data-visualization
Data Visualization
This skill enables an AI agent to transform structured data into meaningful visual representations. The agent selects appropriate chart types based on the data and the question being asked, builds publication-quality static charts with matplotlib and seaborn, and creates interactive visualizations with plotly. It follows established data visualization principles to ensure clarity, accuracy, and visual appeal.
Workflow
-
Understand the data and the question. Examine the dataset's structure — how many variables, what types (numeric, categorical, temporal), and what relationship or comparison the user wants to highlight. The question drives chart selection more than the data alone.
-
Select the appropriate chart type. Match the analytical goal to the right visual form. Use bar charts for categorical comparisons, line charts for trends over time, scatter plots for relationships between two continuous variables, histograms for distributions, box plots for spread and outliers, and heatmaps for correlation matrices or dense categorical grids.
-
Prepare the data for plotting. Aggregate, pivot, or reshape the data as needed. Sort categorical axes by value for bar charts. Resample time-series to the right granularity. Ensure no NaN values leak into the plot that would create gaps or errors.
-
Build the visualization with appropriate styling. Apply consistent color palettes, readable axis labels, descriptive titles, and proper legends. Remove chart junk — unnecessary gridlines, borders, and decorations. Use figure sizes that match the intended output medium (report, slide, dashboard).
-
Add context and annotations. Highlight key data points with annotations, reference lines, or shaded regions. Add summary statistics directly on the chart where helpful (e.g., median line on a box plot, trend line on a scatter). Context turns a chart from decoration into analysis.
-
Export or display. Save static charts as PNG or SVG for reports, or render interactive HTML for dashboards and exploration. Set DPI to 150+ for print-quality output.
Supported Technologies
More from seb1n/awesome-ai-agent-skills
summarization
Summarize text using extractive, abstractive, hierarchical, and multi-document techniques, producing concise outputs at configurable detail levels.
23proofreading
Proofread and correct text for grammar, spelling, punctuation, style, clarity, and consistency, with support for multiple style guides and readability analysis.
19note-taking
Capture, organize, and retrieve notes efficiently using structured formats, tagging, and file management for meetings, ideas, research, and daily logs.
18knowledge-graph-creation
Build structured knowledge graphs from unstructured text by extracting entities, mapping relationships, generating graph triples, and visualizing the result.
17data-analysis
Analyze datasets to extract insights through statistical methods, trend identification, hypothesis testing, and correlation analysis.
14technical-writing
Write clear, concise, and accurate technical documentation including API references, user guides, tutorials, changelogs, and architecture docs, tailored to the target audience.
14