email-marketing-bible – skill Marketing & SEO cho agent AI

Email Marketing Bible

Overview

The Email Marketing Bible turns an agent into an email marketing operator. It covers building automation flows, segmenting audiences, writing and de-slopping copy, directing email design, diagnosing deliverability, and operating an ESP through MCP or connectors behind hard pre-send gates. Part A is the operating manual for when the agent acts; Part B is the dense reference (metrics, flows, deliverability, compliance, platforms, benchmarks and 19 industry playbooks).

Adapted from the official skill at [CosmoBlk/email-marketing-bible](https://github.com/CosmoBlk/email-marketing-bible) (v2.7, 8 Sep 2026, MIT) by George Hartley, co-founder of Nitrosend. It is distilled from a 19-chapter guide built on 908 sources ([nitrosend.com/email-marketing-bible](https://nitrosend.com/email-marketing-bible)) and from running SmartrMail (about 12,000 customers, 6 billion emails). Imported source/usage counts and personal field notes are author claims, not independently verified in this review. Figures are mid-2026; verify anything volatile (inbox rules, ESP features, pricing, model names) before acting.

When to Use This Skill

• Use when building or editing email automation flows: welcome, abandoned cart, browse abandonment, post-purchase, win-back, sunset.
• Use when an agent drives an ESP through MCP, a connector or an API (Klaviyo, Mailchimp, Resend, Nitrosend and similar) to create segments, flows or campaigns.
• Use when diagnosing deliverability: spam or Promotions placement, bounce or complaint spikes, SPF, DKIM and DMARC problems, warm-up and ESP migrations.
• Use when writing, reviewing or de-slopping email copy, subject lines and CTAs.
• Use when directing AI email design or critiquing a rendered email.
• Use when choosing an ESP, pulling benchmarks, checking compliance (CAN-SPAM, GDPR, CASL, Australian Spam Act), or planning cold email, WhatsApp, SMS or RCS.

How It Works

Step 1: Apply the hard gates

Read section 0 before touching a real account. Every segment, draft, campaign, flow or staged send on a live ESP is real, and nothing goes to more than one recipient without explicit human approval in the conversation.

Step 2: Route the task

Use the task router (section 1) to jump to the right section, and gather the listed inputs before acting.

Step 3: Read, reason, act, verify

Read account state first (lists, flows, recent campaigns, deliverability, suppressions), change one thing at a time, and verify it against real counts.

Step 4: Show the pre-send packet and wait

Approval binds the exact content, audience/exclusions, account, sender and timing. Recheck counts/suppressions immediately before dispatch and reauthorize material changes; saving a draft or flow is not permission to activate it. One send cannot be rolled back after delivery; the kill switch only stops queued/future work.

Run the pre-send checklist (section 3), show the packet (preview URL, audience size, suppressions, subject, preview text, send time, sender, unsubscribe, compliance risk) and wait for an explicit "send it".

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 needs monitoring: propose a scoped health digest of flows not fired/erroring and metric drops; create a recurring task only when the user requests or authorizes it.

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 quoting/escaping depends on the renderer. Preserve quoted HTML href attributes, escape the rendered URL appropriately and verify the compiled template; do not remove quotes as a universal fix.
• 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).
• Verify migration suppression completeness from the old ESP’s authoritative export/API, including unsubscribes, complaints and bounces; some CSV exports omit them, others include them.

3. PRE-SEND CHECKLIST

Confirm every line, surface it, wait for "send it".

• [ ] Audience: size and segment logic verified against actual counts (AI segments run over-broad)
• [ ] Suppressions: unsubscribed, bounced, complained, globally suppressed, frequency-capped, open support issue
• [ ] Authentication: SPF/DKIM and DMARC alignment verified for the actual provider; Gmail bulk-sender minimum permits p=none. Tighten enforcement only after legitimate streams are inventoried and aligned
• [ ] One-click unsubscribe (RFC 8058) + physical address present
• [ ] Copy: §4 pass,

… (nội dung đầy đủ có trong gói tải về)