Skills

Alt Text

Generate and improve accessible alt text for data visualizations and images in R...

Install

npx skills add posit-dev/skills --skill alt-text -g -a claude-code -y
Repository
posit-dev/skills551
Category
Design
Updated
7d ago
License
MIT
Context cost
Mediumabout 1,583 tokens
Runs scripts
No, instructions only

What it does

Generate and improve accessible alt text for data visualizations and images in R packages and Quarto documents. Use when the user wants to add, improve, or audit alt text for figures in a pkgdown site or .qmd files. Activate for requests that mention fig-alt, fig.alt, figure descriptions, or alt text in the context of an R package or Quarto document.

Write Accessible Alt Text

Generate accessible alt text for data visualizations and images in this project.

ARGUMENTS

  • label: (optional) specific figure label or chunk to target
  • file: (optional) specific file to process

Detect project type

Before proceeding, identify the project context and read the relevant reference. Check for a _pkgdown.yml file in the project root to detect a pkgdown site:

ls _pkgdown.yml 2>/dev/null && echo "pkgdown" || echo "not pkgdown"
  • pkgdown site (_pkgdown.yml present) → read references/pkgdown.md
  • Quarto documents (no _pkgdown.yml, .qmd files present) → read references/quarto.md

If the context is still ambiguous, ask the user which format they are working in.

Key advantage: source code access

Unlike typical alt text scenarios where you only see an image, we have access to the code that generates each chart. Use this to extract precise details:

From plotting code:

  • Variable mappings → exact variable names for axes
  • Color/fill mappings → what color encodes
  • Plot type functions → scatter, histogram, line chart, etc.
  • Trend lines or fitted curves → overlaid statistical fits
  • Faceting/subplots → number of panels and what varies
  • Color scales → encoding scheme (sequential, diverging, categorical)
  • Axis labels and titles → customized labels

From data generation code:

  • Random distributions → expected distribution shape
  • Transformations → what was done to data
  • Feature engineering → preprocessing applied
  • Filtering/subsetting → what subset is shown

From surrounding prose:

  • Text before/after the chunk explains the purpose and key insight
  • Chapter context tells you what the figure is meant to teach
  • This is often the best source for the "key insight" part of alt text

Three-part structure (Amy Cesal's formula)

Read the whole SKILL.md on GitHub

More in Design