Accessibility alt text auditor

Skill sisodiabhumca/agent-skills/skills/accessibility-alt-text-auditor

Production-Ready Agent Skills : product analytics, growth experiments, CRM, research synthesis, postmortems, data contracts, SaaS spend, compliance, architecture maps, and LLM eval and many more.

Install

npx -y skills add sisodiabhumca/agent-skills --skill accessibility-alt-text-auditor

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Vendor-neutral skill to audit image alt-text coverage and basic quality heuristics for accessibility.

SKILL.md

1.2 KB, as published. Nobody here has run it

When to invoke

You maintain a website/app content library and want to improve accessibility.
You need an audit of missing or low-quality alt text for images.

Inputs needed

A JSON export of images with fields: page, src, alt.
Optional policy: minimum alt length, banned phrases, whether decorative images may be empty.

Workflow

Validate input records and normalize text.
Score each image:
- Missing alt
- Empty alt (allowed only if decorative)
- Too short / too long
- Generic alt (e.g., “image”, “photo”, file names)
Produce a remediation list sorted by severity.
Summarize coverage and common issues.

Output format

JSON report:
- summary metrics
- issues[] with per-image findings and suggested fix hints

Guardrails

This is a heuristic audit; do not claim WCAG compliance.
Do not fetch remote images or attempt vision-based descriptions.

Reference code

accessibility_alt_text_auditor.py reads image metadata JSON and outputs an audit JSON.