shopify-admin-agentic-…
Edit the theme's robots.txt.liquid to explicitly allow AI crawlers (GPTBot, ClaudeBot,…
Read-only: scans the customer database for malformed emails, role accounts, disposable domains, and bounce-suspect patterns to protect sender reputation.
$ npx -y skills add 40rty-ai/shopify-admin-skills --skill shopify-admin-email-deliverability-audit --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/shopify-admin-email-deliverability-auditContext preview
The summary Claude sees to decide when to auto-load this skill.
Read-only: scans the customer database for malformed emails, role accounts, disposable domains, and bounce-suspect patterns to protect sender reputation.
name: shopify-admin-email-deliverability-audit role: customer-ops description: "Read-only: scans the customer database for malformed emails, role accounts, disposable domains, and bounce-suspect patterns to protect sender reputation." toolkit: shopify-admin, shopify-admin-execution api_version: "2025-01" graphql_operations: - customers:query status: stable compatibility: Claude Code, Cursor, Codex, Gemini CLI
Scans the entire customer list and flags addresses that will hurt email deliverability if included in marketing sends: syntactically invalid addresses, role accounts (info@, admin@, sales@), known disposable / temporary domains, and suspected hard-bounce patterns. Output is a suppression list ready to import into your email platform. Read-only — no mutations.
| Parameter | Type | Required | Default | Description | |-----------|------|----------|---------|-------------| | store | string | yes | — | Store domain (e.g., mystore.myshopify.com) | | marketing_consent_only | bool | no | true | Only scan customers who currently accept marketing — those are the ones at risk of being mailed | | disposable_domains | array | no | built-in list | Override built-in disposable-domain list | | role_localparts | array | no | `["info","admin","sales","support","contact","noreply","help","webmaster","postmaster"]` | Local-part prefixes to flag as role accounts | | format | string | no | human | Output format: `human` or `json` |
> ℹ️ Read-only skill — no mutations are executed. Safe to run at any time. No emails are sent, no marketing consent is changed.
For each customer email, run these checks in order and assign one or more flags:
1. **`invalid_syntax`** — fails RFC 5322 local-part / domain validation, missing `@`, contains whitespace, double dots, leading/trailing dot 2. **`role_account`** — local part exactly matches a `role_localparts` entry (case-insensitive) 3. **`disposable_domain`** — domain matches the disposable-domain list (mailinator, guerrillamail, tempmail-style domains, etc.) 4. **`plus_alias`** — contains `+` in local part (informational; not a deliverability problem on its own, but useful for de-duplication) 5. **`bounce_suspect`** — heuristics: numeric-only local part, length > 64 chars, ALL-CAPS, repeated characters (`aaaaa`), keyboard rolls (`asdfghjk`) 6. **`duplicate`** — same normalized email already seen in the customer set
A customer can carry multiple flags; the most severe (`invalid_syntax` > `bounce_suspect` > `disposable_domain` > `role_account` > `plus_alias`) drives the recommended action.
1. **OPERATION:** `customers` — query **Inputs:** `first: 250`, select `id`, `defaultEmailAddress { emailAddress, marketingState }`, `numberOfOrders`, `tags`, pagination cursor. If `marketing_consent_only: true`, filter `query: "email_marketing_state:subscribed"` **Expected output:** All targeted customers with email; paginate until `hasNextPage: false`
2. Run detection rules over each email; collect flags
3. Aggregate counts per flag, build suppression list
# customers:query — validated against api_version 2025-01
query DeliverabilityAudit($query: String, $after: String) {
customers(first: 250, after: $after, query: $query) {
edges {
node {
id
displayName
defaultEmailAddress {
emailAddress
marketingState
}
numberOfOrders
amountSpent {
amount
currencyCode
}
tags
createdAt
}
}
pageInfo {
hasNextPage
endCursor
}
}
}**Claude MUST emit the following output at each stage. This is mandatory.**
**On start**, emit:
╔══════════════════════════════════════════════╗ ║ SKILL: Email Deliverability Audit ║ ║ Store: <store domain> ║ ║ Started: <YYYY-MM-DD HH:MM UTC> ║ ╚══════════════════════════════════════════════╝
**After each step**, emit:
[N/TOTAL] <QUERY|MUTATION> <OperationName>
→ Params: <brief summary of key inputs>
→ Result: <count or outcome>**On completion**, emit:
For `format: human` (default):
══════════════════════════════════════════════ EMAIL DELIVERABILITY AUDIT Customers scanned: <n> Subscribed customers: <n> ───────────────────────────── Invalid syntax: <n> (<pct>%) 🔴 suppress Role accounts: <n> (<pct>%) ⚠️ suppress Disposable domains: <n> (<pct>%) ⚠️ suppress Bounce-suspect patterns: <n> (<pct>%) ⚠️ review Plus aliases: <n> (<pct>%) ℹ️ informational Duplicates: <n> (<pct>%) ℹ️ informational Recommended suppression: <n> (<pct>% of subscribed) Output: deliverability_audit_<date>.csv ══════════════════════════════════════════════
For `format: json`, emit:
{
"skill": "email-deliverability-audit",
"store": "<domain>",
"customers_scanned": 0,
"flags": {
"invalid_syntax": 0,
"role_account": 0,
"disposable_domain": 0,
"bounce_suspect": 0,
"plus_alias": 0,
"duplicate": 0
},
"recommended_suppressions": 0,
"output_file": "deliverability_audit_<date>.csv"
}CSV file `deliverability_audit_<YYYY-MM-DD>.csv` with columns: `customer_id`, `email`, `flags`, `recommended_action`, `marketing_state`, `order_count`, `total_spent`, `created_at`
`recommended_action` is one of: `suppress`, `review`, `keep`.
| Error | Cause | Recovery | |-------|-------|----------| | `THROTTLED` | API rate limit exceeded | Wait 2 seconds, retry up to 3 times | | Customer with no email | Phone-only / POS account | Skip, do not include in suppression list | | Disposable list out of date | N
Community-maintained AI agent skills for operating Shopify stores — workflows, optimization, reports and more
Edit the theme's robots.txt.liquid to explicitly allow AI crawlers (GPTBot, ClaudeBot,…
Rewrite thin product descriptions into structured, fact-rich copy (materials, fit, use-cases,…
Generate and set descriptive alt text on product images so AI agents (which can't 'see'…
Generate and publish an /llms.txt guide (brand summary, flagship products, key policies,…
Define and populate agentic-commerce metafields (material, attributes, key features, specs,…
Inject an Organization JSON-LD block (name, logo, sameAs social links, contactPoint) into the…