using-superpowers

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

Updated Jun 8, 2026
One-click install
npx skills add https://github.com/Avistian/nba --skill using-superpowers-avistian
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/Avistian/nba/tree/main/.cursor/skills/using-superpowers
Command: npx skills add https://github.com/Avistian/nba --skill using-superpowers-avistian

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI assistants often skip available skills and answer directly, missing workflows that would produce better results. This Skill establishes a mandatory protocol that forces the assistant to check for and invoke relevant skills before any response, including clarifying questions. ## Core Features & Use Cases - Mandatory Skill Check: Requires invoking any skill with even a 1% chance of applying before responding or acting. - Decision Flowchart: Provides a graph-based decision process covering skill invocation, announcement, and checklist-driven execution via TodoWrite. - Rationalization Detection: Lists common red-flag thoughts that signal the assistant is skipping skills, with corrections for each. - 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 build a feature, the assistant invokes the brainstorming skill first, then implementation skills, instead of jumping straight to code. ## Quick Start Start a new conversation and ask the assistant to build or fix anything, and it will check for applicable skills 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 check for skills before answering?▼

Install this skill so it loads at conversation start. It instructs the assistant to invoke any potentially relevant skill before responding, including before clarifying questions, and lists rationalizations to avoid.

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 follow to guide execution.

Does this skill work outside Claude Code?▼

Yes, but the invocation mechanism differs. In Claude Code you use the Skill tool; in other environments you follow that platform's documentation for how skills are loaded and presented.

When should a rigid skill versus a flexible skill be adapted?▼

Rigid skills like TDD and debugging must be followed exactly without adapting away discipline. Flexible skills present patterns that can be adapted to context, and the skill itself states which type it is.

Why does the assistant skip skills even when they exist?▼

Assistants rationalize skipping with thoughts like 'this is a simple question' or 'I need context first'. The skill lists these red flags explicitly and requires a skill check before any action regardless.