# Agentic Growth — follow-along guide

Zero to Launch, session 06 · Wed Oct 14, 2026 · 50 min

Two days before the hackathon. Distribution that runs without you, and the one number that decides whether paid works at all.

## Five-minute setup

Do this before the session starts, or in the first ten minutes while the framing happens. Nothing here is required to attend.

**Have an agent installed.** Claude Code, the Codex extension, or whatever you already run. Every skill file below is plain markdown with frontmatter — it works in anything that reads a skills directory.

**Get the skills.** Download this session's bundle and unzip it at the root of your project. It writes into .claude/skills/ and nothing else.

    unzip -o zero-to-launch-06-growth-engineering.zip -d .

**Not sure which skill you need?** Run /ask-santos and describe the problem in your own words. It names one skill, says why that one, and tells you what comes after it. You don't have to learn the catalogue.

**Point it at a real product.** An idea in a notes app counts. The skills read your repo, your site and your README before asking you anything, so run them from inside the project rather than a blank folder.

**Make somewhere to put the output.** The template repo already has the folders. If you're working in your own project, a docs/gtm/ directory is fine — the skills write markdown, they don't care where.

## The steps

### 01. Automate the content pipeline

`/social-automation`

Agents that draft from your content map, hold your voice, and queue on a schedule. Decide where a human stays in the loop and be honest about where the loop is theatre.

*Done looks like:* A week of posts is queued and you didn't write them the morning of.

### 02. Pick a cadence that survives a busy month

The ambitious schedule is the one you abandon in week three. Halve it.

*Done looks like:* You'd still hit it during a bad week.

### 03. Do the CAC ceiling arithmetic

`/unit-economics`

LTV, churn and payback, inverted into the most you can pay for a customer. Everything about paid is downstream of this number.

*Done looks like:* One number, and you can show the arithmetic that produced it.

### 04. Set pricing deliberately

`/pricing-model`

The model has to match how customers actually get value. Better decided now than anxiously on Saturday.

*Done looks like:* You can explain why it's per-seat, or usage, or flat — in one sentence.

### 05. Plan the paid push

`/paid-basics`

Only if /paid-test cleared. Account structure, creative angles versus variations, targeting narrow before broad, and the daily raise/hold/cut loop.

*Done looks like:* You know what you'd check tomorrow morning and what you'd do about each outcome.

### 06. Run the pre-launch checklist

`/launch-checklist`

The Friday-night one. Analytics firing, links working, OG images, the thing that always breaks.

*Done looks like:* It comes back clean, or you know what's still broken and it's on purpose.

## What you leave with

06-growth/ — unit-economics.md with the CAC ceiling, pricing.md, paid-basics.md, and social-automation.md with a week queued.

## If you get stuck

If the CAC ceiling comes out lower than any channel can hit, that's not a marketing problem — it's pricing or retention. Fix it before Saturday.

---

Slides, skill downloads and the full session page: https://www.shipai.club/hackathon/workshops/growth-engineering
Discord: https://discord.gg/kZSJMNveYM

© 2026 Ship AI — free to take and run.