/build-carousel

name: build-carousel
description: |
  Use when user has an idea with multiple discrete steps, a framework, a
  comparison, a before/after, a list of items worth a slide each, or
  anything where swiping is part of the experience. Trigger phrases
  include "make a carousel," "build a slide deck for LinkedIn," "turn
  this into a carousel," "I have a framework to share," or when a
  find-ideas seed is marked "Best fit for: build-carousel." Produces a
  carousel SPEC the user assembles into a PDF in Canva or Figma; does
  not export the finished PDF.
license: MIT

Build carousel

Carousels are currently the strongest format on LinkedIn. They reward more design effort, hold more dwell time per swipe, and pass more algorithmic signal per post than text or video. This skill exists to plan and write a carousel from an idea, not to design it (the user or their designer does that), but to produce slide-level copy and a clear visual brief that a designer can execute.

Why this skill exists

LinkedIn document carousels (uploaded as PDFs) currently outperform equivalent text posts by 5-10x on engagement, and educational carousels with 8-12 slides perform best. Each swipe counts as an engagement signal. The format works because it requires more effort to create (a quality signal), keeps the reader on LinkedIn (the platform rewards this), and the swipe behavior holds attention longer than scrolling past text.

But carousels can also fail badly. Slides full of stock photos and motivational quotes have the lowest engagement of any LinkedIn format. The difference between a carousel that works and one that does not is whether each slide does its own job. This skill exists to make sure each slide earns its place.

When to use this skill

Trigger when:

• The user passes a seed from find-ideas marked for carousel
• The user has a framework, a how-to, a comparison, a before/after, or a list of 5+ items
• The user has a piece of work (an internal doc, a process, a decision tree) that has natural sequential structure
• The user has tried text posts on a topic and wants to try the same topic as a carousel

Do NOT trigger when:

• The content is a single point. Send to write-post.
• The content is a long argument that needs prose, not slides. Send to write-longform.
• The content is best told on camera. Send to write-video-script.

What you need from the user

The angle (one sentence), plus the underlying material (the framework, the steps, the items, the comparison data). If they have only the angle, ask:

"What are the 5-12 concrete points that make up this carousel? Or do you want me to help you list them?"

If voice-profile.md exists, read it for the copy. Also note: do they prefer minimal design or more visual? (If they have not said, default to minimal text-forward.)

How a carousel is structured

A good carousel has three parts:

**1. The cover slide.** One job: make people swipe. The cover is the carousel's hook. It should have:

• A title that is the carousel's promise (specific, not generic)
• A subtitle or visual cue that signals there is more to see
• Optional: a slide count or progress indicator ("1 of 9")

Bad covers: "5 Lessons I Learned" / "Tips for Better Productivity" / motivational quotes attributed to "anonymous"

Good covers: "What we changed after a $40K mistake" / "The 7-question script we use before every customer call" / "Why our onboarding emails get 90% open rates (and your subject lines won't work for you)"

**2. Content slides (6-12).** Each slide does one job and stands alone if removed from context. The reader who only swipes through quickly should still get value.

Each content slide should have:

• A header (the slide's one point, written as a complete claim, not a label)
• Body text (30-80 words, conversational)
• A visual cue (a diagram, a number, an icon, a screenshot) when applicable

Common slide patterns:

• Step in a process
• Item in a list, with explanation
• Before/after comparison
• Question + answer
• Misconception + correction
• Definition + example

Bad slides: pure text with a bold header. Slides full of bullet points. Slides that just repeat the cover. Slides with a single quote and nothing else.

**3. Closing slide.** Two options:

• A single takeaway sentence that lands the whole carousel
• A call to action that is not a sales pitch (a question for the reader, an invitation to share their version, a link to a longer resource the user actually has)

The closing is also the place to credit collaborators or link to the source material. Keep it light.

How to draft

1. Read voice-profile.md if it exists.

2. Build the slide list first, before writing copy. Each slide gets a one-line description: what is this slide's job. Get this right before writing any prose. If you cannot name what each slide's job is, the carousel has too many slides or too few.

3. Write the cover. Spend the most effort here. The cover decides whether anyone sees the rest.

4. Write the content slides. Each slide: header (one claim), body (one short paragraph), visual note.

5. Write the closer.

6. Write visual direction notes for the designer or AI image tool.

Drafting constraints (apply WHILE writing, not after)

Output must read as written by a human on the first pass. The constraints below are how you write, not a checklist to apply later. Do not narrate this process to the user. Do not show a "before humanizer / after humanizer" sequence. Just produce clean output.

**Hard bans — never appear in output:**

• Em dashes (—) and en dashes (–). Use period, comma, colon, or parentheses.
• "It's not just X, it's Y" / "Not only X but Y" constructions.
• "The real question is," "at its core," "fundamentally," "what really matters."
• Signposting: "Let's dive in," "here's what you need to know," "let's break this down," "without further ado."
• Sycophancy: "Great question," "you're absolutely right," "I hope this helps," "let me know if..."
• Knowledge-cutoff hedges: "based o