Send Email Campaign

/digital-marketing-pro:send-email-campaign

Script location. If your host does not set ${CLAUDE_PLUGIN_ROOT}, the scripts are in this plugin's scripts/ folder, next to skills/.

Purpose

Create and send a targeted email campaign through the brand's connected email platform with personalization, A/B subject lines, compliance checks, and deliverability monitoring. Handles the full lifecycle from content validation through send execution to post-send monitoring, with tiered risk controls based on recipient list size. Ensures every send passes spam, compliance, and brand voice gates before reaching any inbox.

Execution gate (MANDATORY — cannot be skipped)

1. Present the full preview — recipients / spend / changes / compliance — as an Execution Summary before touching any live system.
2. The user must type yes (or an equivalent explicit approval). ANY other input — ambiguous, implied, partial, or absent approval — cancels the run.
3. Never proceed on ambiguous input. Never auto-retry a failed execution; a failure needs human review before any re-run.
4. Only after the user types yes, record it: python "${CLAUDE_PLUGIN_ROOT}/scripts/approval-manager.py" --brand {slug} --action create-approval --data '{"type":"send-email","platform":"<platform>","content_summary":"<one line from the Execution Summary>","risk_level":"<tier>"}', then python "${CLAUDE_PLUGIN_ROOT}/scripts/approval-manager.py" --brand {slug} --action approve --id {approval_id}. If either command errors, stop and report the error; never work around it with another tool. The record proves the approval step ran for this action; it cannot prove who typed yes.
5. Execute. A write sent through connector_executor.py needs --approval-id and fires only against a matching, unused, unexpired record (see /digital-marketing-pro:execute-action). A write through a connected MCP server tool is outside that code check: it relies on this typed yes and on your host's permission prompt. Afterwards run python "${CLAUDE_PLUGIN_ROOT}/scripts/approval-manager.py" --brand {slug} --action mark-executed --id {approval_id} --data '{"execution_result":"success"}' (or failure).

Input Required

The user must provide (or will be prompted for):

• Email content: Subject line, preview text (40-90 chars), body copy with HTML structure, and primary CTA — or a draft to refine
• Target list or segment: The recipient list name, segment ID, or audience criteria for the send — with confirmation of list hygiene status (last cleaned date)
• Email platform: Which email service to use — SendGrid, Klaviyo, Customer.io, Brevo, or Mailchimp — must have the corresponding MCP server connected
• Personalization fields: Dynamic fields to personalize — first name, company, product interest, last purchase, location, or custom merge tags with fallback defaults for missing data
• A/B variants: Optional — 2-3 subject line or content variants for split testing with desired test percentage (10-50%), test duration, and winning metric (open rate or click rate)
• Send time: Immediate send, scheduled date and time with timezone, or "optimal" to use send-time optimization based on historical engagement data per segment
• Reply-to address: Reply-to email address if different from the default sender configured in the platform
• Sender name and from address: Display name and from address — must match authenticated sending domain (SPF, DKIM, DMARC)
• Unsubscribe handling: Confirm unsubscribe link placement, one-click unsubscribe header compliance (required for bulk senders per Gmail/Yahoo 2024 rules), and preference center link
• UTM tracking: Google Analytics UTM parameters for all links in the email body (source, medium, campaign), or auto-generate based on brand naming conventions
• Suppression list: Any additional email addresses or domains to exclude from this send beyond the platform's global suppression list
• Email template: Optional — platform template ID to use, or build from scratch with the provided content and brand styling
• Preheader text strategy: Whether the preview text should complement, tease, or extend the subject line — affects how the email appears in inbox list view
• Fallback content: Plain-text version of the email for recipients whose clients do not render HTML, or auto-generate from the HTML body

