What is engenharia-de-criativos?

A Portuguese-language method for transcribing and examining audio or video advertisements. It maps the ad's structure, promise, evidence, audience awareness, and call to action before adapting it.

Use it to transcribe a media file, diagnose its sales message, or create a new piece based on the analyzed reference.

It turns an advertisement into a reusable plan, so its persuasive structure can be understood before creating a new version.

engenharia-de-criativos — Skill for Codex by gabrielima783-prog

Install

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.

Any agent

npx skills add gabrielima783-prog/copy-skills --skill engenharia-de-criativos

Clone the repo

git clone --depth 1 https://github.com/gabrielima783-prog/copy-skills

Made for: Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gabrielima783-prog/copy-skills/engenharia-de-criativos/github.svg)](https://agentmods.dev/skills/gabrielima783-prog/copy-skills/engenharia-de-criativos)

Your own site

<a href="https://agentmods.dev/skills/gabrielima783-prog/copy-skills/engenharia-de-criativos"><img src="https://agentmods.dev/badge/skills/gabrielima783-prog/copy-skills/engenharia-de-criativos/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gabrielima783-prog/copy-skills/engenharia-de-criativos"><img src="https://agentmods.dev/badge/skills/gabrielima783-prog/copy-skills/engenharia-de-criativos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,135 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00089	$0.01135
Opus 5.5	$0.00036	$0.00454
Sonnet 5.5	$0.00018	$0.00227
Haiku 4.5	$0.00009	$0.00113

Measured 2mo ago against content hash 4f504fa40499, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

engenharia-de-criativos 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 2mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/extract-frames.sh, scripts/setup.sh, scripts/transcribe.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/engenharia-de-criativos/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Engenharia de criativos

Transformar um criativo em um mapa reutilizavel: extrair a fala, observar o video, diagnosticar a persuasao e construir uma nova peca.

Escolher o modo

Transcricao: executar somente a etapa tecnica quando o usuario pedir texto ou legenda.
Engenharia completa: transcrever, observar e desmontar quando pedir analise, estrutura, raio-X ou avaliacao.
Criacao pela referencia: executar a engenharia completa antes de escrever a adaptacao.

Nao depender de uma skill de roteiro. Entregar diretamente fala, visual, texto na tela e funcao de copy.

Preparar o ambiente

Resolver o diretorio desta skill a partir do caminho do SKILL.md. Na primeira execucao, rodar:

<diretorio-da-skill>/scripts/setup.sh

O script cria .venv e models/ dentro da skill. Exigir python3 e ffmpeg. Se ffmpeg estiver ausente, informar a dependencia e orientar a instalacao adequada ao sistema operacional.

Transcrever

Executar:

<diretorio-da-skill>/scripts/transcribe.sh "/caminho/arquivo.mp4"

Por padrao, salvar em engenharia-de-criativos-output/<nome-limpo>/ no projeto atual. Aceitar um segundo argumento para outro diretorio de saida dentro do projeto:

<diretorio-da-skill>/scripts/transcribe.sh "/caminho/arquivo.mp4" "/caminho/do/projeto/analises"

Conferir .txt, .srt, .vtt, .tsv e .json. Usar turbo primeiro. Se houver perda relevante por ruido, fala rapida ou diccao, executar novamente com WHISPER_MODEL=medium.

Corrigir apenas erros evidentes de nomes, cidades e termos. Sinalizar correcoes incertas e trechos inaudiveis.

Observar o criativo

Nao inferir o formato visual somente pela fala. Inspecionar o video e identificar:

formato: talking head, UGC, entrevista, demonstracao, narracao, montagem, estatico animado ou hibrido;
abertura visual, enquadramento, ritmo, cortes, imagens de apoio e mudancas de cena;
texto na tela, legendas, provas exibidas, autoridade e CTA visual;
relacao entre fala, imagem e texto.

Read the full file on GitHub · 114 lines

Files

What ships with it

4 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.

Changes

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.

2mo ago First seen · 114 lines · 89 tokens per session scan A 4f504fa40499

Subscribe to this mod's changes

engenharia-de-criativos is a skill published in the GitHub repository gabrielima783-prog/copy-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 1,135 once invoked, about $0.0004 per session on Opus 5.5. 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.

Creative and media Marketing and SEO

engenharia-de-criativos next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
engenharia-de-criativosgabrielima783-prog/copy-skills	Skill	2	2mo ago	MIT	A	89	Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	yesterday	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	4d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code