using-superpowers

Prioritizes Skill selection before responding to ensure workflows follow established rules and constraints.

15|2|Updated Jun 21, 2026

Search Tags:#workflow #safety #ai-agent #prompt-injection #skill-invocation

Ready to run

npx skills add https://github.com/Liuchun-oss/codelf-agent --skill using-superpowers-liuchun-oss

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/Liuchun-oss/codelf-agent/tree/main/resources/skills/using-superpowers
Command: npx skills add https://github.com/Liuchun-oss/codelf-agent --skill using-superpowers-liuchun-oss

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enforces an explicit, tool-guided decision process by ensuring the appropriate Skill is invoked before any reply, anchoring interactions to a structured, safe, and repeatable workflow.

Core Features & Use Cases

Ensures upfront Skill invocation to determine the applicable tools and constraints.
Guides conversations through a deterministic Skill-first protocol, minimizing misinterpretation and scope drift.
Useful for complex tasks that span planning, tool use, and safety checks, such as multi-step data gathering or tool orchestration.

Quick Start

Invoke the Skill tool before any response and follow the loaded guidance to respond.

Frequently Asked Questions about using-superpowers

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

FAQPage Schema

How do I ensure an AI agent invokes the right skill before replying?▼

To ensure an AI agent invokes the right skill, enforce an explicit, tool-guided decision process that loads applicable tools and constraints before generating a final answer. This structured workflow minimizes scope drift and misinterpretation.

What is the best way to prevent prompt injection in multi-step AI agent workflows?▼

The best way to prevent prompt injection in multi-step workflows is to apply a skill-first protocol with enforced safety guardrails, guiding conversations through deterministic tool use and safety checks before any response is generated.

How do I stop scope drift when orchestrating tools with an AI agent?▼

To stop scope drift during tool orchestration, enforce upfront skill invocation to determine the applicable tools and constraints. This deterministic skill-first protocol minimizes misinterpretation and keeps complex tasks on track.

Can I enforce safety guardrails before an AI agent responds to a complex query?▼

Yes, you can enforce safety guardrails by applying a skill-first protocol that requires the AI agent to identify and load applicable skills following priority rules, ensuring all guidance is followed before producing a final answer.

When do I need a deterministic skill invocation protocol for AI agents?▼

You need a deterministic skill invocation protocol for complex tasks that span planning, tool use, and safety checks, such as multi-step data gathering or tool orchestration, ensuring a structured and repeatable workflow.