Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tiago1002bravy/skills-marketing --skill creative-meta-adsgit clone --depth 1 https://github.com/tiago1002bravy/skills-marketingWrote 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/creative-meta-ads)<a href="https://agentmods.dev/skills/tiago1002bravy/skills-marketing/creative-meta-ads"><img src="https://agentmods.dev/badge/skills/tiago1002bravy/skills-marketing/creative-meta-ads/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/creative-meta-ads"><img src="https://agentmods.dev/badge/skills/tiago1002bravy/skills-marketing/creative-meta-ads.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 | $0.00150 | $0.02668 |
| Opus 5 | $0.00075 | $0.01334 |
| Sonnet 5 | $0.00030 | $0.00534 |
| Haiku 4.5 | $0.00015 | $0.00267 |
Grade A, and why
creative-meta-ads scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST "https://graph.facebook.com/v21.0/$META_ADS_ACCOUNT_ID/adimages" \ How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creative Meta Ads — pipeline de criativos 9:16
Pipeline pra gerar variações de criativos Meta Ads (Instagram/Facebook) seguindo um padrão visual com diagrama técnico do produto. Boa pra produtos B2B SaaS / IA / automações que dependem de credibilidade técnica pra converter.
Princípios
- A/B testing dentro do mesmo tema antes de trocar. Esgote variações de um tema (
01-,02-,03-...) antes de partir pra outro. Trocar de tema cedo demais não dá tempo do Meta aprender. - Termos técnicos reais ou nada. Quem é da área percebe na hora se um termo está errado (ex: alíquota antiga, sigla extinta, lei revogada) e a credibilidade do criativo cai a zero. Veja
references/building-your-niche.mdantes de inventar qualquer termo. - Texto frozen na animação. Modelos de vídeo redesenham cada frame, então o prompt PRECISA dizer "text stays 100% identical, only animate icons/lines". Mesmo assim pode ter ruído. Kling 3.0 pro é o que melhor preserva texto até hoje.
- Estrutura de pastas fixa.
[output_dir]/[Persona]/NN-tema/vNN_tema.png+.mp4. Persona = público (Contadores, Advogados, Empresários, Arquitetos, Agências de Marketing...). Tema = dor específica.
Pipeline (6 etapas)
Etapa 1 — Briefing
Pergunte ou infira do contexto:
- Persona — quem é o público (Contadores, Advogados, Empresários, Arquitetos, Agências, Médicos...).
- Tema — dor específica que o criativo ataca (ex:
folha-fiscal,due-diligence,compatibilizacao-projetos,reporting-cliente). - Variação N — próximo número disponível na pasta da persona+tema (consulte o diretório de saída).
- Ângulo — o que distingue da V anterior (headline em pergunta vs afirmação, número diferente, dor específica diferente).
Se for primeira vez do tema na persona → 01-{tema}. Se já tem 01-, vai pra 02- etc.
Etapa 2 — Gerar copy
Estrutura fixa validada (não negocie a ordem):
EYEBROW (caps, espaçado, accent color) ← persona
HEADLINE (preto, peso 900, número grifado em amarelo)
[bloco accent com diagrama técnico do produto]
SUBHEAD (case normal, com bold seletivo em termos técnicos)
CTA (pílula preta com seta ↓ em círculo accent)
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 175 lines · 150 tokens per session scan A 0cc63f71cbd0
creative-meta-ads is a skill published in the GitHub repository tiago1002bravy/skills-marketing (6 stars, last pushed 4mo ago), licensed MIT. It adds 150 tokens to every session and 2,668 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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…