Visualization Expert
Pick the right chart type and dashboard layout so product metrics and research results communicate clearly to users and stakeholders.
Overview
Visualization Expert is an agent skill most often used in Grow (also Build) that recommends chart types, dashboard patterns, and plotting code for clear honest data communication.
Install
npx skills add https://github.com/shubhamsaboo/awesome-llm-apps --skill visualization-expertWhat is this skill?
- Chart selection guide: comparison, distribution, relationship, composition, and time-series patterns
- Four principles: clarity, honesty, simplicity, and color-blind accessibility
- Recommends bar/column, histogram, scatter, line/area—and cautions on pie charts
- Output includes chart rationale plus matplotlib/plotly-oriented code examples and interpretation notes
- MIT-licensed visualization-expert v1.0.0 from awesome-llm-apps
- Four visualization principles: clarity, honesty, simplicity, accessibility
- Five chart-purpose categories in the selection guide
Adoption & trust: 2.9k installs on skills.sh; 114k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have numbers or experiment results but do not know which chart type will communicate the insight without misleading or cluttering the UI.
Who is it for?
Solo builders adding analytics views, writing data-driven launch posts, or refactoring confusing charts in an admin panel.
Skip if: Heavy ML modeling, ETL pipeline design, or teams that already enforce a fixed corporate design system with no chart flexibility.
When should I use this skill?
Use when creating visualizations, choosing chart types, designing dashboards, or when the user mentions data visualization, charts, or graphs.
What do I get? / Deliverables
You get a chart recommendation with rationale, starter plotting code, design practices, and interpretation guidance ready to drop into a dashboard or report.
- Chart type recommendation with rationale
- Example plotting code and interpretation guidance
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Visualization choices matter most when you are interpreting and presenting metrics in Grow, with repeat use while building in-app analytics in Build. Analytics subphase covers funnels, KPIs, and insight delivery—where chart selection, honesty in scales, and accessibility directly affect decisions.
Where it fits
Turn weekly signup and retention CSV exports into a honest trend line instead of a crowded pie chart.
Specify bar vs stacked bar for a billing usage widget in your React admin.
Pick a simple composition chart for a launch thread showing feature adoption without exaggerating slices.
How it compares
Advisory chart-selection skill—not a hosted BI product or auto-dashboard generator.
Common Questions / FAQ
Who is visualization-expert for?
Indie SaaS founders, data-curious developers, and agent users who need quick, principled help choosing and coding charts without a dedicated analytics designer.
When should I use visualization-expert?
In Grow analytics when presenting KPIs; in Build frontend when designing dashboards; anytime you mention charts, graphs, or data visualization in a session.
Is visualization-expert safe to install?
It is guidance-only MIT metadata in the awesome-llm-apps bundle—still review the Security Audits panel on this Prism page before adding to your agent skill path.
SKILL.md
READMESKILL.md - Visualization Expert
# Visualization Expert You are an expert in data visualization and effective visual communication of data insights. ## When to Apply Use this skill when: - Selecting appropriate chart types - Designing effective visualizations - Creating dashboards - Improving existing charts - Presenting data insights visually ## Chart Selection Guide **Comparison**: Bar charts, column charts **Distribution**: Histograms, box plots **Relationship**: Scatter plots, bubble charts **Composition**: Pie charts (use sparingly), stacked bars **Trend over time**: Line charts, area charts ## Visualization Principles 1. **Clarity**: Make data easy to understand 2. **Honesty**: Don't mislead with scales or cherry-picking 3. **Simplicity**: Remove chart junk 4. **Accessibility**: Consider color-blind users ## Output Format Provide visualization recommendations with: - Chart type and rationale - Code examples (matplotlib, plotly, etc.) - Design best practices - Interpretation guidance --- *Created for data visualization and chart selection*