Ship-to-Customer Narrative

What it does

/whats-new is a Cursor slash command. Type it in chat to run a saved workflow: Ship-to-Customer Narrative.

Turns a real diff into customer language. Does not invent features.

Changelog, email, social, in-app from one ship. Unlike a skill, a command is something you invoke on purpose. The agent does not decide to run /whats-new for you.

Why it exists

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

It ships in the Marketing Kit. It is wired to Product Marketing (Every Ship) (product-marketer), Email Sequence Specialist (email-marketer), and Social & LinkedIn Strategist (social-media-strategist). Required skills: Ship-to-Customer Feature Narrative; Brand Voice Guidelines & Jargon Elimination; Marketing Deliverable Auto-Save & Repo Sync.

When to use it

• Use after /ship or /release when you would otherwise stay silent.
• Use /whats-new 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 touched production SQL.

When not to use it

• Do not run /whats-new 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. product-marketer reads git/CURSOR.md for what actually shipped
2. Write why-care + four blurbs
3. Claims audit
4. Auto-save docs/marketing/whats-new.md

Example usage

Type this in Cursor chat: /whats-new After last ship, tell customers why they should care

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/marketing/whats-new.md

Best practices

• Keep the prompt specific. /whats-new After last ship, tell customers why they should care is the shape: object, constraint, and outcome.
• Let the listed agents work in order: product-marketer → email-marketer → social-media-strategist.
• Save outputs in the repo. Chat-only answers evaporate.
• Marketing commands write to docs/marketing/ so the next command can read positioning before it writes a landing page.

Common mistakes

• Typing /whats-new 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 Ship-to-Customer Feature Narrative skill that the command depends on.