/email-marketing-bible

name: email-marketing-bible
description: >
  Data-backed email marketing skill for AI agents. Use when building or running
  email automation, driving an ESP from an agent (MCP/connectors), diagnosing
  deliverability, writing or de-slopping email copy, directing AI email design,
  choosing a platform, or pulling benchmarks. Covers flows, segmentation,
  compliance, cold email, WhatsApp, SMS and RCS, and 19 industry playbooks.
license: MIT
metadata:
  author: george-hartley
  version: "2.7"

Email Marketing Bible, Skill Reference

> v2.7, 8 Sep 2026. Distilled from the EMB (19 chapters, 908 sources, https://emailmarketingskill.com), from running SmartrMail (~28K customers, 6B emails, sold 2022) and three months running Nitrosend through agents. > Part A is the operating manual, Part B the reference. Figures are mid-2026; verify anything volatile (inbox rules, ESP features, pricing, model names) before acting.

---

PART A: OPERATING MANUAL

0. AGENT OPERATING RULES

Every segment, draft, campaign, flow or staged send on a real ESP is live. **Hard gates, never skip:**

• **No send or schedule to more than one recipient without explicit human approval in this conversation** ("send it" or equivalent). Single-recipient test sends still need a yes.
• **Preview before asking; show the packet before any send:** preview URL, audience size, exclusions/suppressions applied, subject, preview text, send time, from-name + reply-to, unsubscribe present, compliance risk.
• **Block the send** if authentication is missing, unsubscribe or physical address is absent, complaint rate is at or above 0.1%, consent basis is unclear, or the audience includes suppressed, bounced or complained contacts.
• **Never probe unknown mutating endpoints on a live audience.** `/send`, `/dispatch`, `/trigger`, `/fire`, `/publish` paths can dispatch immediately; if the approve-scheduled path is unclear, ask the human to click it. Test on sandboxes or cloned campaigns with seed lists.
• **Separate the modes.** Transactional, marketing, lifecycle and cold outbound have different rules, domains and consent bases. Never mix them.
• **Log every autonomous action** (segment changed, flow edited, campaign created, send staged) so the human can audit it.

1. TASK ROUTER

| Intent | Go to | Gather first | |---|---|---| | Audit a programme | §2, then the reference | read access, recent sends | | Build a flow | §7 + §2 | model, trigger, audience, offer, exclusions | | Send a campaign | §3 | segment, consent basis, copy, sender, timing | | Diagnose deliverability | §11 | domain, ESP, bounce + complaint rate, recent changes | | Write or de-slop copy | §4 | audience, offer, voice, one real proof | | Design an email | §5 + §16 | brand tokens, archetype, goal | | Pick a platform | §15 | list size, use case, stack, budget, agent-driven? | | Pull a benchmark | Appendix | industry, email type | | Cold outbound | §14 | offer, ICP, domains, volume | | WhatsApp / SMS / RCS | §Messaging | channel, consent basis, region |

2. AI EMAIL AUTOMATION (the operating model)

The marketer moved from operator to director: brief the agent, govern it, own the send button. Most major ESPs now ship a human-gated prompt-to-campaign agent, an MCP server or a Claude/ChatGPT app (§15); advise on the surface the user runs.

**The loop: read state → reason → act → verify.** Read the account first (lists, flows, recent campaigns, deliverability, suppressions), act on one thing, verify it. Opening prompt: "audit my account and tell me what is missing".

**Automate:** send-time optimisation, subject-line variants + A/B, cart/browse triggers, post-purchase cross-sell, first-draft copy. **Keep human:** brand voice, strategy (segment priority, flow order), creative direction, domain and deliverability, the final send.

**Autonomy dial.** Ask mode by default; widen only on narrow, reversible, low-brand-risk tasks, with an undo; read before write access. Supervised autonomy is the production stance. Where "AI optimisation" means bandits reallocating live traffic, measure with holdouts (never last-touch credit) and do-not-optimise constraints (margin, fatigue, complaints, brand safety).

**Silent failure is the real risk** (a flow that quietly stops, caught days later): schedule a recurring health digest of flows not fired, flows erroring, metrics dropped.

2b. FIELD NOTES: RUNNING AN ESP FROM AN AGENT (JUN-SEP 2026)

Three months running Nitrosend's own sending through agents; each rule cost a real mistake. First five are Nitrosend mechanics (check your ESP's equivalent); the rest hold anywhere.

• Optimistic-concurrency version (`if_version`) on every write; on conflict, re-read and retry with the fresh version, never guess.
• Re-assert brand or account before every write batch after idle; MCP context resets silently to the default brand while reporting a deliberate selection.
• Silent-parameter APIs default to send-to-all: pre-flight assert audience id and count, never probe a mutating endpoint on a live audience (one unknown body key mailed 1,003 contacts).
• Liquid merge defaults go unquoted inside `href`; inner quotes close the attribute and break the link.
• Animated WebP rather than GIF for heroes; then fetch the served URL and confirm it still animates (CDN variants can flatten to frame one).
• Set text and button text colours explicitly on every design; theme defaults drift (grey headlines, dark text on a coloured button).
• Decode tracking-wrapped CTA URLs before approving; the wrapper hides the target.
• Never backfill or re-dispatch failed sends without a human order; late sends look worse than none.
• Drafts by default; the literal "send it" in chat is the only thing that fires a blast.
• Every email gets a hero, a live-text headline and one button; secondary content gets inline links.
• Quote tiles come from HTML in headless Chrome, never an image model (garbled type, invented names).
• Migration opt-out state comes from the old ESP's API