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

Claude Cowork Patterns

ASecurity

Use when applying Claude Cowork patterns — task execution, file ops, folder processing, recurring tasks, approval gates. Triggers on "claude cowork patterns", "cowork patterns claude", "task execution patterns", "file operations patterns", "folder processing patterns", "recurring tasks claude".

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

Works with

claude codecursorcliapi

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Claude Cowork Patterns?

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

Security grade badge for Claude Cowork Patterns
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-claude-cowork-patterns/badge)](https://www.skillsdirectory.com/skills/majinmagros-claude-cowork-patterns)

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

Download Zip
Files
SKILL.md
---
name: claude-cowork-patterns
description: Use when applying Claude Cowork patterns — task execution, file ops, folder processing, recurring tasks, approval gates. Triggers on "claude cowork patterns", "cowork patterns claude", "task execution patterns", "file operations patterns", "folder processing patterns", "recurring tasks claude".
metadata:
  origin: AUTORAL
  source_docs:
    - https://www.youtube.com/watch?v=Bezlzmti6_U (Luciana Papini video)
    - https://docs.anthropic.com/en/docs/claude-code/cowork
  platforms: [claude-code, opencode, cursor, codex, gemini-cli, hermes, openclaw]
  requires_adapters: [hooks, commands]
---

# Claude Cowork Patterns - Padrões Cowork

Padrões Cowork: **task execution, file ops, folder processing, recurring tasks, approval gates**. Código em `scripts/`.

## Quando usar (gatilhos concretos)

- "Cowork task execution patterns"
- "File operations patterns"
- "Folder processing patterns"
- "Recurring tasks patterns"
- "Approval gates patterns"

## Quando NÃO usar

- Automação apenas API (use `api-connector-builder`)
- Automação desktop-only (use `automacao-deterministica`)
- Automação mobile-only

## Core Patterns (resumo — código em `scripts/`)

**1. Task execution** (`task_execution.py`): decompose em subtarefas atômicas via LLM → `execute_with_checkpoints` (falha se checkpoint inválido) → `parallel_execution` (semáforo asyncio, max 3).

**2. File ops** (`file_operations.py`): `safe_read` (existe + ≤10MB) · `safe_write` (backup `.bak.timestamp` + mkdir) · `atomic_write` (temp + rename) · `organize_downloads` (regex → pastas).

**3. Folder processing** (`folder_processing.py`): `process_folder_recursive` (processor + pattern + max_depth → {processed, errors, skipped}) · `watch_folder` (watchdog, patterns, recursive).

**4. Recurring tasks** (`recurring_tasks.py`): `add_recurring_task` (cron-like via `schedule`) + scheduler em background thread (daemon, 60s tick).

**5. Approval gates** (`approval_gates.py`): `require_approval` decorator (input y/N) · `auto_approve_low_risk` (read/list/search/analyze) · `log_execution` (audit: action, params, resumo, ms, timestamp).

**Integração** (`integration.py`): exemplo `research_and_organize` com `claude-chrome-automation` (pesquisa multi-tab → organiza downloads por tópico).

```python
from skills.claude-cowork-patterns.scripts.file_operations import FileOperationPatterns
FileOperationPatterns.atomic_write("relatorio.md", conteudo)  # sem corrupção parcial
```

## Referências Oficiais

- [Luciana Papini Video](https://www.youtube.com/watch?v=Bezlzmti6_U)
- [Claude Code Cowork Docs](https://docs.anthropic.com/en/docs/claude-code/cowork)

## Adapters (Por Plataforma)

```
adapters/
├── opencode/ (hooks, README)
├── cursor/ (hooks, README)
├── codex/ (hooks, README)
└── ...
```

## Conversa unificada (leva YouTube rodada 9)

Nao force escolha de superficie: mesma thread para pergunta e tarefa profunda. O modelo roteia (responder vs executar); o usuario faz steer/edit no meio. Se a thread mistura pergunta + execucao, separe a prova por entrega, nao por mensagem.

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 →