PluginBench
Skill
Review
Audit score 70

using-superpowers

obra/superpowers

Establish skill-first workflow—invoke relevant skills before any response or action.

SourceView on skills.sh

What is using-superpowers?

This skill enforces a disciplined approach to agent task execution by requiring skill invocation before responding to requests, clarifying questions, or exploring code. Use it at the start of any conversation to set the expectation that applicable skills must be checked and used first, preventing ad-hoc problem-solving and ensuring systematic, skill-guided workflows.

  • Requires skill invocation before any response, clarification, or action
  • Establishes skill priority rules: process skills first, then implementation skills
  • Provides red-flag checklist to catch rationalization and premature action
  • Defines platform-specific adaptations for Claude Code, Codex, Pi, and other harnesses
  • Clarifies that user instructions take precedence over default skill behavior

How to install using-superpowers

npx skills add https://github.com/obra/superpowers --skill using-superpowers
Claude Code
Cursor
Windsurf
Cline

How to use using-superpowers

  1. 1.Invoke this skill at the start of any conversation or task
  2. 2.Check if any other skills apply to the current request before proceeding
  3. 3.If multiple skills apply, run process skills (brainstorming, systematic-debugging) first, then implementation skills
  4. 4.Announce 'Using [skill] to [purpose]' and follow the skill exactly
  5. 5.If the skill has a checklist, create a todo item per checklist entry
  6. 6.Consult the red-flags table if you feel tempted to skip skill invocation

Use cases

Good for
  • Starting a new conversation to set skill-first discipline across all subsequent tasks
  • Debugging a complex problem by ensuring systematic-debugging skill is invoked before exploration
  • Building a feature by invoking brainstorming skill before implementation skills
  • Preventing ad-hoc code exploration by checking for applicable skills first
  • Coordinating multi-skill workflows where process skills must run before domain-specific skills
Who it's for
  • AI agents (Claude Code, Cursor, Codex) executing user tasks
  • Teams establishing disciplined skill-based workflows
  • Projects requiring systematic approaches to debugging, design, and implementation

using-superpowers FAQ

What if I think a skill doesn't apply?

If there is even a 1% chance a skill might apply, you must invoke it. This is not negotiable. If it turns out wrong, you don't have to use it, but you must check first.

Should I clarify the request before invoking skills?

No. Skill checking comes before clarifying questions. Invoke relevant skills first, then ask clarifications if needed.

What if multiple skills apply?

Process skills (brainstorming, systematic-debugging) run first to set the approach, then implementation skills (frontend-design, etc.) carry it out.

Do user instructions override skills?

Yes. User instructions (CLAUDE.md, direct requests) take precedence over skills, which in turn override default behavior.

How do I know which platform adaptations apply?

Check if your harness (Claude Code, Codex, Pi, Antigravity, Hermes, Muse) appears in the Platform Adaptation section and read its reference file for special instructions.

Full instructions (SKILL.md)

Source of truth, from obra/superpowers.


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:

ThoughtReality
"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.