agentleFS
email-marketing-skillsemail-marketing-skills/email-marketing-skills/skills/email-lifecycle/SKILL.md

email-lifecycle

Skill1 starsChanged 34 days agoApache-2.0View on GitHub

Design or repair welcome, onboarding, activation, trial-conversion, retention, and winback email flows. Use when users ask for lifecycle automation, drip sequences, trigger rules, stop conditions, or emails after signup; not for one-off copy edits.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read product context, event definitions, existing flows, and the actual first-value action.

    line 12
  2. Very specific:

    Read the worked flow. Create marketing/lifecycle-map.md and a detailed spec for the first priority flow.

    line 22

“Common” is measured: kept by at least 6 in 10 of the 3 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

Lifecycle flows that follow customer state

Read product context, event definitions, existing flows, and the actual first-value action. Ask only for missing entry events or outcomes that change the sequence. File access is useful; no email-provider connection is required to design the flow.

Build a state map

Map anonymous visitor → interested subscriber → signed-up user → activated user → paying user → inactive/cancelled user only where these states exist. Record the authoritative event and timestamp for each transition. A free account is not necessarily a marketing opt-in, and a cancelled subscription is not necessarily an unsubscribe.

Choose the weakest relevant transition based on evidence. Do not schedule an email for every state just to fill a map. Identify necessary account messages separately from marketing flows.

Specify the flow

Read the worked flow. Create marketing/lifecycle-map.md and a detailed spec for the first priority flow. For each message include goal, enrollment trigger, delay/timezone, current-state predicate, exclusions, re-entry policy, copy angle, one CTA, and exit events. Explain why that message belongs there.

Check state immediately before dispatch. Skip setup reminders after setup. Suppress marketing on opt-out, complaint, hard bounce, and any applicable support pause. For outreach, any reply pauses all follow-ups, including out-of-office replies until reviewed. Set a frequency cap across flows; identify which message wins a conflict.

Implement when asked

Use existing app event and queue patterns. An event ID identifies a source event; a stable recipient+flow-version+step identity identifies a message. Persist them. Handle duplicate events and restart without duplicate messages. For an ambiguous sender timeout, reconcile with the provider before retrying. Verify and deduplicate provider callbacks. Never treat opens as a reliable state transition.

Draft copy can use fictional examples clearly labeled as such, but integration tests use synthetic recipients. Keep secrets out of artifacts. Read current official provider docs for live integration. Do not send or deploy unless already authorized for the exact scope.

Acceptance and output

Provide the state map, flow spec, implementation or plan status, and a test matrix: duplicated signup, conversion before reminder, consent change while queued, missing name, repeated scheduling, out-of-order event, and reply before follow-up. Include the event trace and due/skipped decision in each case. Mark simulated versus integrated behavior. Finish with one primary outcome and an observation window.

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.