using-superpowers

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

1|Updated Oct 11, 2025
One-click install
npx skills add https://github.com/ibytechaos/claude --skill using-superpowers-ibytechaos
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/ibytechaos/claude/tree/main/plugins/superpowers/skills/using-superpowers
Command: npx skills add https://github.com/ibytechaos/claude --skill using-superpowers-ibytechaos

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? AI assistants often skip available skills and respond directly, missing established workflows like TDD, debugging, or brainstorming. This Skill establishes a mandatory protocol that forces the assistant to check for and invoke relevant skills before any response, including clarifying questions. ## Core Features & Use Cases - Mandatory Skill Check: Requires invoking any potentially relevant skill (even at 1% relevance) before responding or acting. - Instruction Priority Framework: Defines a clear hierarchy where user instructions (CLAUDE.md, AGENTS.md) override skill defaults, which override system prompt behavior. - Cross-Platform Tool Mapping: Ships reference guides mapping Claude Code tools to Codex and Gemini CLI equivalents for portable skill execution. - Use Case: When a user asks to fix a bug, the assistant invokes the debugging skill first rather than improvising, ensuring disciplined, repeatable workflows. ## Quick Start Start a new conversation and ask the assistant to fix a bug, then observe it invoke the relevant debugging 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 Claude Code always check for skills before responding?

Install this skill so it loads at conversation start. It instructs the assistant to invoke any potentially relevant skill via the Skill tool before responding, including before clarifying questions or codebase exploration.

What happens when multiple skills apply to the same task?

Process skills like brainstorming and debugging take priority over implementation skills like frontend-design. For example, a build request triggers brainstorming first, then implementation skills guide execution.

Do user instructions override skill workflows like TDD?

Yes. User instructions in CLAUDE.md, GEMINI.md, or AGENTS.md have the highest priority. If your config says not to use TDD, that overrides any skill mandating it.

Can I use superpowers skills with Gemini CLI or Codex?

Yes. The skill includes reference files mapping Claude Code tools to Gemini CLI equivalents like activate_skill and write_todos, and to Codex equivalents like spawn_agent and update_plan.

Why does the assistant skip skills even when they exist?

Assistants rationalize skipping skills with thoughts like 'this is just a simple question' or 'I remember this skill.' This skill lists those rationalizations as red flags and mandates invocation even at 1% relevance.