using-superpowers

Enforce mandatory skill invocation by AI agents before any response.

Updated Mar 14, 2026

Search Tags:#workflow #prompt engineering #skills #ai agent #tool usage #invocation

Ready to run

npx skills add https://github.com/marcusfelix/barney --skill using-superpowers-marcusfelix

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/marcusfelix/barney/tree/main/src/prompts/skills/using-superpowers
Command: npx skills add https://github.com/marcusfelix/barney --skill using-superpowers-marcusfelix

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill ensures that AI agents correctly identify and invoke relevant skills before responding, preventing them from bypassing crucial workflows or providing incomplete answers.

Core Features & Use Cases

Mandatory Skill Invocation: Enforces the use of skills when there's even a slight chance they apply.
Instruction Hierarchy: Clarifies that user instructions always override skill behavior.
Platform Adaptation: Provides guidance on tool mapping for different AI environments (Claude Code, Gemini CLI).
Use Case: When asked a question that could be answered by a skill, the AI must first attempt to invoke the relevant skill, rather than answering directly.

Quick Start

Always invoke any potentially relevant skill before generating a response or asking clarifying questions.

Frequently Asked Questions about using-superpowers

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

FAQPage Schema

How do I force an AI agent to invoke relevant skills before generating a response?▼

To enforce mandatory skill invocation, you need a protocol that prevents AI agents from answering directly and requires them to check predefined workflows before taking action or responding to user queries.

Why does my AI agent bypass prompt engineering workflows and rationalize answers?▼

AI agents bypass workflows and rationalize answers when strict skill activation protocols are missing, allowing them to skip tool mapping and provide direct responses instead of invoking relevant skills.

Can I use mandatory skill invocation across different AI platforms like Claude Code and Gemini CLI?▼

Yes, mandatory skill invocation can be adapted for different AI platforms by applying platform-specific tool mapping guidance for environments like Claude Code and Gemini CLI to ensure correct skill activation.

What is the best way to ensure AI tool usage adherence during conversational turns?▼

The best way to ensure tool usage adherence is applying a mandatory invocation protocol across all conversational turns and task executions, forcing the AI to attempt relevant skill activation before asking clarifying questions.

Do user instructions override mandatory AI skill activation protocols?▼

Yes, user instructions always override skill behavior, establishing an instruction hierarchy where direct user commands take precedence over the enforced skill invocation protocols during task execution.