using-superpowers

Enforces skill discovery and invocation before any agent response or action.

Updated Aug 14, 2026
One-click install
npx skills add https://github.com/bill80362/laravel-thread-admin --skill using-superpowers-bill80362
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/bill80362/laravel-thread-admin/tree/main/.github/superpowers/using-superpowers
Command: npx skills add https://github.com/bill80362/laravel-thread-admin --skill using-superpowers-bill80362

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? AI agents often skip available skills and improvise answers, leading to inconsistent workflows and missed best practices. This Skill establishes a mandatory discipline: check for and invoke applicable skills before any response, including clarifying questions or codebase exploration. ## Core Features & Use Cases - Mandatory Skill-First Rule: Requires invoking any potentially relevant skill before responding, with a red-lines table that counters common rationalizations for skipping skills. - Skill Priority Routing: Defines precedence rules where process skills (brainstorming, systematic debugging) run before implementation skills, plus routing to Chinese-localized skills for Chinese-language projects. - Cross-Platform Tool Mappings: Ships reference files mapping Claude Code tool names to equivalents in Codex, Gemini CLI, Copilot CLI, Pi, Antigravity, Hermes Agent, and Qoder. - Use Case: An agent asked to "fix this bug" first invokes the systematic-debugging skill rather than jumping straight into editing code, ensuring a disciplined root-cause workflow. ## Quick Start Start every conversation by checking which skills apply to the user's request and invoke the matching skill 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 agent always use available skills before responding?

Install a meta-skill like this one that mandates skill invocation before any response, including clarifying questions. It defines red-line rules that treat rationalizations like "this is a simple question" as signals to stop and check skills first.

What is the correct order when multiple skills apply to one task?

Process skills take priority over implementation skills. For example, run brainstorming before building a feature, or systematic-debugging before applying domain-specific fix skills, then follow the implementation skill for execution.

Does this skill work with Gemini CLI, Codex, or Copilot CLI?

Yes, it includes reference files mapping Claude Code tool names to equivalents in Codex, Gemini CLI, Copilot CLI, Pi, Antigravity, Hermes Agent, and Qoder. Each platform file explains subagent dispatch, task tracking, and file operation equivalents.

Can user instructions override skill workflows?

Yes, user instructions from files like CLAUDE.md, AGENTS.md, or direct requests take priority over skills, and skills take priority over default behavior. Skills can only be skipped when the human explicitly says to skip them.

When should the Chinese-localized skills be triggered?

Chinese-specific skills activate when the project contains Chinese comments, a Chinese README, a .gitee directory, or Chinese commit history. They stack with translated process skills rather than replacing them, such as combining code review flow with Chinese review style.