Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Automacao Deterministica

ASecurity

Use when a task is predictable and should become a script instead of AI reasoning — or when deciding what to automate vs keep with the model. Triggers on "automatiza", "script pra isso", "tarefa previsível", "a+b=c", "postar automático", "não precisa pensar", "ganhar eficiência". Automates deterministic steps; keeps creative/reasoning with the LLM.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentspythongogitapi

Works with

cliapi

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill automacao-deterministica --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Automacao Deterministica?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Automacao Deterministica
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-automacao-deterministica/badge)](https://www.skillsdirectory.com/skills/majinmagros-automacao-deterministica)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: automacao-deterministica
description: Use when a task is predictable and should become a script instead of AI reasoning — or when deciding what to automate vs keep with the model. Triggers on "automatiza", "script pra isso", "tarefa previsível", "a+b=c", "postar automático", "não precisa pensar", "ganhar eficiência". Automates deterministic steps; keeps creative/reasoning with the LLM.
---

# Skill: Autoacao-deterministica — script pro previsível, IA pro que pensa

Tarefa A+B=C (entrada previsível → saída previsível) vira SCRIPT determinístico.
Script roda idêntico toda vez e não gasta tokens. IA fica para o que exige
raciocínio, criatividade e variação.

## Quando usar (gatilhos)

- "Automatiza essa tarefa repetitiva"
- "Faço isso todo dia, tem como virar script?"
- "A+B=C: entrada igual, saída igual"
- "Postar/transcrever/converter no automático"
- "Isso precisa de IA ou dá pra scriptar?"

## Exemplo

```python
# A+B=C: transcrever vídeo todo dia → script, não agente
baixar(url) → converter_mp3() → transcrever() → salvar_txt()
```

## 1. Decida: automatizar ou não?

| Automatize (script) | Mantenha na IA |
|---|---|
| Postar vídeo pronto nas redes | Escrever roteiro/copy criativo |
| Transcrever vídeo (download → texto) | Gerar materiais didáticos do conteúdo |
| Baixar/formatar/converter arquivos | Análise que decide no caminho |
| Regra fixa: "input X → sempre Y" | Onde o "bom" muda a cada vez |

Teste mental: a saída depende de decisão/criatividade? Sim → IA. Não → script.

## 2. Processo

1. Identifique o passo determinístico dentro do fluxo (ex.: transcrever =
   baixar + converter; não é "fazer a aula").
2. Peça ao agente para **escrever o script** (Python/CLI) — você não precisa
   saber programar.
3. Integre ao fluxo; atualize o script quando a plataforma mudar (você só
   atualiza o script, não re-faz a tarefa na mão).

## 3. Cuidados

- **Não automatize tudo**: script de tarefa usada 1x a cada meses custa mais
  manutenção do que economiza. Automatize o que roda TODO DIA e é estável.
- **Custo de erro**: sem camada de verificação, automação quebra calada.
  Adicione alerta/revisão se o erro for caro.
- Prefira conector/API oficial a browser automation (quebra com mudança de layout).
- Credenciais em `.env`, nunca no repositório público.

## 4. Regra

- Automação não substitui agente — elimina o trabalho burro do agente para ele
  sobrar para o que importa.

## 5. Verify + cost-gate + idempotency (leva YouTube rodada 5)

Antes de ligar qualquer schedule/webhook externo:

- **Validate local primeiro** — TDD local + DM/teste de ponta a ponta com custo
  medido antes de migrar. `hosted proof test` (run de prova no scheduler com
  schedule desligado) antes do `enable`.
- **Teto custo/run** — defina ex.: $0.25/run; meça o real (ex.: $0.0133) e
  alerte se 3 runs seguidas estourarem 2x o teto.
- **Idempotency key** — flag `delivered` (ou hash do payload): mesmo conteúdo
  12:01 vs 12:33 = skip duplicata. Teste a duplicata de propósito antes do go-live.
- **`.env` nunca no repo** — segredos vão para as env vars do scheduler, copiados
  à mão. Repo privado + `.env` no `.gitignore` + prova de que nada vazou no log.

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →