🧰 JSON-LD Offer Field Audit
Read-only audit of Product and Offer JSON-LD in pasted HTML — flags missing price, currency and availability, and never invents offer values.
What it does
Paste page HTML (or the <script type="application/ld+json"> blocks). The skill finds Product / Offer (and AggregateOffer) nodes, checks required commerce fields, and returns a pass/fail table. It does not invent prices, currencies or stock status.
Use it when: a product template just shipped and you want a quick structured-data sanity check before QA, or a rich-result preview looks empty.
Works with: Claude Code, Claude.ai (Skills upload), Cursor and Codex. Install the ZIP, then ask your agent to audit the Product/Offer JSON-LD fields in the HTML.
Read-only. It does not fetch live URLs or rewrite markup unless you ask. For social-card tags, use a separate OG/Twitter audit skill.
Output preview
Install
Unzip first. You get a folder named json-ld-offer-field-audit containing SKILL.md.
Claude Code
Put the folder in your personal skills directory, or in the project to share it with your team.
~/.claude/skills/json-ld-offer-field-audit/SKILL.md.claude/skills/json-ld-offer-field-audit/SKILL.mdClaude Code picks up new skills in the current session (run /reload-skills if the skills folder didn't exist when the session started). The skill loads when a task matches its description.
Claude.ai
Turn on code execution (Settings → Capabilities), then go to Customize → Skills, click +, then Create skill → Upload a skill, and select the ZIP. Full guide.
Cursor
Put the folder in your user or project skills directory. Cursor also reads .claude/skills.
~/.cursor/skills/json-ld-offer-field-audit/SKILL.md.cursor/skills/json-ld-offer-field-audit/SKILL.mdCodex
Put the folder in your user or repository skills directory, then restart Codex or run /skills to check it is listed.
~/.agents/skills/json-ld-offer-field-audit/SKILL.md.agents/skills/json-ld-offer-field-audit/SKILL.mdThese are the standard skill locations for each tool. The tools a skill is verified on are listed under “Tested on” above, if any.
Test log
| Date (UTC) | Tool | Model | Run | Result | Checks | Tokens in / out |
|---|---|---|---|---|---|---|
| Nov 4, 2026 | Codex | gpt-5.4-mini | Test | Failed | 1/4
| 0 / 0 |
Each row is a real run recorded by our test runner. For each tool, the latest test run decides whether it appears under “Tested on”. Baseline runs do the same task with no skill installed and never count.