seo-commerce
Skill6 starsChanged 3 months agoApache-2.0View on GitHub
Use when auditing or planning ecommerce search visibility across product/category pages, Product or MerchantListing structured data, Google Merchant Center, Bing shopping feeds, price/availability/shipping/returns parity, IndexNow freshness, or documented AI product-discovery and commerce integrations; require visible-page and feed truth, policy evidence, and no eligibility, ranking, recommendation, or sales guarantee.
In this repository27 other files it gives its agents.
- llms.txtllms.txt
- ai-search-researchSkill
- ai-visibility-monitorSkill
- optimise-seoSkill
- seo-action-planSkill
- seo-aeoSkill
- seo-agenticSkill
- seo-architectureSkill
- seo-auditSkill
- seo-authoritySkill
- seo-competitor-pagesSkill
- seo-contentSkill
- seo-geoSkill
- seo-hreflangSkill
- seo-imagesSkill
- seo-localSkill
- seo-news-discoverSkill
- seo-pageSkill
- seo-performanceSkill
- seo-planSkill
- seo-programmaticSkill
- seo-researchSkill
- seo-schemaSkill
- seo-sitemapSkill
- seoSkill
- seo-technicalSkill
- seo-videoSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Read markdown-delivery-contract.md for every task.
- Distinctive: line 17
Read commerce-evidence-protocol.md before a formal audit.
- Distinctive: line 32
Never invent feed access, merchant diagnostics, product attributes, reviews, stock, price, or eligibility.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Commerce SEO
Markdown delivery contract
Read markdown-delivery-contract.md for every task. Write a substantive .md document for every material work step and register its direct destination in the work index.md. For public-site work, apply the owner-required Markdown discovery profile across the full eligible inventory; preserve native standards and immutable evidence formats.
Lane outputs: commerce-review.md; catalog-parity.md (combine small related steps with stable section links). Project approved product, price, currency, availability, variants, limits and freshness to Markdown from the same catalog revision as HTML/feeds. Exclude private checkout/session data. Dynamic claims need a reliable refresh owner; feeds/protocols keep native formats.
Audit the complete product-discovery system: visible product/category pages, structured data, merchant feeds, change notification, policy fields, and documented AI commerce integrations. Keep every platform-specific control scoped to current primary documentation.
Read commerce-evidence-protocol.md before a formal audit.
Procedure
- Define markets, locales, storefront domains, catalog scope, product identifiers, feed destinations, currencies, inventory systems, and the decision owner.
- Capture representative visible product/category pages, raw/rendered markup, Product/MerchantListing data, canonical/index state, merchant feed rows, platform diagnostics, and update timestamps.
- Reconcile identifiers and buyer-visible facts across page, structured data, and feeds: name, brand, GTIN/MPN/SKU, variants, price/currency, availability, condition, shipping, returns, seller, reviews, and promotions.
- Inspect crawlable navigation, variants, facets, pagination, canonical handling, product retirement, out-of-stock behavior, image/video assets, and sitemap/feed discovery.
- Evaluate Merchant Center, Bing shopping, OpenAI product/merchant data, ACP/UCP, or other commerce capabilities only when the current platform documents the exact integration. Treat protocol discovery as optional capability, not ranking leverage.
- For frequently changing URLs, evaluate IndexNow or platform feed updates with exact changed-URL scope, key verification, rate handling, logs, owner, and rollback. Notification is not an indexing guarantee.
- Separate confirmed defects, platform-recommended opportunities, experiments, and unknowns. Route page markup to
seo-schema, crawl/index issues toseo-technical, query evidence toseo-research, agent task flows toseo-agentic, and measurement toseo-performanceorai-visibility-monitor. - Package production-relevant findings as SEO Findings
1.1.0inseo-findings.json, usingfeed,web_page,template,protocol_capability, or site targets andcommerce/freshnesscategories. Validate beforeseo-action-plan.
Guardrails
Never invent feed access, merchant diagnostics, product attributes, reviews, stock, price, or eligibility. Do not recommend hidden AI-only content, feed-page divergence, fake availability, review markup without visible reviews, or automatic protocol adoption without a documented consumer and owner.
Formal evidence handoff
Package only supported observations as SEO Findings 1.1.0. Let <suite-root> mean ${CLAUDE_PLUGIN_ROOT} in Claude Code. In Codex, read .seo-suite-runtime.json beside this SKILL.md when present and use its suite_root value; otherwise use the absolute repository checkout, then run python "<suite-root>/scripts/validate_seo_findings.py" validate-findings <bundle>/seo-findings.json --bundle <bundle>. Keep the handoff provisional until this command passes.
Output
Return the catalog scope, evidence inventory, page-schema-feed parity table, discovery/freshness findings, policy and protocol decisions, owners, verification, rollback, and limitations. Do not produce a composite commerce score.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

