOUS so you know what was found versus inferred.
Caveman
Makes your coding agent answer in a stripped down, high signal style that keeps every technical fact and cuts filler, saving output tokens on chat style questions.