/onboarding

First-Run Activation & Empty States

Checklist, empty states, and one aha moment after signup.

/onboarding After signup, user creates first project in under 2 minutes

Where it installs

# .claude/commands/onboarding.md
---
description: ...
argument-hint: [activation goal or flow]
allowed-tools: Read, Grep, Glob, Skill, TodoWrite, Edit, ...
---

What it does

/onboarding is a Cursor slash command. Type it in chat to run a saved workflow: First-Run Activation & Empty States.

Designs and implements the first five minutes: empty states with a next click, a short setup checklist, and one activation event.

Checklist, empty states, and one aha moment after signup. Unlike a skill, a command is something you invoke on purpose. The agent does not decide to run /onboarding for you.

Why it exists

Founders retype the same multi-step prompt until it rots. /onboarding exists so the pipeline, all 4 steps of it, is a file in .cursor/commands, versioned with the repo.

It ships in the Engineering Kit. It is wired to Activation & First-Run Engineer (onboarding-engineer), React 19 & Next.js Specialist (react-specialist), and Exploratory QA Specialist (qa-explorer). Required skills: In-Product Activation & First-Run UX; SaaS Architecture Patterns & Multi-Tenancy; Product Analytics & Funnel Tracking.

When to use it

  • Use when signup works but users never reach value, or the dashboard looks abandoned.
  • Use /onboarding when you want that pipeline, not a freeform chat. If you only need one step, use a narrower command or a single agent.
  • Start a new chat. Do not run this command in a thread that just wrote marketing copy.

When not to use it

  • Do not run /onboarding as a substitute for reading the diff. The command produces files; you still gate them.
  • Do not chain it into a 40-turn chat. Fresh context is part of the design.
  • Do not run it if you have not filled CURSOR.md. The pipeline will invent a stack.

Example workflow

  1. onboarding-engineer defines the first value moment from CURSOR.md
  2. react-specialist implements empty states and checklist UI
  3. analytics-engineer wires one activation event
  4. qa-explorer clicks the path like a new user

Example usage

Type this in Cursor chat: /onboarding After signup, user creates first project in under 2 minutes

The command file tells the session which agents to adopt and which skills to read. You should see phase headers, not a single dump of code.

If a phase fails its gate, stop. Do not add 'just continue'.

Example output

  • Expected artifact: docs/product/onboarding.md
  • Expected artifact: src/app/.../page.tsx

Best practices

  • Keep the prompt specific. /onboarding After signup, user creates first project in under 2 minutes is the shape: object, constraint, and outcome.
  • Let the listed agents work in order: onboarding-engineer → react-specialist → qa-explorer.
  • Save outputs in the repo. Chat-only answers evaporate.
  • Engineering commands should leave tests or an audit note, not only implementation files.

Common mistakes

  • Typing /onboarding with no object ('do the thing'). The pipeline will guess.
  • Re-running the command in the same chat after a failed gate instead of fixing the failing file.
  • Editing the command file to skip review so it 'goes faster'.
  • Skipping the In-Product Activation & First-Run UX skill that the command depends on.

Frequently asked questions

  • What does /onboarding do in Cursor?
    Designs and implements the first five minutes: empty states with a next click, a short setup checklist, and one activation event.
  • When should I run /onboarding?
    Use when signup works but users never reach value, or the dashboard looks abandoned.
  • What is an example /onboarding prompt?
    /onboarding After signup, user creates first project in under 2 minutes
  • Which skills does /onboarding load?
    In-Product Activation & First-Run UX; SaaS Architecture Patterns & Multi-Tenancy; Product Analytics & Funnel Tracking
  • Is /onboarding a Cursor skill?
    No. /onboarding is a slash command you type. Skills are playbooks the agent may load. Use both: the command runs the workflow, the skills constrain how it writes.

Run /onboarding from your own repo

AgenticKit installs 47 slash commands, 46 agents, and 61 skills. One command installation.