data-storytelling-analyst

Name: data-storytelling-analyst
Availability: InStock
Author: organvm-i-theoria

Transforms datasets into narrative visualizations using Python or R charting libraries.

Updated May 16, 2026

Search Tags:#storytelling #data visualization #dashboard #matplotlib #ggplot2 #chart selection #colorblind accessibility

Ready to run

npx skills add https://github.com/organvm-i-theoria/_agent-ontology --skill data-storytelling-analyst-organvm-i-theoria

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: data-storytelling-analyst
Source: https://github.com/organvm-i-theoria/_agent-ontology/tree/main/.agents/skills/data-storytelling-analyst
Command: npx skills add https://github.com/organvm-i-theoria/_agent-ontology --skill data-storytelling-analyst-organvm-i-theoria

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Raw analysis results often fail to communicate insight to stakeholders because charts are poorly chosen, inaccessible, or lack narrative structure. This Skill turns datasets and analysis outputs into clear, audience-appropriate visual stories. ## Core Features & Use Cases - Chart Selection Guidance: Recommends the right chart type (bar, Sankey, violin, waterfall, etc.) based on data relationship, audience, and common pitfalls. - Accessible Visualization Code: Produces commented Python (Matplotlib, Seaborn, Plotly) or R (ggplot2) code using colorblind-safe palettes like Viridis and ColorBrewer. - Narrative Insight Summaries: Structures findings into a Context-Conflict-Resolution flow with annotation and design principles. - Use Case: After an ML experiment run, generate a feature-importance chart with an executive-ready insight summary and accessible color palette for a stakeholder presentation. ## Quick Start Analyze this CSV dataset and create an accessible visualization with a short narrative explaining the key insight for an executive audience.

Frequently Asked Questions about data-storytelling-analyst

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I choose the right chart type for my data?▼

Match the chart to the data relationship: bar charts for category comparison, line charts for trends over time, scatter plots for correlations, histograms for distributions, and Sankey or funnel charts for flows. The chart-selection guide includes a decision tree and avoid-when rules for each type.

What color palettes are safe for colorblind viewers?▼

Viridis is the recommended default for sequential data because it is perceptually uniform and works in grayscale. For categorical data use ColorBrewer Set2 or Tableau 10, and avoid red-green combinations which affect roughly 8% of men.

Should I use Python or R for data visualization?▼

Python with Matplotlib, Seaborn, or Plotly is the default unless R is requested, in which case ggplot2 with the viridis package is used. Both stacks support accessible palettes and the same design principles apply to either.

Why does my chart fail to communicate the insight?▼

Common causes include 3D effects, dual axes, truncated y-axes, rainbow colors, and missing context. Fix these by using 2D charts, starting axes at zero, adding reference lines or benchmarks, and writing titles that state the insight rather than describing the data.

How do I make visualizations accessible beyond color choices?▼

Use redundant encoding by combining color with shape, pattern, or direct labels so meaning does not depend on color alone. Maintain at least 3:1 contrast for data elements and 4.5:1 for text, and test with grayscale and colorblind simulators before publishing.