Process

1. Load brand context: Read ~/.claude-marketing/brands/_active-brand.json for the active slug, then load ~/.claude-marketing/brands/{slug}/profile.json. Apply brand voice, compliance rules for target markets (skills/context-engine/compliance-rules.md), and industry context. Also check for guidelines at ~/.claude-marketing/brands/{slug}/guidelines/_manifest.json — if present, load restrictions. Check for agency SOPs at ~/.claude-marketing/sops/. If no brand exists, ask: "Set up a brand first (/digital-marketing-pro:brand-setup)?" — or proceed with defaults.
2. Verify email platform connection: Check which email MCP server is connected and confirm it matches the user's target platform. Verify the sending domain is authenticated (SPF, DKIM, DMARC records). If not connected or not authenticated, instruct the user on setup steps.
3. Score email subject lines: Run email-subject-tester.py on all subject line variants to evaluate length (optimal 30-50 chars), power words, personalization token effectiveness, emoji usage, and predicted open rate. Recommend improvements if any variant scores below threshold.
4. Check spam score: Run spam-score-checker.py to analyze subject lines and body content for spam trigger words, excessive capitalization, exclamation marks, link-to-text ratio, image-to-text ratio, and authentication alignment. Flag any deliverability risks with specific remediation steps.
5. Optimize send time — the ladder: If the user selected "optimal" timing: (a) if the connected email platform offers per-recipient send-time optimization, use THAT — it outperforms any global window (the script's sto_note states the doctrine); (b) if the list has a send log (timestamps + opens + recipients), write it to JSON and run python "${CLAUDE_PLUGIN_ROOT}/scripts/send-time-optimizer.py" --industry {industry} --audience-type {b2b|b2c|mixed} --history {file} for first-party windows ranked by measured open rate with sample sizes; (c) otherwise the same command without --history returns the DATED population baseline (baseline_as_of + capped-at-medium ceiling; stale baselines refuse with exit 3). Factor in the timezone distribution of the recipient list.
6. Build platform-specific payload: Structure the email payload per the target platform's API requirements — consult skills/context-engine/platform-publishing-specs.md for field mappings, template rendering, merge tag syntax (e.g., {{first_name}} vs {first_name}), A/B test configuration parameters, and scheduling API format.
7. Verify list size and consent compliance: Confirm recipient count and segment definition. Check that the list has proper opt-in consent flags for the applicable jurisdiction. Verify unsubscribe mechanism is functional, one-click unsubscribe header is present, physical mailing address is included, and compliance with CAN-SPAM (US), GDPR (EU), CASL (Canada), and any other regulations for the brand's target markets.
8. Score brand voice: Run brand-voice-scorer.py on the email body content to verify alignment with brand tone and messaging guidelines. Flag any copy that deviates from brand standards.
9. Create approval record: Create the record via approval-manager.py --action create-approval with the tiered risk level inside the --data JSON — {"type":"send-email","platform":"<platform>","content_summary":"...","risk_level":"medium"} for fewer than 1,000 recipients, "high" for 1,000-10,000, "critical" for more than 10,000. There is no --risk-level flag; see the Execution gate above for the exact command. Generate a send summary with all campaign details, scores, and compliance status.
10. Present campaign summary: Display the complete summary for user review — subject lines with scores, preview text, recipient count and segment name, send time, personalization preview with sample recipient data, spam score, brand voice score, and compliance checklist. Wait for explicit confirmation.
11. Send test email: On initial approval, send a test email to the user's address (and any additional test addresses) via the MCP server. Ask the user to confirm the test renders correctly across desktop and mobile, personalization tokens resolve, links work, and images load.
12. Execute full send via MCP: After test confirmation, trigger the campaign send through the connected email platform MCP. Handle A/B test split configuration, scheduling, and any platform-specific send options (track opens, track clicks, Google Analytics UTM tagging).
13. Monitor deliverability: After send, poll the platform API at 15-minute intervals for the first hour to track delivery metrics — bounce rate, delivery rate, soft bounces, hard bounces, and spam complaints. Alert the user if bounce rate exceeds 3% or spam complaint rate exceeds 0.1%.
14. Capture early engagement signals: After 1 hour and again at 4 hours, pull open rate and click rate data. Compare against the brand's historical averages for the same segment. If A/B testing, report which variant is leading.
15. Log execution: Run execution-tracker.py to log the send event with timestamp, platform, campaign ID, list size, subject lines, A/B configuration, send time, initial delivery metrics, and compliance verification status. Save an insight about subject line performance for future email strategy optimization.