agentleFS
pabloirracionalpabloirracional/claude-skills/skills/building-email-sequences/SKILL.md

building-email-sequences

Skill0 starsChanged 4 months agoMITView on GitHub

Designs and drafts multi-email sequences with explicit timing, branching, exit conditions, and full copy for every email - not just subject line placeholders. Use whenever the user wants an email sequence, drip campaign, onboarding flow, or nurture flow designed or written.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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:

    Map timing and triggers before writing copy: when does each email send, and what event or lack of event triggers it.

    line 13
  2. Distinctive:

    Every email needs a single CTA - if a draft has two calls to action, cut one before it ships.

    line 51

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Building email sequences

Designs a complete sequence: timing, branching logic, exit conditions, and full copy - written out for real, not left as a structural outline.

Workflow

  1. Define the sequence's single goal first - onboarding (activation), nurture (education toward a decision), or re-engagement (win back inactive users). Each needs different pacing and tone.
  2. Map timing and triggers before writing copy: when does each email send, and what event or lack of event triggers it.
  3. Branching logic: define what happens on key actions (clicked vs didn't, activated vs didn't) - a sequence that ignores engagement wastes the data available on the recipient.
  4. One goal per email - stacking multiple asks in one email reduces response on all of them.
  5. Exit conditions: define when a contact stops receiving the sequence (converted, unsubscribed, sequence ended) - open-ended sequences are a common source of unsubscribes.

Worked example: 5-email onboarding sequence

Context: user signed up for a free trial of an automation tool but hasn't connected their first integration yet (concrete scenario, not a placeholder outline).

#TriggerTimingGoalBranch
1Signup completedImmediateWelcome + single next action: connect first integration-
2No integration connectedDay 1, if #1's CTA wasn't clickedRemove friction: show the 2-minute setup, not more featuresIf connected → skip to #4
3No integration connectedDay 3, if still not connectedAddress the likely blocker (unsure which to connect first)If connected → skip to #4
4Integration connectedImmediate on connectionCelebrate + show one concrete result from their own dataIf no second action in 2 days → send #5
5Active but not upgradedDay 6Case for upgrading, tied to their actual usage so farExit: converts, or trial ends

Full copy for Email 2 (the one most sequences leave generic - "just a reminder!" - written out properly instead):

Subject: faltou 1 passo (leva 2 minutos)

Oi {{first_name}},

Você criou sua conta ontem mas ainda não conectou nenhuma integração - sem isso, não tem como o [produto] fazer nada automaticamente ainda.

É rápido: escolhe uma ferramenta que você já usa (CRM, planilha, WhatsApp) e a gente guia o resto.

[Conectar minha primeira integração →]

Se travou em algum passo específico, só responder esse email - a gente resolve junto.

— {{sender_name}}

Why this version, not a generic reminder: names the specific blocker (zero integrations = zero value delivered), keeps the CTA to exactly one action, and offers a low-friction escape hatch (reply to this email) for whoever is stuck on something not covered - a generic "don't forget to finish setup!" doesn't do any of that.

Notes

  • Flag if the described sequence needs list segmentation the user hasn't set up yet - branching logic is only as good as the data available to trigger it.
  • Every email needs a single CTA - if a draft has two calls to action, cut one before it ships.

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.