How to use Alt Text for Data Visualizations in your AI agent

What you'll get

This skill helps you write high-quality alt text for data visualizations and images in your R packages or Quarto documents. It follows accessibility best practices to describe charts in a way that makes them understandable to people using screen readers. The skill analyzes your chart code and surrounding text to generate descriptions that capture both what the chart shows and the key insight it communicates.

Step 1 — Get the skill source URL

The Alt Text for Data Visualizations skill lives at:

Step 2 — Add it to your AI agent

Copy one of these prompts and paste it into your AI tool. The agent will fetch and install the skill for you.

Add the agent skill from https://github.com/posit-dev/skills/tree/main/alt-text to my project.

Install this agent skill: https://github.com/posit-dev/skills/tree/main/alt-text

Add this skill to .codex/skills/: https://github.com/posit-dev/skills/tree/main/alt-text

Add the skill at https://github.com/posit-dev/skills/tree/main/alt-text to my .gemini/skills/ directory.

Install this agent skill from https://github.com/posit-dev/skills/tree/main/alt-text

Add this skill: https://github.com/posit-dev/skills/tree/main/alt-text

Step 3 — Try these prompts

Once the skill is installed, ask your AI things like:

• Publishing data visualizations and need to make them accessible to all readers
• You have charts in documentation or articles that need screen-reader-friendly descriptions
• Improve existing alt text to follow current best practices
• Auditing a Quarto document or R package site for accessibility compliance

What this skill does

• Generates alt text for charts in R packages and Quarto documents following accessibility guidelines
• Uses your actual chart code to identify exact variables, data patterns, and visual elements
• Structures descriptions with chart type, data details, and key insights in plain language
• Ensures alt text complements rather than duplicates your existing captions
• Adapts description length and detail based on chart complexity