AgentStack
SKILL verified MIT Self-run

Agentic Commerce Audit Images Alt

skill-commerce-agentic-agentic-commerce-skills-agentic-commerce-audit-images-alt · by commerce-agentic

Image alt-text coverage audit. Critical for vision-language AI agents (Gemini, GPT-4V, Claude) that parse product listings via image understanding.

No reviews yet
0 installs
10 views
0.0% view→install

Install

$ agentstack add skill-commerce-agentic-agentic-commerce-skills-agentic-commerce-audit-images-alt

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Agentic Commerce Audit Images Alt? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Purpose

Vision-language AI agents (GPT-4V, Gemini 2.5, Claude with vision) decide whether to recommend products partly by reading image alt text. Products with missing or generic alt text ("image1.jpg", "product photo") are systematically deprioritized.

This skill audits alt-text coverage on every product image and ranks products by their image-dimension penalty in the Agentic Commerce Spec score.

Prerequisites

  • Authenticated Shopify CLI session: shopify auth login --store
  • API scopes: read_products

Parameters

| Parameter | Type | Required | Default | Description | |-----------|------|----------|---------|-------------| | store | string | yes | — | Store domain | | format | string | no | human | Output format: human or json | | limit | integer | no | 250 | Max products to audit | | mincoverage | float | no | 0.50 | Minimum alt-text coverage ratio to pass (0.0-1.0) | | minlength | integer | no | 5 | Alt text shorter than this is counted as missing |

Workflow Steps

  1. OPERATION: products — query with images + altText fields
  1. For each product:
  • Count total images (filter: type=IMAGE)
  • Count images with descriptive alt text (length >= min_length, not matching generic patterns like ^image\d+|^untitled|^product[\s-]?\d*$)
  • Compute coverage ratio
  1. Bucket products:
  • Critical: 0% coverage AND >= 2 images
  • Warning: coverage = min_coverage
  1. Output ranked report with per-product coverage % and image count.

Safety

> Read-only operation. No mutations.

GraphQL Operations

# products:query — images + altText only
query ImageAltAudit($first: Int!, $after: String) {
  products(first: $first, after: $after) {
    edges {
      node {
        id
        title
        images(first: 25) {
          edges {
            node {
              altText
              url
            }
          }
        }
      }
    }
    pageInfo {
      hasNextPage
      endCursor
    }
  }
}

Companion fix

After this audit, the [agentic-commerce-generate-alt-text](../../catalog-fix/agentic-commerce-generate-alt-text/SKILL.md) skill uses Claude (or any vision model) to generate descriptive alt text from the actual image content + product context, then writes it back to Shopify in one pass.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.