Agent-Ready Store Audit

Before: a well-known coffee brand's Shopify store looks complete in a browser, with prices, variants, Shop Pay and a refund page.

After (excerpt from the skill's report, 3 October 2026):

Score: 77/100. Agents can reach the store and read prices, but can't answer shipping, returns or review questions.
Agent Q&A test: 6/12 answered. Shipping cost/time: Not found on both pages. Returns: Not found (footer link only).
1. Add a "Shipping & returns" block to product pages · Impact: High · Effort: 5 min. Online Store → Themes → Customize → Product template → Add block → Collapsible tab…
2. Write the shipping policy: /policies/shipping-policy has 0 words.

(Store names are left out on purpose. Full test logs are kept internally.)

On a second store (an apparel brand), the audit found product pages with no JSON-LD and the price only in JavaScript. In a browser nothing looks wrong, but an agent reading the page can't quote a price.

ChatGPT, Copilot, Gemini and Google AI Mode now show Shopify products inside their answers (Shopify announced Agentic Storefronts on 24 March 2026). This skill checks your store the way an AI shopping agent sees it, and tells you what to fix first.

You give it: your store URL.
You get: a 0–100 score across 5 areas, an "agent's-eye" test of real buyer questions, the top 7 fixes with the exact Shopify admin path or theme snippet for each, and a short list of conversion blockers that cost you human sales too.

Tested on 4 real public Shopify stores. Final runs: 9, 9, 9.5 and 9 out of 10.

We tested it on 4 real public Shopify stores (coffee, apparel, body care, footwear), in both owner and competitor mode, and scored each run against a written rubric. Final runs scored 9, 9, 9.5 and 9 out of 10. One early run reported a price mismatch that turned out to be a localization artifact. We fixed the script and added a verification rule before shipping.

The tests ran on real public data, never made-up cases, and were scored against a written rubric. A skill in this range ships only when every test scores 8/10 or more.

How we test, what we do not do, and which assistants we ran it on.

• It can't see whether you're opted in to Shopify's Agentic Storefronts / Catalog (it tells you where to check), and it can't see live checkout behaviour or your actual rankings inside ChatGPT.
• A better score removes reasons for an agent to skip you. It doesn't guarantee recommendations or sales.

Works with any assistant that reads SKILL.md skills (Claude, Codex, Gemini CLI, Cursor and others), plus a paste-in prompt version for ChatGPT or any chatbot. We run our release tests on Claude Sonnet and Opus. Use your assistant's strongest model: in our tests, a small, fast model added facts that were not in the source data. The check script needs Python 3 (standard library only) and web access. On claude.ai, turn code execution on; without it the skill falls back to a manual audit and marks the score as estimated.

1. Unzip the download. It holds the agent-ready-store-audit folder, ready-made zips for claude.ai in a claude-ai folder, a README and the licence.
2. Put the agent-ready-store-audit folder where your assistant looks for skills. The generic path is .agents/skills/ (or npx skills add from a folder). Tool-specific paths:
   • Claude Code: ~/.claude/skills/ (or .claude/skills/ inside one project)
   • OpenAI Codex, Gemini CLI, Cursor and others: .agents/skills/ or the skills folder their docs name
   • claude.ai: Customize, Skills, then the plus button, Create skill, Upload a skill, and upload the zip from the claude-ai folder without unzipping it (code execution must be on in Settings, Capabilities)
   • ChatGPT or any chatbot: open the skill's prompt.md, paste it into the chat, then paste your own text or link
   • Steps for each tool, with links to its official docs: how to install Agent Skills
3. Ask for the job in plain words, for example: "Is my store ready for AI shopping agents? It's mystore.com". The skill loads by itself.