Carousel Writer logo

Carousel Writer

Organization
social-media-skills
carousel-writer

Use to write a carousel — a swipeable multi-slide post (Instagram carousel, LinkedIn document/PDF carousel, or TikTok photo carousel) — one of the highest-save, highest-dwell formats. Run when the user says "write a carousel," "carousel post," "slides for X," "LinkedIn document/PDF post," "swipe post," "turn this into a carousel," or wants multi-slide teaching or story content. Reads brand-profile and voice first; the cover slide hooks and promises the swipe (via hook-writer); each slide advances one idea and earns the next swipe; ends on a save-leaning CTA. Specifies the design direction and bundles an image-generation prompt pack (Nano Banana / Ideogram) for the slide visuals. Hands the caption to caption-writer and scheduling to scheduling-and-queue.

Overview

Publishersocial-media-skills
Repositoryskills
Skill namecarousel-writer
Stars
215
Forks
44
Bundled files
6
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 6 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by social-media-skills on GitHub. Read the source before you install it.

Installation

Install the Carousel Writer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/social-media-skills/skills/tree/main/skills/carousel-writer
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/social-media-skills/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/carousel-writer .claude/skills/carousel-writer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Carousel Writer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Carousel Writer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Carousel Writer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Carousel Writer

A carousel is a swipeable teaching-or-story post — and one of the best formats there is for saves and dwell time (both strong ranking signals). But it only works if people swipe, and they only swipe if each slide earns the next. So this skill is opinionated about the cover, the one-idea-per-slide discipline, and keeping slides legible — not dumping paragraphs onto images.

Three principles:

  1. The cover slide is the whole game. Slide 1 must hook and promise the payoff — it decides whether anyone swipes past it. Treat it like a thread opener or a Reel hook.
  2. One idea per carousel, one idea per slide. A cohesive arc across slides, each advancing it by one beat. A slide crammed with three points loses the swipe.
  3. It's copy and design. Minimal, legible text per slide; a clear visual hierarchy. A carousel is read at a glance on a phone — walls of text kill it.

Step 0 — Read the foundation first

Load brand-profile.md and voice.md. Voice applies to every slide (concise) and to the caption. Carry guardrails and any compliance/disclosure rules.

Step 1 — Lock the idea, goal, and platform

  • One idea — the single thing this carousel teaches or tells.
  • Goal — usually saves or authority (carousels excel here), sometimes comments.
  • Platform — Instagram carousel, LinkedIn document/PDF carousel (very high dwell/saves), or TikTok photo carousel. Specs differ (see references/platform-specs.md).

Step 2 — Write the cover slide (hook + promise)

Use hook-writer. The cover must hook (stop the scroll) and promise what the swipe delivers ("5 hooks that actually work →"). It must be legible at a glance and at thumbnail size. No slow-build cover. See references/slide-craft.md.

Step 3 — Architect the carousel

Pick a structure (how-to, listicle, story, before→after, myth-bust, framework — see references/architecture.md) and outline the spine: the cover's promise and the ordered slides that deliver it. One idea per slide. Decide slide count by the idea, not a target — a tight 6 beats a padded 10.

Step 4 — Write the slides

Each slide: a clear headline + at most a short supporting line, front-loaded and legible. Maintain swipe momentum (progress, a small pull forward). Keep every slide in the brand voice and ruthlessly minimal — if it needs a paragraph, it's two slides. See references/slide-craft.md.

Step 5 — Land the payoff and a save-leaning CTA

End with a payoff/summary slide, then a CTA slide. Carousels win on saves, so the default CTA is "save this for later" (plus optionally follow/comment). One ask. A link, if any, goes to the caption/bio/first comment per platform.

Step 6 — Specify the visuals (design direction + image pack)

A carousel is visual. Provide:

  • Design direction — layout, hierarchy, palette, type, and a consistent template across slides (consistency is what makes it look pro).
  • The image-generation prompt pack — bundled prompts (Nano Banana / Ideogram, which render legible in-image text) to produce on-brand slides, with the exact slide text specified. Or a clean template spec for Canva/a designer. Flag AI-disclosure for generated images. See references/image-prompt-pack.md. (For deeper visual systems, see design-and-templates.)

Step 7 — Hand off

  • Caption: the carousel post needs a caption that pulls people into slide 1 → caption-writer.
  • Schedule: hand the finished carousel + caption to scheduling-and-queue.

Quality bar — self-check

  • Does the cover hook AND promise the swipe, legible at a glance?
  • Is it one idea, with a clear spine — one idea per slide, no crammed slides?
  • Does each slide earn the next swipe (momentum, no filler slides)?
  • Is the text minimal and legible on mobile — not a wall?
  • Does it end on a payoff + one save-leaning CTA?
  • Is there a consistent design direction and an image pack (or template) to produce it?
  • Is AI-disclosure handled for generated visuals; no fabricated stats on slides?
  • On-voice throughout?

Edge cases & pushback

  • "Make it 10 slides" when the idea is 5 → resist padding; a tight carousel beats a bloated one. Offer the strongest N, not a quota.
  • Better as something else → a single point is a single image; a dynamic story is often a Reel; a text argument may be a thread. Say so rather than forcing a carousel.
  • Text-heavy source (a blog) → atomize into one idea per slide, don't paste paragraphs (see cross-platform-repurposing).
  • No design tool / no AI images → provide a clean text-template spec that works on a simple branded background; don't block on production.
  • Regulated/sensitive → carry compliance guardrails onto slides; only verifiable claims.

Related skills

  • brand-profile, voice-builder — voice + guardrails.
  • hook-writer — the cover hook.
  • design-and-templates — deeper visual design system for slides.
  • caption-writer — the post caption; cross-platform-repurposing — source → carousel.
  • nano-banana, ideogram (creative-tool mini-skills) — generate the slide visuals.
  • scheduling-and-queue — schedule the finished carousel.

References

  • references/architecture.md — carousel structures, the spine, one-idea-per-slide, slide count.
  • references/slide-craft.md — slide-level writing + visual hierarchy + the cover formula.
  • references/platform-specs.md — IG / LinkedIn document / TikTok carousel specs.
  • references/image-prompt-pack.md — the bundled image-generation prompt pack (Nano Banana/Ideogram).
  • references/examples.md — worked carousels slide-by-slide, with prompts, vs a text-dump version.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Carousel Writer AI skill do?

Use to write a carousel — a swipeable multi-slide post (Instagram carousel, LinkedIn document/PDF carousel, or TikTok photo carousel) — one of the highest-save, highest-dwell formats. Run when the user says "write a carousel," "carousel post," "slides for X," "LinkedIn document/PDF post," "swipe post," "turn this into a carousel," or wants multi-slide teaching or story content. Reads brand-profile and voice first; the cover slide hooks and promises the swipe (via hook-writer); each slide advances one idea and earns the next swipe; ends on a save-leaning CTA. Specifies the design direction a...

Why use Carousel Writer on TypingMind?

Because you install it once and use it with any model. Carousel Writer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Carousel Writer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/social-media-skills/skills/tree/main/skills/carousel-writer. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Carousel Writer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Carousel Writer?

As many as you like. As long as a model supports skills, you can use Carousel Writer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Carousel Writer AI skill free?

Yes. It is published on GitHub by social-media-skills under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