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

Routines

ASecurity

Use when scheduling autonomous Claude Code sessions in the cloud — recurring tasks that run without the machine being on. Triggers on "routines", "agendar", "tarefa recorrente", "funcionário 24/7", "roda todo dia", "webhook", "gatilho", "cloud code na nuvem". Covers schedule/webhook/GitHub triggers, vs VPS/n8n/Mac mini.

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

Works with

claude codecliapi

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Routines?

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

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

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

Download Zip
Files
SKILL.md
---
name: routines
description: Use when scheduling autonomous Claude Code sessions in the cloud — recurring tasks that run without the machine being on. Triggers on "routines", "agendar", "tarefa recorrente", "funcionário 24/7", "roda todo dia", "webhook", "gatilho", "cloud code na nuvem". Covers schedule/webhook/GitHub triggers, vs VPS/n8n/Mac mini.
---

# Skill: Routines — sessões autônomas agendadas na nuvem

Agenda sessões completas do Claude Code na nuvem, sem deixar o computador
ligado e sem VPS/Mac mini. Uma rotina = skill + prompt de ativação.

## Quando usar (gatilhos literais)

- "Agendar tarefa todo dia"
- "Roda esse fluxo mesmo com PC desligado"
- "Funcionário 24/7 na nuvem"
- "Webhook que dispara agente"
- "Rotina recorrente sem VPS"

## Exemplo

```text
Rotina: "todo dia 8h → resume notícias → envia no e-mail"
Gatilho: agendamento | Skill: pesquisa + envio
```

## 1. Quando usar (vs alternativas)

| Opção | Bom para | Custo/limite |
|---|---|---|
| **Execução local** | Tarefa agendada no próprio PC | PC desligado/sem internet = não roda; RAM estoura |
| **VPS** | Fluxo flexível que decide no caminho | Setup técnico alto |
| **n8n/Make** | Pipeline previsível A+B=C | Rígido, quebra com atualização, sem agente LLM |
| **Routines** | Agente agêntico 24/7 na nuvem, fácil | Recurso da Anthropic; usa repositório no GitHub |

Routines vence quando o fluxo precisa de DECISÃO ao longo do caminho (n8n é
rígido demais) mas não vale o setup de VPS.

## 2. Gatilhos (3 formas de ativar)

1. **Agendamento**: horário fixo (todo dia às 8h, a cada X min, semanal).
2. **Endpoint/webhook**: HTTP request dispara o fluxo (ex.: cliente comprou →
   checkout chama o webhook → onboarding automático). Também permite falar com
   o agente via WhatsApp para um número.
3. **Evento GitHub**: PR aberto → revisão de código automática, atribuição,
   etc.

## 3. Como montar

1. Tenha o agente num **repositório no GitHub** (CLAUDE.md + skills já
   configurados).
2. Conecte o repo ao Routines (painel `claude.ai/code/routines`).
3. Descreva a rotina: **skill + prompt** que ativa a skill ("pesquise as
   notícias do dia e envie no meu e-mail").
4. Escolha o gatilho e conecte os connectors (e-mail, WhatsApp, Sheets).
5. Teste manualmente antes de agendar.

## 4. Regras

- O que roda na nuvem é uma **sessão completa** do Claude Code, não um script limitado.
- Tarefa sem decisão/revisão → considere n8n (mais barato/estável).
- Rotina com chave/credencial: mantenha em `.env`, nunca no repositório público.

## 5. Enriquecimento 2026-08-20 — Loop engineering + 5 tasks + V2 cloud (SimonScrapes)

- **Loop engineering `UfN4l2yCT54`**: loop = repeat until `done` (ex.: `every receipt matched or flagged`). **Done criteria** claro = setup rápido. Triggers: turn-based (mensagem), time-based (schedule Fri/1st), event-based (email/meeting) — event pode ser polled hourly via `check inbox`.
- **5 tasks exemplo time-based**: use esta taxonomia para desenhar qualquer workflow custom.
- **V2 Hands-Off `b3OiEUp1GIU`**: evolução v1 local (precisa laptop aberto `stay open`), v2 API `managed agents`, v3 VPS+tmux+Telegram (painful), v4 cloud zero setup (`describe task + pick schedule`, laptop shut, phone view). Matriz 4 opções guia migração VPS→cloud.

## Cross-link: inbox de bot via AgentMail (auditoria semanal 13-18/09)

Rotina webhook para inbox proprio de bot (AgentMail): receita completa em grokbot-team-ops (receita AgentMail). Use este padrao quando o bot precisar receber email sem conta humana.

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 →