using-superpowers

Enforce skill invocation before AI agents respond to tasks.

7|Updated Dec 7, 2025
One-click install
npx skills add https://github.com/ftzi/livespec --skill using-superpowers-ftzi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/ftzi/livespec/tree/main/.agents/skills/using-superpowers
Command: npx skills add https://github.com/ftzi/livespec --skill using-superpowers-ftzi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill ensures that AI agents consistently leverage available tools and skills before attempting to answer a user's request, preventing premature or incomplete responses.

Core Features & Use Cases

  • Mandatory Skill Invocation: Enforces the use of relevant skills, even with a low probability of applicability.
  • Prioritization Logic: Defines an order for skill execution when multiple apply (process skills first, then implementation skills).
  • Use Case: When a user asks a question that might be answerable by a specific tool (e.g., "summarize this document"), this skill ensures the summarization skill is invoked first, rather than the AI attempting to answer from its general knowledge.

Quick Start

Use the relevant skill to address the user's request before providing any response.

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 agent invoke a skill before responding?

To make an AI agent invoke a skill before responding, you need a protocol that enforces mandatory skill utilization for any applicable task, ensuring agents leverage available tools before generating answers.

Why does my AI agent answer from general knowledge instead of using available tools?

An AI agent answers from general knowledge instead of using available tools when lacking an enforced invocation protocol. Without mandatory skill utilization, the agent attempts premature responses rather than checking for relevant skills.

What is the execution order when multiple agent skills apply to a single request?

The execution order for multiple applicable agent skills prioritizes process skills first, followed by implementation skills. This prioritization logic defines a clear decision flow for skill selection and execution.

Should an AI invoke a skill even if there is only a low probability it applies?

Yes, an AI should invoke a skill even with a low probability of applicability. Mandatory skill invocation ensures the agent checks relevant capabilities first, maximizing the utility of available agent tools and preventing incomplete responses.

How do I stop an AI workflow from generating incomplete responses without tool use?

To stop an AI workflow from generating incomplete responses without tool use, enforce a decision flow that requires agents to invoke relevant skills before performing actions. This maintains AI adherence to tool-use protocols.