/gtm-init

name: gtm-init
version: 2.1.1
description: Set up or update the project profile (PROFILE.md) that the rest of Adaptico OS uses as context, for /gtm init [name]. Runs a founder-friendly intake - stage diagnostic, ICP and goal, what customers would use instead (competitive alternatives, not just competitor names), why the last customers came looking, what's already been tried - and points existing interview notes at /gtm interviews. Use when the user wants to create, set up, or edit their project profile, or onboard a new project. Also trigger for "set up my startup", "create a profile", "onboard my project", or "start a new GTM project".

GTM Init - Set Up Your Project Profile

You set up (or update) the **project profile** that the rest of Adaptico OS uses as context. Every profile lives in `projects/<name>/PROFILE.md`.

When invoked

The user types `/gtm init` or `/gtm init <name>`:

• If a name is NOT provided, ask the user for a project name (advise them to keep it short for ease of typing later).
• Once a name is provided, set up `projects/<name>/PROFILE.md`.

---

Step 1: Determine the mode

Check whether `projects/<name>/PROFILE.md` already exists:

| Situation | Mode | |-----------|------| | No `PROFILE.md` | **New profile** - create it from scratch | | `PROFILE.md` exists | **Update mode** - read it, fill in only what's missing |

Tell the user which mode you're in. For update mode: > "Found an existing PROFILE.md for this project. I'll check what's missing and only ask about the blank fields."

---

Step 2a: New profile - gather information

Ask these one at a time. Keep it short and founder-friendly.

Before the first question, set expectations in one honest line - say why the intake is this long:

> "A heads-up before we start: this intake is about a dozen short questions. None of them are filler - every answer adds context that makes each `/gtm` command sharper and more specific to your project, so the few minutes here pay back in every report. Don't have an answer yet? Say so and we'll move on - a blank is better than a guess."

1. **Website URL** - "What's your project's URL? (e.g. https://yourproject.com)" 2. **One-liner** - "Give me the one-sentence version: what does your product do, and for whom?" 3. **Project type** - "Which fits best: self-serve SaaS (users sign up and start on their own), sales-led B2B SaaS (you win customers through demos and sales calls), AI/API product, dev tool/infra, or prosumer/mobile app?" 4. **Stage diagnostic** - a short set of questions that place the founder on the maturity curve (this drives the recommendations). Q1-Q3 are the high-signal questions; Q4 is a revenue cross-check. Ask them all, then derive the tier:

• **Q1 - Product status:** A) pre-MVP/conceptual; B) MVP live, seeking traction; C) live with a stable paying base.
• **Q2 - Acquisition reality:** A) non-existent/manual (or no paying customers); B) one channel but constant manual effort; C) automated, predictable inbound.
• **Q3 - Primary bottleneck** (pick the one that sounds most like you): A) people don't seem to get what it is or who it's for, and you're not sure who'd really pay; B) people show up but don't sign up, or sign up and never become paying users; C) the product lands with the people who try it, but you've run out of ways to reach new ones, or users sign up then drift away; D) not sure - that's what you're here to figure out.
• **Q4 - Revenue check** (a cross-check, not the main signal): roughly, what's your monthly recurring revenue right now? A) none yet, or under $1k; B) $1k-$3k; C) $3k-$10k; D) over $10k.

5. **ICP** - "Who's your ideal customer? (role, company type, the pain you solve)" 6. **Main goal** - ask two quick parts; the first matters most:

• **Next 30 days (required):** "What's the one thing you most want to move in the next 30 days? (e.g. more signups, your first paying users, a launch.) This is your near-term focus - we'll revisit it each time you re-run /gtm audit."
• **90-day direction (optional):** "Where's that heading over the quarter? (e.g. first 100 paying users, or one signup channel that reliably works.) Skip it if you're not sure yet - the 30-day goal is what matters."

7. **Alternatives & competitors** - one beat, two parts. First: "If your product vanished tomorrow, what would your customers do instead - a rival tool, a spreadsheet, someone doing it by hand, or just live with the problem?" (this is what positioning actually competes against, so don't skip the non-product answers). Then: "Which of those are named products? Names or URLs, one per line - or leave blank, I can research them with `/gtm competitors`." 8. **Why customers come** *(skip when the diagnostic says there are no customers yet)* - "Think of the last customer who signed up: what was going on for them right before they came looking? And if you remember how they described the problem in their own words, give me the exact phrase - unpolished is better." 9. **Documentation** - "What's your documentation or developer-docs URL, if you have one?" Always ask this explicitly - site parsing (Step 2d) can miss it, and it's the link worth having for certain. 10. **Key pages & socials** *(optional)* - "Any other key links - pricing, blog, changelog, GitHub, social profiles? Paste what you've got, one per line." 11. **What have you already tried?** - "Last one: what have you already done to get users - a launch, ads, cold outreach, content, communities? And what happened? Rough numbers or a gut feeling both count. If you keep notes or a log file, drop it into `projects/<name>/` and I'll pull from it. Notes from customer or user conversations count double - drop those in too and `/gtm interviews` will turn them into evidence every command uses."

When the interface offers suggested answers to these questions, write them for a founder who has never done marketing:

• Plain words only - no GTM or insider jargon (PLG, activation, CAC, mid-market, disc