using-superpowers

Enforces skill discovery and invocation before any response across Claude Code, Codex, Copilot CLI, and Gemini CLI.

Updated May 21, 2026
One-click install
npx skills add https://github.com/CagesThrottleUs/private-ai-harness --skill using-superpowers-cagesthrottleus
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/CagesThrottleUs/private-ai-harness/tree/main/skills/using-superpowers
Command: npx skills add https://github.com/CagesThrottleUs/private-ai-harness --skill using-superpowers-cagesthrottleus

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? AI coding agents often skip available skills and improvise workflows from scratch, leading to inconsistent results. This Skill establishes a mandatory startup protocol that forces the agent to check for and invoke relevant skills before any response, including clarifying questions or codebase exploration. ## Core Features & Use Cases - Mandatory Skill-First Rule: Requires invoking any potentially applicable skill before responding, with a red-flags table that counters common rationalizations for skipping skills. - Skill Priority Ordering: Directs process skills (brainstorming, systematic-debugging) to run before implementation skills when multiple skills apply. - Cross-Platform Tool Mapping: Ships reference guides translating Claude Code tool names to Codex, Copilot CLI, and Gemini CLI equivalents, including subagent dispatch conventions. - Use Case: A user asks the agent to fix a bug; instead of diving into files, the agent first invokes the systematic-debugging skill, then follows its structured workflow on the correct platform. ## Quick Start Start a new conversation and ask the agent to fix a bug, then confirm it announces and invokes the systematic-debugging skill before taking any action.

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 always check for skills before responding?

Install a startup skill that mandates skill invocation before any response, including clarifying questions or file exploration. This skill establishes that rule and provides a red-flags table to catch rationalizations for skipping it.

How to use Claude Code skills in Codex or Gemini CLI?

Skills written with Claude Code tool names can run on other platforms using tool-mapping references. This skill includes codex-tools.md, copilot-tools.md, and gemini-tools.md, which map tools like Task, TodoWrite, and Skill to each platform's native equivalents.

Does this skill work with GitHub Copilot CLI?

Yes, it supports Copilot CLI through a dedicated reference file mapping Claude Code tools to Copilot equivalents such as view, edit, task, and the skill invocation command. The agent reads this reference before its first tool call.

What happens when multiple skills apply to one task?

Process skills run first to set the approach, then implementation skills carry it out. For example, brainstorming precedes implementation skills for new features, and systematic-debugging precedes domain skills for bug fixes.

When should a subagent ignore this skill?

Subagents dispatched to execute a specific task should ignore this skill entirely, as stated in its SUBAGENT-STOP block. The skill governs top-level conversation startup, not delegated task execution.