In-Product Activation & First-Run UX

What it does

In-Product Activation & First-Run UX is a Cursor skill: a SKILL.md playbook that AgenticKit installs at .cursor/skills/activation-onboarding. Cursor's agent loads it when the task matches the skill description, instead of stuffing the same rules into every chat.

Playbook for designing the first five minutes so a new user reaches value without a feature tour.

Empty states, checklists, and one first-value moment. The file is domain knowledge, not a slash macro. You do not type it. The agent reads it when the job is activation onboarding.

Why it exists

Default Cursor has no memory of how your team ships code, schema, and tests. Founders paste the same conventions into chat, then watch the model drift on the next turn. This skill exists so those conventions live on disk and load only when relevant.

It ships in the Engineering Kit. It is wired to the Activation & First-Run Engineer (onboarding-engineer) and React 19 & Next.js Specialist (react-specialist) agents. It is wired to the /onboarding: First-Run Activation & Empty States and /qa-pass: Exploratory QA Pass commands. That graph is the point: the skill is the standard, the agent is the role, the command is the trigger.

When to use it

• Use In-Product Activation & First-Run UX when the work is specifically about empty states, checklists, and one first-value moment.
• Load it before a long session that will touch this surface more than once. A one-line edit does not need the full playbook.
• Use it on production SaaS work (multi-tenant apps, paid features, anything that will be reviewed) rather than a throwaway prototype.

When not to use it

• Do not treat the skill as a replacement for a slash command. Skills teach. Commands run a pipeline.
• Do not paste the whole SKILL.md into chat. If Cursor is not loading it, fix the description or invoke the matching command.
• Do not use it as a generic 'write better code' rule. Scope is this domain only.

Example workflow

1. Install the Engineering Kit so .cursor/skills/activation-onboarding lands in the repo.
2. Open a new Cursor agent chat pointed at the files this skill governs.
3. Ask the Activation & First-Run Engineer (onboarding-engineer) to read the skill, or run /onboarding: First-Run Activation & Empty States.
4. Review the first artifact against the practices below. If it violates one, stop and correct the file. Do not prompt 'just finish it'.
5. Commit the skill-guided files with the rest of the slice so the next session inherits the same standard.

Example usage

Example prompt: "Read .cursor/skills/activation-onboarding and apply it to this change. Do not invent extra conventions."

Or trigger the pipeline: /onboarding: First-Run Activation & Empty States. That command is written to load this skill.

Check the output against: Define one measurable first-value moment before drawing UI

Example output

• The skill itself does not write a single output file. It changes what the agent is allowed to produce in code, schema, and tests.
• When you run /onboarding: First-Run Activation & Empty States, expect repo files plus notes under docs/, not a chat-only answer.

Best practices

• Define one measurable first-value moment before drawing UI
• Empty states include a single next action
• Checklists stay at 3–5 steps completable in one sitting
• Instrument activation without putting PII in event properties

Common mistakes

• Ignoring "Define one measurable first-value moment before drawing UI" and hoping a later prompt will clean it up.
• Copying the skill into .cursor/rules as always-on. That burns context and fights Cursor's load-on-match design.
• Running two overlapping skills that contradict each other in the same turn.
• Letting the agent skip tests or types because 'the skill is about architecture'.