Alt Text
- 9 installs
- 5 repo stars
- Updated August 1, 2026
- ahgraber/skills
alt-text is a Claude Code skill that describes an image, chart, diagram, or screenshot for alt-text, accessibility, and documentation.
About
alt-text is a Claude Code skill that describes an image, chart, diagram, screenshot, or figure so a reader who cannot see it understands both what it depicts and what it communicates. It covers figure type, key elements, relationships, and conclusions, and enforces plain declarative sentences while banning openers like 'image of'. A developer uses it to generate accessible descriptions for documentation or publishing.
- Describes an image, chart, diagram, screenshot, or figure for alt-text and accessibility
- Produces a description detailed enough to reproduce the figure from text alone
- Enforces plain declarative present-tense sentences and bans 'image of' style openers
Alt Text by the numbers
- 9 all-time installs (skills.sh)
- Ranked #1,150 of 1,879 Documentation skills by installs in the Skillselion catalog
- Data as of Aug 2, 2026 (Skillselion catalog sync)
alt-text capabilities & compatibility
- Capabilities
- alt text generation · accessibility · image description · documentation
- Use cases
- documentation
What alt-text says it does
Describe the figure so a reader who cannot see it understands both what it depicts and what it communicates.
The description should be detailed enough that someone could reproduce or redraw the figure from the text alone.
npx skills add https://github.com/ahgraber/skills --skill alt-textAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 9 |
|---|---|
| repo stars | ★ 5 |
| Last updated | August 1, 2026 |
| Repository | ahgraber/skills ↗ |
What it does
Generate accessible alt-text descriptions of images, charts, diagrams, and screenshots.
Who is it for?
Writing accessible alt-text or figure descriptions for images, charts, and diagrams.
Skip if: Describing visual styling like colors or fonts unless it carries meaning.
When should I use this skill?
The user shares an image, chart, diagram, or screenshot and needs it described for alt-text or accessibility.
What you get
A plain, declarative description conveys what the figure depicts and communicates, detailed enough to redraw.
- accessible text description of a figure
By the numbers
- 4 coverage areas (figure type, key elements, relationships, outcomes)
- explicit do-not list of banned openers
Files
Alt-Text
Invocation Notice
Inform the user when this skill is being invoked by name: alt-text.
When to Use
- User attaches an image and asks for a description or alt-text
- User shares a chart, diagram, schematic, or screenshot and wants it explained
- User needs an accessible description for documentation or publishing
If the image is not attached, ask the user to attach it before proceeding.
Instructions
Describe the figure so a reader who cannot see it understands both what it depicts and what it communicates. The description should be detailed enough that someone could reproduce or redraw the figure from the text alone.
Cover, as applicable:
- Figure type and overall structure (e.g., bar chart, flowchart, photograph, schematic)
- Key elements: labels, axes, data values, components, or steps
- Relationships, trends, comparisons, sequences, or hierarchies shown
- Outcomes, conclusions, or emphasis the figure conveys
Write in plain declarative sentences, present tense. End with a period.
Do not:
- Open with "image of," "picture of," "figure of," "graphic of," or similar
- Use phrases like "shown above," "as seen," or "depicted here"
- Describe visual styling (colors, fonts, layout) unless it carries meaning
- Guess at emotions, identities, or intent not clearly conveyed by the figure
Output
Respond with the description only — no preamble, commentary, or metadata.
Related skills
Lark MarkdownInstantly turn any markdown file into clean, formatted Lark/Figma-compatible documents without manual reformatting.488k
Lark DocCreate, read, update, summarize, rewrite and manage Feishu/Lark cloud documents directly from agent workflows.401k16.1kLark WikiCreate, organize, query, and manage documents, spaces, and members inside Lark (Feishu) knowledge bases directly from AI agent workflows.397k16.1k
Domain ModelingBuild and sharpen a project's domain model: pin down domain terminology in a glossary and record architectural decisions as ADRs.318k202k
Opensource Guide CoachGet expert, attribution-safe guidance on launching and sustaining an open-source project.270k71Readme I18nMaintain consistent, updatable language selector blocks across every README variant in a multilingual repository.270k71