Skip to main content
ClaudeWave
ES, Spanish
Skill2.1k estrellas del repoactualizado 10d ago

lifecycle-messaging

Designs automated email and SMS programs — welcome and onboarding sequences, nurture, re-engagement, transactional messaging, and the timing and segmentation behind them. Use this to build or fix an email sequence, plan lifecycle automation, improve open or click performance, set up SMS flows, or decide what messages a customer should receive and when.

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/cbrock84/headcount /tmp/lifecycle-messaging && cp -r /tmp/lifecycle-messaging/plugins/demand-generation/skills/lifecycle-messaging ~/.claude/skills/lifecycle-messaging
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

# Lifecycle messaging

## Map the lifecycle before writing any message

For each stage, name what the person is trying to do and what would move them forward. Messages
written without that answer become announcements, and announcements get unsubscribed from.

The stages that matter: just signed up, activated but not habitual, habitual, at risk, lapsed.
Most programs over-invest in the first and neglect at-risk entirely, which is where the money is.

## The welcome sequence

The highest-engagement messages you will ever send. Do not waste them on company history.

1. **Immediate** — deliver whatever was promised, plus the single next action.
2. **Within days** — the fastest route to first value, one step.
3. **After that** — the use case most people miss, or the objection most people have.

Set expectations early: what you send, how often. It reduces unsubscribes more than any subject-line
technique.

## Timing and cadence

Trigger on behavior, not the calendar, wherever possible. A message sent because someone did
something is many times more relevant than one sent because it is Tuesday.

Cadence sustainable at your worst week. Every message should be one the recipient would miss.

## SMS is a different medium

Higher consent bar, higher intrusion, higher cost. Reserve it for time-sensitive and transactional
messages — delivery, appointment, security, an expiring window. Marketing SMS at any volume trains
people to opt out.

Explicit opt-in, honored opt-out, sending hours respected in the recipient's timezone. These are
legal requirements in most jurisdictions, not preferences.

## SMS compliance is not optional

> Consult qualified counsel before launching an SMS program. The exposure here is statutory damages
> per message, which is how these become class actions.

In the US, marketing SMS requires **express written consent** obtained before sending — implied
consent, an existing customer relationship, or a phone number collected for another purpose does not
qualify. The consent record must show what the person agreed to receive and when, and it must be
retained.

The operational requirements that follow:

- Disclose program purpose, frequency, and that message rates may apply, at the point of consent.
- Honor opt-out immediately, on every standard keyword, with a single confirmation message and
  nothing after it.
- Respect quiet hours in the **recipient's** timezone, not yours.
- Keep consent and opt-out records for as long as the retention rules require — these records are
  the entire defense if challenged.
- Never buy or rent SMS lists. Purchased consent is not consent.

Other jurisdictions impose their own rules, and several are stricter. Determine which apply by where
recipients are, not where you are.

## Subject lines and preview text

They are one unit and get read together. A subject line that works with the preview repeating it
wastes the second-most-read text in the message — use the preview to extend the subject, not echo
it, and never leave it to default to the first line of the body.

## Diagnosing

- **Low open** — subject line, sender reputation, or list quality. Check deliverability before
  rewriting subject lines; a reputation problem looks exactly like a copy problem.
- **Open but no click** — the message did not deliver on the subject, or has no single clear action.
- **Click but no conversion** — the destination, not the email.
- **Rising unsubscribes** — frequency or relevance. Usually frequency.

## Tooling

Lifecycle automation: Customer.io, Braze, Iterable, Klaviyo for commerce, HubSpot or
Marketo for B2B, and similar.

Transactional sending is a separate job with separate reputation: Postmark, SendGrid,
Resend, and similar. Keep it off the marketing domain.

In-product messaging: Intercom, Appcues, Pendo, and similar. An email that should have been
an in-app prompt reaches half the audience at best.

## Never

- Send to a list that did not opt in.
- Bury the unsubscribe.
- Run a re-engagement program without a plan to actually remove the people who do not re-engage. An
  unengaged list damages delivery for everyone else.
account-based-marketingSkill

Concentrates marketing and sales effort on a named set of accounts rather than on volume — qualifying whether the model fits your economics at all, building the account list and the buying group inside each, tiering effort against account value, coordinating so the account experiences one campaign rather than several, and measuring account progression instead of leads. Use this to decide whether to run an account-based program, build one, or work out why an existing one produces activity and no pipeline.

agent-hierarchySkill

Designs orchestrator-and-subagent hierarchies for a repository — splitting agents by exclusive write surface, pairing every producer with an independent auditor, and enforcing the split with a script that runs in CI. Use this whenever the user wants to set up, expand, audit, or fix a multi-agent or subagent structure for a codebase; asks how to divide work between agents; wants agent charters, roles, or a surface map written; or is hitting agents that collide on the same files, review their own work, or drift from their remit. Also use when sizing a roster or deciding whether a new agent is justified.

ai-ml-governanceSkill

Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory exposure, or when deciding whether an AI system is fit for a consequential decision.

ai-research-analystSkill

Produces executive-level research — market sizing, competitor mapping, trend analysis, and strategic intelligence — grounded in cited sources with the confidence in each claim made explicit. Use this to analyze a market or industry, map competitors, evaluate a market-entry or build-versus-buy decision, produce a research brief, or assemble evidence for a decision. Also use when comparing options that need a structured, evidence-based verdict rather than an opinion.

ai-search-optimizationSkill

Optimizes for AI assistants and AI-generated answers — being retrievable, being cited, and being represented accurately when a model answers on your behalf. Use this when traffic is shifting from links to AI answers, when a brand is misrepresented or absent in AI responses, when planning content for retrieval rather than ranking, or when deciding how AI search changes an existing SEO program.

app-store-optimizationSkill

Improves visibility and conversion in the App Store and Google Play — metadata, keywords, screenshots, ratings, and the listing experience that turns an impression into an install. Use this to audit or optimize an app listing, plan a launch listing, diagnose poor install conversion, or improve store search visibility.

backup-and-recoverySkill

Protects and restores data — backup coverage and scope, retention, immutability against ransomware, and proving restores actually work. Use this to design a backup regime, verify restores, plan retention, protect backups from ransomware, or recover from data loss.

budgeting-and-forecastingSkill

Runs the planning cycle — annual budget, rolling forecast, consolidation of business unit inputs, and the variance analysis that explains actuals against plan. Use this to build or challenge a budget, run a forecast cycle, consolidate departmental submissions, explain why results diverged from plan, or improve forecast accuracy.