
Image Alt Text Checker
Reviews HTML images for missing, generic, or misleading alt text and suggests accessible fixes
- Repository
- thedaviddias/Front-End-Checklist
- Stars
- 74,632
- Licence
- MIT
- Files
- 2 files
What it does
When installed, the agent checks the images in a web project for accessibility problems with alt text, the short description screen readers read aloud. It flags images with no alt attribute, filename-style or generic alt values like "image", and links or text-images described poorly, then rewrites them to describe purpose and meaning, using alt="" for decorative images. It also reviews image files, sizing and loading behaviour in code, and explains how to confirm the fix in browser DevTools.
Great for
- Front-end developers auditing a site for WCAG 1.1.1 compliance
- Designers or content editors who want clearer alt text for a page
- Teams preparing an accessibility review before launch
Skip it if
- Projects that need automated scanning across a whole site without a developer reviewing the output, since the agent judges alt text by reading code and may misjudge context
- Generating alt text for images the agent cannot see; the skill works from markup and file names, so descriptions of actual image content may be guesses that need a human check
Try asking
- “Check all the <img> tags in this React project and flag any missing or generic alt text”
- “Rewrite the alt text on my product gallery so it describes what each image shows to a shopper”
- “Which of these images are decorative and should use alt=""?”
- “Review our header logo link and suggest alt text describing where it goes”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 2 original files, the MIT licence and an attribution note.
alt-text.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip alt-text.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip alt-text.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Give the agent access to the actual HTML or component files so it can scan every <img> element rather than guessing.
- Tell it whether images are purely decorative or carry meaning, since it cannot always tell from filenames alone.
- Review the suggested alt text yourself, especially for charts and infographics, and test with a screen reader or DevTools accessibility panel.
What's inside
- references/rule.md
- SKILL.md
Redistributed unmodified from thedaviddias/Front-End-Checklist under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.