# Using Superpowers

> Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

Source: https://skillsagentes.com/skills/obra/superpowers/using-superpowers
Repository: https://github.com/obra/superpowers
Author: obra
License: MIT
Updated: anteayer
Context cost: 39 tok installed, 777 tok once triggered, 4.3k tok with every bundled file
Bundle: 6 files, 17 KB
Permissions requested: none declared

## Install

```bash
npx -y skills add obra/superpowers --skill using-superpowers --agent claude-code
```

## What it does

- Obliga a comprobar e invocar skills relevantes antes de responder, hacer preguntas aclaratorias o explorar el código
- Establece que las skills de proceso (brainstorming, systematic-debugging) van antes de las skills de implementación
- Anuncia el uso de la skill con "Using [skill] to [purpose]" y sigue su checklist con un todo por ítem
- Adapta el comportamiento según la plataforma leyendo un archivo de referencia (Codex, Pi, Antigravity, Hermes Agent)

## Use it when

- Al comenzar cualquier conversación
- Cuando el usuario dice "Let's build X" (usar brainstorming primero)
- Cuando el usuario dice "Fix this bug" (usar systematic-debugging primero)
- Antes de entrar en modo de planificación, si aún no se ha hecho brainstorming

## Don't bother when

- Si fuiste despachado como subagente para ejecutar una tarea específica

## What triggers it

- "Vamos a construir una nueva función de exportación"
- "Arregla este bug en el checkout"
- "Necesito que revises el código antes de responder"

## Before you install

- Si tu harness es Codex, Pi, Antigravity o Hermes Agent, hay que leer su archivo de referencia correspondiente en references/.

## Files

- SKILL.md — 3 KB
- references/antigravity-tools.md — 1 KB
- references/codex-tools.md — 5 KB
- references/gemini-tools.md — 4 KB
- references/hermes-tools.md — 2 KB
- references/pi-tools.md — 1 KB

## SKILL.md

Reproduced verbatim from obra/superpowers under MIT. This section is the upstream document and is in English.

<SUBAGENT-STOP>
If you were dispatched as a subagent to execute a specific task, ignore this skill.
</SUBAGENT-STOP>

<EXTREMELY-IMPORTANT>
If you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill.

IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT.

This is not negotiable. You cannot rationalize your way out of this.
</EXTREMELY-IMPORTANT>

## The Rule

**Invoke relevant or requested skills BEFORE any response or action** — including clarifying questions, exploring the codebase, or checking files. If it turns out wrong for the situation, you don't have to use it.

**Before entering plan mode:** if you haven't already brainstormed, invoke the brainstorming skill first.

Then announce "Using [skill] to [purpose]" and follow the skill exactly. If it has a checklist, create a todo per item.

## Skill Priority

When multiple skills apply, process skills come first — they set the approach, then implementation skills (frontend-design, etc.) carry it out. Brainstorming and systematic-debugging are Superpowers' most common process skills, but the rule holds for any of them.

- "Let's build X" → superpowers:brainstorming first, then implementation skills.
- "Fix this bug" → superpowers:systematic-debugging first, then domain skills.

## Red Flags

These thoughts mean STOP—you're rationalizing:

| Thought | Reality |
|---------|---------|
| "This is just a simple question" | Questions are tasks. Check for skills. |
| "I need more context first" | Skill check comes BEFORE clarifying questions. |
| "Let me explore the codebase first" | Skills tell you HOW to explore. Check first. |
| "I can check git/files quickly" | Files lack conversation context. Check for skills. |
| "Let me gather information first" | Skills tell you HOW to gather information. |
| "This doesn't need a formal skill" | If a skill exists, use it. |
| "I remember this skill" | Skills evolve. Read current version. |
| "This doesn't count as a task" | Action = task. Check for skills. |
| "The skill is overkill" | Simple things become complex. Use it. |
| "I'll just do this one thing first" | Check BEFORE doing anything. |
| "This feels productive" | Undisciplined action wastes time. Skills prevent this. |
| "I know what that means" | Knowing the concept ≠ using the skill. Invoke it. |

## Platform Adaptation

If your harness appears here, read its reference file for special instructions:

- Codex: `references/codex-tools.md`
- Pi: `references/pi-tools.md`
- Antigravity: `references/antigravity-tools.md`
- Hermes Agent: `references/hermes-tools.md`

## User Instructions

User instructions (CLAUDE.md, AGENTS.md, GEMINI.md, etc, direct requests) take precedence over skills, which in turn override default behavior. Only skip skill workflows or instructions when your human partner has explicitly told you to.

---

Skills Agentes — https://skillsagentes.com/skills/obra/superpowers/using-superpowers