- name
SKILL.md
स्किल फ़ाइल पब्लिशर की रिपॉज़िटरी में ही रहती है।
कॉपी की गई कमांड टर्मिनल में पेस्ट करें। यह इस SKILL.md को उस एजेंट में इंस्टॉल करती है।
npx skills add CosmoBlk/email-marketing-bible --skill email-marketing-bible -a cursor -yकॉपी की गई कमांड टर्मिनल में पेस्ट करें। यह इस SKILL.md को उस एजेंट में इंस्टॉल करती है।
npx skills add CosmoBlk/email-marketing-bible --skill email-marketing-bible -a claude-code -yकॉपी की गई कमांड टर्मिनल में पेस्ट करें। यह इस SKILL.md को उस एजेंट में इंस्टॉल करती है।
npx skills add CosmoBlk/email-marketing-bible --skill email-marketing-bible -a codex -yकॉपी की गई कमांड टर्मिनल में पेस्ट करें। यह इस SKILL.md को उस एजेंट में इंस्टॉल करती है।
npx skills add CosmoBlk/email-marketing-bible --skill email-marketing-bible -a grok -yकॉपी किया गया संदेश Grok Bot चैट में भेजें। Bot यह SKILL.md GitHub से लाता है और उसे उन स्किल में जोड़ देता है जो आपके सभी Bot साझा करते हैं।
Install this skill: https://github.com/CosmoBlk/email-marketing-bible/tree/HEAD/skills/email-marketing-bibleपब्लिशर से
By George Hartley, co-founder of Nitrosend. Disclosure: Nitrosend is one of the platforms compared in references/platforms.md.
v2.8.4, 12 Nov 2026. Distilled from the EMB guide (19 chapters), from running SmartrMail (~12K customers, 6B emails, sold 2022) and field notes from running an ESP through agents. Rules and gates are here; detail is in
references/, named by the router (§2). Ifreferences/is missing, ask the user to install the full package or paste https://emailmarketingskill.com/llms.txt (then use its URLs verbatim). Otherwise name the chapter and never invent the figure.
Every segment, draft, campaign, flow or staged send on a real ESP is live. Hard gates, never skip:
/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.Account data beats benchmarks. Dated facts (law, inbox rules, vendor features, prices, model names) live in references/ with a Last checked date. If that date is more than about 90 days old, or the answer turns on the fact, verify it live before stating it as current. A benchmark is a starting hypothesis, never a pass/fail gate. Opens are unreliable in both directions: judge on bot-filtered clicks, replies, conversions and revenue per recipient.
Files are in references/.
The marketer moved from operator to director: brief the agent, govern it, own the send button. Advise on the surface the user runs (references/platforms.md).
The loop: read state → reason → act → verify. Read the account first (lists, flows, recent campaigns, deliverability, suppressions), act on one thing, verify it.
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. Measure AI optimisation with holdouts, never last-touch credit (guardrails in references/measurement.md).
Silent failure is the real risk (a flow that quietly stops, caught days later). Where the ESP offers failure webhooks or events (flow paused, sending paused, domain verification lost), subscribe to them; otherwise schedule a recurring health digest of flows not fired, flows erroring, metrics dropped.
Run it before you stage, schedule or activate anything beyond a seed test. Confirm every line in the packet, then wait for approval (§0).
Compliance first. (1) Type: transactional, lifecycle, marketing, newsletter or cold? (2) Recipient region? (3) Consent basis for this audience and this content, including buyers? (4) One-click unsubscribe and physical address present? (5) Suppressions applied? (6) Content materially accurate, with deadlines, scarcity and discounts real (the calendar honours the deadline, the stock limit exists, the discount is the checkout price)? Any unclear answer: refuse or ask. AI does not transfer liability: you own an agent's sends, so re-check the footer and unsubscribe after every template edit.
hrefSlop costs trust: 40% of US consumers would trust a retailer's emails less if they knew AI wrote them (Validity, Jun 2026) [vendor].
Design inputs first. Before the first compose, gather two or three screenshots of the brand's best emails or landing page, the brand document, the logo in light and dark variants, and a folder of approved real images. Name the images to use in each email. After any brand-kit scrape, read it back (logo, brand name, colours, footer, social links, dark-mode logo) and fix it before the first draft. A site on a store or link-in-bio platform can hand the scrape that platform's branding. Context beats prompt: feed the brand kit, design tokens, a tested module library and a rules file before iterating on wording.
AI defaults to competent and generic; force it off its defaults.
role="presentation" tables and dark-mode-safe colours (~#121212, never pure #000 backgrounds or #fff logos).Direct the agent: Discover, Define, Deliver. Adapted for email from Anshu Chimala, "How to turn your AI into a world-class designer" (Lenny's Newsletter, 1 Sep 2026, https://www.lennysnewsletter.com/p/how-to-turn-your-ai-into-a-world) via the design-director skill. LLMs predict the median; divergence has to come from outside the model. Method (full in references/design.md): seed strings inside the brand tokens; 12-20 one-line directions, one picked by the human, brief approved before any image or code; ambitious briefs; a fresh-context critic loop to 9/10, four rounds at most; delivery by subtraction.
Model roles. Critic: the strongest vision-capable model you can reach, in a fresh context. Implementer: your coding agent. Stills and motion: the current image and video models. Names and dates: references/models.md.
The first three are ESP mechanics (check your ESP's equivalent); the rest hold anywhere.
if_version); on conflict, re-read and retry with the fresh version, never guess.href, give Liquid merge defaults single quotes; inner double quotes close the attribute and break the link.Full guide: https://emailmarketingskill.com (chapter URLs: llms.txt, above). references/sources.md says which chapter answers what. Where a chapter and a reference disagree, the reference wins.
01-fundamentals, 02-building-your-list, 03-segmentation-and-personalisation, 04-the-emails-that-make-money, 05-copywriting-that-converts, 06-design-and-technical, 07-deliverability, 08-testing-and-optimisation, 09-analytics-and-measurement, 10-compliance-and-privacy, 11-industry-playbooks, 12-choosing-your-platform, 13-cold-email-and-b2b-outbound, 14-whatsapp-business, 15-sms-and-rcs, 16-ai-and-agentic-marketing, 17-company-case-studies, 18-expert-directory, 19-best-email-designs-2026, appendix-a-benchmarks, appendix-b-frequency-guide, appendix-c-calendar, appendix-d-methodology.
>
---name: email-marketing-bibledescription: >---# skills/email-marketing-bible/SKILL.mdFAQ
पब्लिशर से skills/email-marketing-bible/SKILL.md डाउनलोड करें, या पाथ कॉपी करके रिपॉज़िटरी खोलें। PlugMCP स्किल को सूचीबद्ध करता है, फ़ाइल होस्ट नहीं करता।
पब्लिशर इसे https://github.com/CosmoBlk/email-marketing-bible पर रखता है।
Claude, Cursor, Codex और Grok Build वह SKILL.md पढ़ सकते हैं जिसे आप पब्लिशर की रिपॉज़िटरी से जोड़ते हैं। जब आप चैट में स्किल के GitHub फ़ोल्डर का लिंक भेजते हैं, तो Grok Bot उसे इंस्टॉल कर देता है।
| Connect or run an agent, routine or MCP |
| agent-ops.md |
| Lowest scope chosen; gates confirmed |
| Model choice for design | models.md | Roles filled with current names, date checked |
| Go deeper | sources.md, §8 | Chapter named or fetched |