Social Carousel Skill

SkillMedia

social-carousel is a skill that lets an AI agent build an Instagram carousel of three 1080×1080 square cards whose headlines flow as one message across the series. It produces a single self-contained HTML file with gradient-based cinematic panels, brand marks, numbering, captions, and loop stamps, following a design system file for fonts and colors.

Available today. Use it from your connected AI after setup.

Have a design system file (DESIGN.md) covering color, typography, layout, and components available to the agent.

Then ask your AI: use the Social Carousel Skill skill

What your AI can do with it

  • Produces a three-panel carousel post as one self-contained HTML file
  • Lays out three 1080×1080 square cards in a row that stacks on narrow viewports
  • Writes captions that read as one sentence when the cards are stacked
  • Builds cinematic backgrounds using only radial and linear gradients, no images
  • Follows a DESIGN.md file for color, typography, layout, and component tokens
  • Adds brand marks, index chips, and 1× LOOP stamps to each card

Getting started

  1. Have a design system file (DESIGN.md) covering color, typography, layout, and components available to the agent.
  2. Provide a brief with a theme and captions, or ask the agent to pick captions that read as one sentence across the three cards.
  3. Ask for a carousel post, social carousel, Instagram carousel, LinkedIn series, or X thread cards.
  4. Preview the generated index.html to check that each panel has a distinct palette and consistent branding.

What this skill tells your AI

The instructions your AI receives, as published by nexu-io/open-design in design-templates/social-carousel/SKILL.md and read by ahel’s review.

Produce a 3-panel social carousel on a single dark stage. Each panel is a 1080×1080 cinematic still — connected as a series, but each readable on its own.

Workflow

  1. Read the active DESIGN.md (injected above). Pick the loudest serif token for the headline lockups and a mono token for stamps / counters.
  2. Pick the theme + 3 captions from the brief. The captions must read as one sentence when stacked: ("onwards." → "to the next one." → "looking ahead." or "input." → "iterate." → "ship.").
  3. Stage — full-bleed dark page. Top header strip:
    • Left: serif italic display "Three posts. One beat."
    • Just below the title: a one-line description in muted mono ("1080×1080 · cinematic video loops · minimal type. Drop into Instagram, LinkedIn, or X — each post stands on its own or runs as a three-part series.").
    • Right: small mono badge "SERIES · 01 → 03".
  4. Cards — 3 squares in a horizontal row (wraps to stack on narrow viewports). Each card is aspect-ratio: 1 / 1 with rounded 12px corners and a subtle 1px border, plus a soft drop shadow.
    • Background: a layered gradient that suggests a cinematic photo — for example, panel 1 = warm dawn meadow (stacked greens with a cyan sky wash); panel 2 = forest dusk (warm oranges fading into deep teals); panel 3 = pink-mountain ridge (rosy peaks against a dim violet sky). Use radial-gradient + linear-gradient only — no images.
    • Top-left chip: brand wordmark in serif italic ("Jerrod Lew") with a small accent dot.
    • Top-left below chip: micro mono index "AI · 01 / 03" (and 02, 03).
    • Bottom-left: the headline lockup in white serif display, italic accent on one word.
    • Bottom-right corner: a 1× LOOP mono stamp inside a thin border.
    • Bottom strip caption: small caps mono describing the imagined frame ("Man, walking forward — close.", "Woman, stepping into frame.", "Woman, overlooking the city.").
  5. Write a single HTML document:
    • <!doctype html> through </html>, CSS inline.
    • Cards are sized via width: clamp(280px, 30vw, 380px) so 3 fit comfortably across most desktops and stack at < 1100px.
    • data-od-id on stage, each card, each headline.
  6. Self-check:
    • The three headlines together form one sentence and feel cinematic.
    • Mono is used only for the wordmark index, the loop stamp, and the bottom captions. The headlines stay serif.
    • Each panel's color story is distinct — no two share a dominant hue.

Output contract

Emit between <artifact> tags:

<artifact identifier="carousel-slug" type="text/html" title="Carousel — Title">
<!doctype html>
<html>...</html>
</artifact>

One sentence before the artifact, nothing after.

Signals

GitHub stars
98k
Forks
11k
Last commit
Sep 2026

Others that do the same job

Questions

What size are the cards?
Each card is a 1080×1080 square, sized for drop-in use on Instagram, LinkedIn, or X.
Does it use photos?
No. Backgrounds are layered radial and linear gradients that suggest cinematic stills, so the output needs no image assets.
What does the agent deliver?
A single self-contained HTML file with an index.html entry point that previews the three cards.
Advanced
Item type
skill
Key
social-carousel-2
Source
github.com/nexu-io/open-design