using-superpowers

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

Updated Sep 11, 2026
One-click install
npx skills add https://github.com/CYRUS-pinto/pi-bot --skill using-superpowers-cyrus-pinto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/CYRUS-pinto/pi-bot/tree/main/.agents/skills/using-superpowers
Command: npx skills add https://github.com/CYRUS-pinto/pi-bot --skill using-superpowers-cyrus-pinto

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 process steps. This Skill establishes a mandatory rule that relevant skills must be invoked before any response, including clarifying questions or codebase exploration. ## Core Features & Use Cases - Mandatory Skill Invocation: Requires checking for and invoking applicable skills before any response or action, with a red-flags table that counters common rationalizations for skipping skills. - Skill Priority Ordering: Defines that process skills (like brainstorming or systematic-debugging) run before implementation skills when multiple skills apply. - Platform Adaptation: Ships reference files mapping generic skill actions (subagent dispatch, task tracking, file operations) to concrete tools on Codex, Pi, Antigravity, Hermes Agent, and Gemini CLI. - Use Case: When a user says "fix this bug", the agent invokes the systematic-debugging skill first rather than jumping straight into editing code. ## Quick Start Start any conversation by checking which skills apply to the 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 use skills before responding?

Install a skill-enforcement skill like this one that mandates invoking relevant skills before any response, including clarifying questions. It provides a red-flags table that counters common rationalizations for skipping skill checks.

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

Process skills come first because they set the approach, then implementation skills carry it out. For example, brainstorming runs before frontend-design, and systematic-debugging runs before domain-specific fix skills.

Does this skill work with Codex, Gemini CLI, and other agent harnesses?

Yes, it includes platform adaptation reference files for Codex, Pi, Antigravity, Hermes Agent, and Gemini CLI. Each file maps generic skill actions like subagent dispatch and task tracking to that platform's concrete tools.

How do I dispatch subagents on platforms without a built-in subagent tool?

On Pi, use the optional pi-subagents package which provides a subagent tool with single, chain, parallel, and async workflows. If no subagent tool exists, execute sequentially in the current session rather than fabricating tool calls.

When should a skill be skipped during a task?

Only skip skill workflows when the user has explicitly instructed you to, since user instructions take precedence over skills. Subagents dispatched for a specific task should also ignore this skill per its SUBAGENT-STOP directive.