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 gabrielima783-prog/copy-skills --skill engenharia-de-criativosgit clone --depth 1 https://github.com/gabrielima783-prog/copy-skillsWrote 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/gabrielima783-prog/copy-skills/engenharia-de-criativos)<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.
<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>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 | $0.00044 | $0.00567 |
| Sonnet 5 | $0.00018 | $0.00227 |
| Haiku 4.5 | $0.00009 | $0.00113 |
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 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 — 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.
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.
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 · 114 lines · 89 tokens per session scan A 4f504fa40499
engenharia-de-criativos is a skill published in the GitHub repository gabrielima783-prog/copy-skills (2 stars, last pushed 27d ago), licensed MIT. It adds 89 tokens to every session and 1,135 once invoked, about $0.0004 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…