using-superpowers

Enforces mandatory skill discovery and invocation before any AI response or action.

92|12|Updated Dec 21, 2025
One-click install
npx skills add https://github.com/ARounder-183/HiFiShifter --skill using-superpowers-arounder-183
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/ARounder-183/HiFiShifter/tree/main/.github/skills/using-superpowers
Command: npx skills add https://github.com/ARounder-183/HiFiShifter --skill using-superpowers-arounder-183

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI assistants often skip available skills and improvise answers, leading to inconsistent workflows and missed process discipline. This Skill establishes a mandatory protocol that forces the assistant to check for and invoke relevant skills before responding to any user message, including clarifying questions. ## Core Features & Use Cases - Mandatory Skill Check: Requires invoking the Skill tool whenever there is even a small chance a skill applies, before any response or exploration. - Decision Flowchart: Provides a graph-based decision flow covering skill invocation, announcement, checklist handling, and TodoWrite task creation. - Rationalization Detection: Lists common red-flag thoughts (e.g., "this is just a simple question") that signal improper skill avoidance. - Priority Ordering: Defines precedence when multiple skills apply, putting process skills like brainstorming and debugging before implementation skills. - Use Case: When a user asks to fix a bug, the assistant first invokes the debugging skill, announces its use, creates todos from its checklist, and only then proceeds with the fix. ## Quick Start Ask the assistant to start any task and it will check for applicable skills, invoke the relevant one, and announce its use before responding.

Frequently Asked Questions about using-superpowers

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I make an AI assistant always use available skills?

Install a skill-enforcement instruction that requires invoking the Skill tool before any response, including clarifying questions. This skill mandates invocation whenever there is even a small chance a skill applies, preventing the assistant from improvising.

What is the correct order when multiple skills apply to a task?

Process skills such as brainstorming and debugging come first because they determine how to approach the task. Implementation skills like frontend-design or mcp-builder come second to guide execution.

Should skills be invoked for simple questions?

Yes. Questions count as tasks, and the skill check happens before any response. The instructions explicitly list "this is just a simple question" as a rationalization red flag that should trigger a skill check instead.

How does skill invocation work in Claude Code?

Use the Skill tool to invoke a skill, which loads its content directly into context for you to follow. Never use the Read tool on skill files, since invocation is the supported loading mechanism.

What happens if an invoked skill turns out to be irrelevant?

You can discard it. The rule requires invoking any skill that might apply, but if the loaded skill does not fit the situation, you are not obligated to follow it.

Do user instructions override skill workflows?

No. User instructions specify what to do, not how to do it. A request like "add X" or "fix Y" does not exempt the assistant from following the workflows defined by applicable skills.