agentsclimarketplace
Sign in

Seo ecommerce

Skill Hainrixz/claude-seo-ai/skills/seo-ecommerce

Conditionally audit and generate e-commerce structured data for product pages — validate Product/Offer (price, priceCurrency, availability), AggregateRating/Review, faceted-navigation canonicalization, and variant/ProductGroup handling, cross-checking page-to-schema-to-Merchant-feed consistency, and produce ready-to-inject Product JSON-LD. Module M18. Feeds both the Search SEO and AI Visibility scores.From its SKILL.md

Install
npx -y skills add Hainrixz/claude-seo-ai --skill seo-ecommerce

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

  • runs commandsInstructs the agent to run 1 command, including `node ${CLAUDE_SKILL_DIR}/../../scripts/validate-jsonld.mjs --url <u>`.

SKILL.md

4.5 KB, ~1.0k tokens by cl100k_base, as published. Nobody here has run it

seo-ecommerce (M18)

Conditional commerce module: it only runs when commerce signals are detected, then audits and completes product structured data. Reference: references/schema-tier1.md (Product + Offer, Review/AggregateRating rows).

Audits

Working from the PageSnapshot (rendered_dom if present, else raw_html):

  1. Commerce gate: detect commerce signals (price/currency text, add-to-cart/buy controls, Product/Offer schema, og:type=product). If none, every M18 finding is not_applicable (severity 0) — do not force product schema onto non-commerce pages.
  2. Product + Offer: Product has name, image; Offer has price, priceCurrency, availability (schema.org/InStock etc.). Per references/schema-tier1.md.
  3. AggregateRating / Review: if ratings are visibly shown, expect AggregateRating (ratingValue, reviewCount/bestRating) and/or Review (author). Never mark up ratings not visible on the page.
  4. Page → schema → feed consistency (Tier 2): schema price/priceCurrency/availability must match visible on-page values and the Merchant Center feed. Mismatches risk disapproval and lost rich results.
  5. Faceted navigation: filter/sort URLs (?color=, ?sort=) should canonicalize to the clean product/category URL or be noindex, to avoid index bloat and duplicate-content dilution.
  6. Variants / ProductGroup: multi-variant products should use ProductGroup with hasVariant and variesBy, not duplicate standalone Product blocks per SKU.

Fixes

  • AUTO (fixable: auto): generate complete, valid Product/Offer/AggregateRating JSON-LD inferred from the DOM (name, image, price, currency, availability, visible rating) inside a single @graph with a stable @id. The block is a diff for fix.
  • PROPOSED (fixable: proposed): canonical/noindex tags for faceted URLs and ProductGroup restructuring — drafts requiring per-item accept.
  • ADVISORY (fixable: advisory): price / availability mismatches between page, schema, and feed — the store backend/feed is the source of truth, so the tool never writes these. Never invent prices, currencies, availability, or ratings — ask the user or leave a clearly-marked TODO placeholder.

Verification

  • Offline: node ${CLAUDE_SKILL_DIR}/../../scripts/validate-jsonld.mjs --url <u> (schema_validator) — JSON validity + required Product/Offer properties.
  • Tier 1: Google Rich Results Test / schema.org validator (rich_results_api) for merchant-listing eligibility.
  • Tier 2: Merchant Center feed diff — compare schema vs feed price/availability. When the required data tier (feed/API) is unavailable, status is needs_api, never a false pass.

Findings

Emit findings per schema/finding.schema.json. Severity 5 on ecommerce pages, 0 (not_applicable) otherwise; axis both. Examples:

  • M18.offer.missing_price — Product without Offer.price/priceCurrency (status fail, severity 5, fixable: auto, axis both, confidence established).
  • M18.offer.price_feed_mismatch — schema price differs from on-page/feed price (status warn, severity 5, fixable: advisory, axis both, confidence directional; needs feed → may be needs_api).
  • M18.facets.uncanonicalized — indexable faceted URLs lack canonical/noindex (status warn, severity 5, fixable: proposed, axis both, confidence directional). Each finding: evidence.observed quotes the page (e.g. the rendered price text or the offending ?filter= URL); verification.reproduce is a runnable command; expected_impact is banded + confidence-tagged (no naked %).

Honesty

  • AggregateRating/Review markup does not guarantee star rich results — Google shows them at its discretion and gates them by policy; don't promise stars from markup alone.
  • Faceted-URL hygiene reduces crawl/index waste but is not a direct ranking factor — frame as directional, not a guaranteed gain.
  • Keep schema strictly consistent with visible content and the product feed; fabricated or feed-mismatched values invite Merchant disapproval, not a win.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most marketing audience skills give in ~1.0k tokens

Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07

  • Apply Poppins font to headingsin 41 of 690, across 6 files
  • Apply Lora font to body textin 41 of 690, across 6 files
  • Use Arial fallback for headingsin 39 of 690, across 4 files
  • Use Georgia fallback for body textin 39 of 690, across 4 files
  • Maintain text hierarchy and formattingin 39 of 690, across 4 files
  • Use accent colors for non-text shapesin 38 of 690, across 3 files
  • Use RGB values for precise color matchingin 38 of 690, across 3 files
  • Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
  • Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
  • Use active voice instead of passive voicein 26 of 690, across 10 files
  • Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
  • Prioritize clarity over clevernessin 22 of 690, across 8 files

Said here and by no other author read

  • emit findings per finding schema
  • run only when commerce signals are detected
  • mark all findings not applicable without commerce signals
  • verify ratings schema matches visible on-page content
  • cross-check page schema and feed consistency
  • canonicalize or noindex faceted navigation URLs

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.