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

Superpowers

ASecurity

Use when executing multi-step work in this project. Triggers on "tdd", "testes", "superpowers", "pequenas tarefas", "aprovação", "break the task down", "verify first". Encodes the Superpowers workflow: break work into small verifiable tasks, write verification/tests first, get user approval before proceeding to each step.

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

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Superpowers?

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

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

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

Download Zip
Files
SKILL.md
---
name: superpowers
description: Use when executing multi-step work in this project. Triggers on "tdd", "testes", "superpowers", "pequenas tarefas", "aprovação", "break the task down", "verify first". Encodes the Superpowers workflow: break work into small verifiable tasks, write verification/tests first, get user approval before proceeding to each step.
---

# Skill: Superpowers (TDD + pequenas tarefas + aprovação)

Aplicar a TODA tarefa de mais de 1 passo neste projeto (música ou código).

## Quando usar (gatilhos)

- "Quebra em tarefas pequenas"
- "TDD: verificador primeiro"
- "Me aprova cada passo"
- "Nada de tarefa gigante sem check"
- "Superpowers nesse fix"

## Exemplo

```text
Tarefa: "adiciona login" → 1) teste de aceite 2) implementa 3) roda teste
Aprovação pedida antes do passo 2 (muda estrutura)
```

## 1. Quebre em tarefas pequenas

- Antes de agir, liste as tarefas com `todowrite`: cada item deve ser **pequeno,
  verificável e ter saída concreta** (arquivo criado, comando que roda, nota >= X).
- Nada de "etapas" gigantes. Se um passo não der para verificar em minutos,
  quebre de novo.

## 2. Verificação primeiro (TDD leve)

- Para código: escrever o **verificador/expectativa ANTES** da implementação
  (ex.: `verify_loop.ps1` define os critérios antes de `gen_dnb.py` gerar).
- Para áudio: o **Verificador** (`scripts\verify_loop.ps1`) define a nota mínima
  antes do Criador rodar — já é o fluxo do harness.
- Sempre rode o verificador após implementar. Só avance se ele passar
  (ou registre o desvio explicitamente).

## 3. Aprovação do usuário

- Entre cada bloco de trabalho com impacto (novo script, mudança de estrutura,
  mover/apagar arquivos, mudar prompts), **pare e peça aprovação**.
- Não execute o próximo passo sem OK do usuário.
- Resumo curto do que foi feito + o que vem a seguir, sempre.

## 4. Círculo TDD clássico (para código novo)

RED (teste falha) → GREEN (implementação mínima passa) → REFACTOR (limpa, repetindo teste).

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 →