agentleFS
Sign inStart free
indranilbanerjeeindranilbanerjee/digital-marketing-pro/skills/email-sequence/SKILL.md

email-sequence

Skill873 starsChanged 9 months agoMITView on GitHub

Design an ESP-ready email sequence: subjects, copy, timing, branching, deliverability. \"build a welcome sequence\"

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 74 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write each email: subject line (2-3 options), preview text, body copy with clear CTA

    line 29
  2. Distinctive:

    Add personalization tokens and dynamic content recommendations

    line 32

“Common” is measured: kept by at least 6 in 10 of the 74 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/digital-marketing-pro:email-sequence

Purpose

Design a full email sequence ready for implementation in any ESP. Includes subject lines, preview text, body copy, send timing, segmentation rules, and deliverability best practices.

Input Required

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

  • Sequence type: Welcome, nurture, onboarding, re-engagement, cart abandonment, post-purchase, event, promotional
  • Goal: What the sequence should achieve (activate, convert, retain, upsell, educate)
  • Audience segment: Who receives this sequence and entry trigger
  • Number of emails: Desired count or let the system recommend
  • Key messages/offers: Core value props, promotions, or content to include
  • Existing ESP: Platform in use (Klaviyo, Mailchimp, HubSpot, etc.) for format guidance

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 and relevant category files. Check for custom templates at ~/.claude-marketing/brands/{slug}/templates/. 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. Map the sequence to the customer journey stage and define the narrative arc
  3. Determine optimal email count and send cadence based on sequence type
  4. Write each email: subject line (2-3 options), preview text, body copy with clear CTA
  5. Define segmentation and branching logic (open/click triggers, conditional paths)
  6. Apply deliverability checks: spam trigger words, link density, image-to-text ratio, authentication reminders, and the bulk-sender checklist below
  7. Add personalization tokens and dynamic content recommendations
  8. Review full sequence for brand voice consistency and regulatory compliance (CAN-SPAM, GDPR)

Bulk-sender deliverability checklist (Gmail / Yahoo / Outlook)

Any brand sending at bulk volume (~5,000+ messages/day to a mailbox provider) must meet the mailbox-provider sender requirements or mail is throttled or rejected. Bake these into the sequence's implementation notes (ported from /digital-marketing-pro:send-email-campaign, with Outlook 2025 added):

  • Authenticate the sending domain: SPF and DKIM and a published DMARC policy (at least p=none, aligned) — required by Gmail & Yahoo (Feb 2024) and Microsoft Outlook / Outlook.com (rolling out through 2025 for senders ≥5,000/day).
  • One-click unsubscribe: include the List-Unsubscribe header with one-click support (RFC 8058), and honour opt-outs within 2 days. A visible unsubscribe link in the body is still required in addition.
  • Keep the spam-complaint rate under 0.3% (measured in Google Postmaster Tools / Yahoo / Microsoft SNDS) — ideally under 0.1%.
  • Send from a consistent, PTR/reverse-DNS-valid IP over TLS, with a warmed-up sending domain and consistent from-address.
  • Physical mailing address + accurate From/Reply-To identity in every message (CAN-SPAM), and documented opt-in consent per jurisdiction (GDPR / CASL).
  • List hygiene: suppress hard bounces and inactive addresses; never send to purchased lists.

For per-type email counts and cadence, the per-email blueprint, branching/exit/suppression rules, the per-email deliverability checklist, the deliverable layout, and the after-sequence follow-up menu, read sequence-blueprint.md beside this file.

Output

A complete email sequence containing:

  • Sequence overview with goals, audience, and trigger conditions
  • Per-email breakdown: subject lines, preview text, body copy, CTA, send timing
  • Segmentation and branching logic diagram
  • Deliverability checklist per email
  • Personalization and dynamic content recommendations
  • Compliance checklist (unsubscribe, physical address, consent)
  • Performance benchmarks to measure against

Agents Used

  • content-creator — Email copy, subject lines, narrative arc, CTA strategy
  • brand-guardian — Voice consistency, compliance review, regulatory checks
  • email-specialist — Deliverability optimization, send timing strategy, subject line scoring, spam risk analysis, A/B test design

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free