Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tiago1002bravy/skills-marketingnpx agentmods add skills/tiago1002bravy/skills-marketing/carrossel-jpasvWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tiago1002bravy/skills-marketing/carrossel-jpasv)<a href="https://agentmods.dev/skills/tiago1002bravy/skills-marketing/carrossel-jpasv"><img src="https://agentmods.dev/badge/skills/tiago1002bravy/skills-marketing/carrossel-jpasv/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tiago1002bravy/skills-marketing/carrossel-jpasv"><img src="https://agentmods.dev/badge/skills/tiago1002bravy/skills-marketing/carrossel-jpasv.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00134 | $0.05753 |
| Opus 5 | $0.00067 | $0.02877 |
| Sonnet 5 | $0.00027 | $0.01151 |
| Haiku 4.5 | $0.00013 | $0.00575 |
Grade A, and why
carrossel-jpasv scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Carrossel @jp.asv
Gera 6 slides + caption pra carrossel Instagram seguindo a voz e os padrões virais validados do perfil @jp.asv (João Pedro Nascimento — GESTÃO COM CLAUDE CODE 🇧🇷, 78k seguidores, foco Claude Code pra empresários).
Inputs obrigatórios
- tema — angulo do carrossel (ex: "recuperação tributária com Claude")
- persona —
contador|advogado|empresario|gestor|arquiteto - padrão (opcional) —
A|B|C|D|E|F— se não informar, escolha o mais aderente ao tema
Antes de gerar — leia SEMPRE estes arquivos
<repo>/dataset/padroes_validados.json
<repo>/dataset/top_carrosseis.json (top 10)
<repo>/dataset/vocab.json (do nicho da persona)
<repo>/dataset/meta.json
Nota: o dataset é proprietário e NÃO está incluso neste repositório público. Você precisa montar o seu próprio (top virais do seu perfil + vocab do seu nicho) antes de usar a skill. Veja
dataset/README.mdpra schema esperado.
Output esperado
## Carrossel — {tema}
**Padrão:** {letra} - {nome}
**Persona:** {persona}
**Modelo viral:** {code} ({score} pontos)
### S1 (capa)
{texto}
### S2
{texto}
### S3
{texto}
### S4
{texto}
### S5
{texto}
### S6 (CTA)
Comenta "{palavra}" que mando {material concreto}.
Sem te cobrar nada.
👇
### Caption do feed
{texto curto que repete hook + repete CTA}
Regras de escrita (não quebrar)
Hooks (S1)
- SEMPRE começa com número específico, ferramenta nominal, ou citação real
- NUNCA começa com meta-conceito ("IA está mudando o mercado", "eficiência é tudo")
- NUNCA usa "olha isso", "você sabia", "acabei de descobrir"
- REGRA: 1 FRASE ÚNICA na capa. Máximo 12-16 palavras, ~120 caracteres. Sem segunda frase, sem "então" ou explicação. Tem que caber em 4 linhas grandes (font-size 40px) sem cortar.
- Tem que parar o scroll em 2 segundos
Anti-padrão na capa (proibido):
"SPED de 5 anos lido em 14min. PER/DCOMP montado em 22. Cliente avisado que tem R$ 187k pra recuperar." (3 frases — tela fica poluída)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 382 lines · 134 tokens per session scan A 0fa75a19d432
carrossel-jpasv is a skill published in the GitHub repository tiago1002bravy/skills-marketing (6 stars, last pushed 4mo ago), licensed MIT. It adds 134 tokens to every session and 5,753 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…