TypingMindTypingMindThe best frontend for AI
Carrossel logo

Carrossel

Community
guilhermealvestech
carrossel

Cria carrosséis e posts estáticos com a identidade da marca (Instagram, X, LinkedIn), do roteiro ao PNG em alta, com galeria, slider, comparação de versões e legenda. Use quando o usuário pedir carrossel, post, capa, slide para redes sociais, ou quiser montar a identidade visual da marca para posts.

Overview

Publisherguilhermealvestech
Repositorycarrossel-skill
Skill namecarrossel
Stars
106
Forks
15
Bundled files
32
LicenseMIT
Links
Skill sourceRepository
  • 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.

  • 32 bundled files

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

  • Open source

    Published by guilhermealvestech on GitHub. Read the source before you install it.

Installation

Install the Carrossel 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/guilhermealvestech/carrossel-skill/tree/master/skills/carrossel
  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/guilhermealvestech/carrossel-skill.git /tmp/carrossel-skill
mkdir -p .claude/skills
cp -r /tmp/carrossel-skill/skills/carrossel .claude/skills/carrossel
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Carrossel 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 Carrossel 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 Carrossel 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.

/carrossel

Workflow para produzir carrosséis com cara de marca, não de template. A qualidade vem de quatro coisas: roteiro antes do visual, a galeria como referência, assets próprios e checagem visual de cada render. Siga a ordem abaixo; não pule etapas.

Caminhos: <skill> é a pasta deste arquivo. Rode os scripts da raiz do projeto do usuário; --dir é relativo a ela. O projeto do usuário fica em carrosseis/ na raiz do repositório dele (ou outro caminho passado com --dir).

0. Primeira vez no projeto

  1. node <skill>/scripts/checar-setup.mjs. Se faltar algo, mostre o comando exato ao usuário (normalmente npm install --prefix <skill> e npx --prefix <skill> playwright install chromium).
  2. Se carrosseis/marca/marca.json não existe: node <skill>/scripts/novo-projeto.mjs e faça o onboarding.
    • Pergunte: a marca já tem identidade (logo, cores, posts) ou vamos criar do zero?
    • Já tem: siga references/onboarding-marca-existente.md.
    • Do zero: siga references/onboarding-marca-nova.md.
  3. O onboarding termina com marca/marca.json, marca/manual.md, GOSTO.md iniciado e, se possível, uma série de assets (references/image-gen.md).

1. Antes de qualquer peça: ler

Sempre, nesta ordem: carrosseis/GOSTO.md, carrosseis/marca/manual.md, carrosseis/carrosseis.json (o que já existe e foi aprovado) e os manifest.json em carrosseis/assets/.

Ao sugerir temas, confira a galeria para não repetir o que já foi feito.

2. Roteiro primeiro

Siga references/roteiro.md. Entregue só texto: um bloco por slide, de 4 a 7 slides, capa com 2 ou 3 opções. Não desenhe nada até o usuário aprovar o roteiro.

3. Visual

Siga references/visual.md. Resumo:

  • Parta das peças aprovadas na galeria, não de um layout novo a cada vez.
  • Use templates/slide-base.html como esqueleto. Ele não lê o marca.json: troque à mão os tokens do :root, o <link> da fonte e o nome da marca pelos valores de marca.json.
  • Um foco por slide. Assets grandes, integrados à composição. Prints reais quando falar de produto.
  • Se nenhum asset da biblioteca servir, não invente nem gere sozinho: diga qual asset falta e entregue o prompt pronto (references/image-gen.md) para o usuário gerar no Codex ou no ChatGPT.
  • Nunca numere slides ("01 / 05"): a plataforma já mostra.

4. Render e checagem

  1. Salve cada slide em carrosseis/<id>/v<N>/slide-NN.html com fontes e imagens resolvendo localmente.
  2. Da raiz do projeto: node <skill>/scripts/render.mjs <id>/v<N> --dir carrosseis gera slide-NN.png (1080×1350) e slide-NN-2x.png (2160×2700).
  3. Abra e olhe cada PNG antes de entregar: texto cortado, sobreposição, texto colado na borda, contraste, asset pequeno demais. Corrija e renderize de novo. Nunca entregue sem ter olhado.

5. Entrega

Siga references/entrega.md: registrar em carrosseis.json (com legenda), gerar o slider (build-viewer.mjs) e a galeria (build-gallery.mjs), e mostrar o resultado ao usuário.

6. Feedback vira gosto

Toda aprovação, recusa ou ajuste entra no GOSTO.md na mesma rodada (formato no próprio arquivo). Ao ajustar uma peça, mude só o que foi pedido. Revisão de um tema vira nova versão (v2, v3), nunca sobrescreve a anterior.

Regras fixas

  • Não publicar, agendar ou postar nada. A skill entrega arquivos.
  • Não inventar interface de produto: use print real ou o markup do próprio projeto.
  • Dados de exemplo são identificados como exemplo.
  • Português do usuário na copy; sem jargão que o público da marca não usa.

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 Carrossel AI skill do?

Cria carrosséis e posts estáticos com a identidade da marca (Instagram, X, LinkedIn), do roteiro ao PNG em alta, com galeria, slider, comparação de versões e legenda. Use quando o usuário pedir carrossel, post, capa, slide para redes sociais, ou quiser montar a identidade visual da marca para posts.

Why use Carrossel on TypingMind?

Because you install it once and use it with any model. Carrossel 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 Carrossel in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/guilhermealvestech/carrossel-skill/tree/master/skills/carrossel. 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 Carrossel?

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 Carrossel?

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

Is the Carrossel AI skill free?

Yes. It is published on GitHub by guilhermealvestech 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.

Related AI Skills

View all
affaan-m logo

Documentation Lookup

affaan-m
CommunityPopular

Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React,…

40.4K
270.2K
1 files
View
affaan-m logo

Mle Workflow

affaan-m
CommunityPopular

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML…

40.4K
270.2K
1 files
View
mattpocock logo

Diagnosing Bugs

mattpocock
CommunityPopular

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

22.3K
264.4K
2 files
View
affaan-m logo

E2e Testing

affaan-m
CommunityPopular

Patrones de pruebas E2E con Playwright, Page Object Model, configuración, integración CI/CD, gestión de artefactos y estrategias para pruebas inestables.

39.1K
261.1K
Instructions
View

Set up your own AI workspace now

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