Skills obra superpowers Superpowers
using-superpowers
- Use it when:
- You install the Superpowers bundle: it's the bundle's entry point.
- It does:
- Makes the agent check for a matching skill before every reply, even before a clarifying question.
- Priority:
- Process skills such as brainstorming and systematic-debugging come before implementation skills.
- Needs:
- The rest of Superpowers to be useful.
Skill 1 of 15 in the Superpowers bundle, before brainstorming.
Only works inside its bundle: Makes the agent load the other Superpowers skills before it replies; alone, it has nothing to load. Install Superpowers instead.
TL;DR
It's the rule that makes the other Superpowers skills fire. Loaded at the start of a session, it tells the agent that if there's even a 1% chance a skill applies, it must load it before responding, including before asking a question or exploring the code, and announce which skill it's using. When several apply, process skills come first: brainstorming before building, systematic-debugging before fixing. It lists the excuses agents use to skip skills and answers each one, adapts to harnesses such as Claude Code and Codex, and gives way to your own instructions in CLAUDE.md or AGENTS.md. Subagents ignore it.
Summarizes the skill at bb92a77.
npx skills add https://github.com/obra/superpowers --skill using-superpowers skills.sh pageSource on GitHubAll skills from obra/superpowers
- Total Downloads
- 282,893 on skills.sh, Nov 9, 2026
- Repo stars
- 314,664 obra/superpowers
- First seen
- Jan 19, 2026 on skills.sh
Weekly values
| Week to | Installs |
|---|---|
| Sep 21 | 5,840 |
| Sep 28 | 5,880 |
| Oct 5 | 5,177 |
| Oct 12 | 4,640 |
| Oct 19 | 5,650 |
| Oct 26 | 5,533 |
| Nov 2 | 5,396 |
| Nov 9 | 5,954 |
| Category |
Find, write, vet and route to other skills. Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills. |
|---|---|
| Type |
An entry point that picks and loads other skills. Retired skills that only redirect count as routers. |
| Effect |
Adds no side effects of its own. It shapes how the agent thinks, writes or reviews. Guidelines and routers are always effect:none, even when the task they support edits code. |
| Needs |
Instructions only. Works in any agent that supports skills. |
| Publisher |
Everyone else. Unverified vendor claims default to community. |
| Topics |
SKILL.md
From obra/superpowers at bb92a77. Checked daily, last changed Oct 20, 2026.
Frontmatter
name: using-superpowers
description: Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions<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:
- Claude Code:
references/claude-code-tools.md - Codex:
references/codex-tools.md - Pi:
references/pi-tools.md - Antigravity:
references/antigravity-tools.md - Hermes Agent:
references/hermes-tools.md - Muse:
references/muse-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.