using-superpowers

Check for and invoke relevant skills before responding to requests.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/tDalile/dotfiles --skill using-superpowers-tdalile
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/tDalile/dotfiles/tree/main/agents/skills/using-superpowers
Command: npx skills add https://github.com/tDalile/dotfiles --skill using-superpowers-tdalile

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill ensures that agents check for and invoke specialized skills before taking any action or producing any response, preventing ad-hoc behavior and ensuring the correct workflows, tools, and subagents are used when relevant.

Core Features & Use Cases

  • Mandatory skill check: Forces a skill invocation check at the start of a conversation or before plan/execution steps, even for clarifying questions.
  • Platform mappings: Provides platform-specific tool mappings (Claude Code, Gemini CLI) and guidance for invoking skills and subagents.
  • Workflow governance: Establishes priority rules (user instructions > superpowers > default system prompt) and a checklist-driven flow for plan execution and task delegation.
  • Use Case: When a user requests "Help fix this bug", run the brainstorming/debugging skill invocation flow first, then follow the prioritized implementation skill.

Quick Start

Invoke the using-superpowers skill before responding to determine if a specialized skill or subagent should be loaded for the user's request.

Frequently Asked Questions about using-superpowers

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

FAQPage Schema
How do I enforce skill invocation checks before an AI agent generates a response?

To enforce skill invocation checks before an agent replies, apply a mandatory workflow governance layer at the start of all conversations. This forces the agent to evaluate and load relevant specialized procedures before producing any output or execution plans.

What is the best way to prevent ad-hoc behavior in agent workflows during software engineering?

The best way to prevent ad-hoc agent behavior is to establish priority rules that require checking for specialized skills before taking action. This ensures correct workflows, tools, and subagents are automatically applied to domain-specific software engineering requests.

Can I use platform-specific tool mappings to dispatch subagents in Claude Code or Gemini CLI?

Yes, platform-specific tool mappings support invoking skills and dispatching subagents in environments like Claude Code and Gemini CLI. The system provides tailored guidance for each platform to ensure proper skill loading and specialized workflow activation.

How do priority rules work when user instructions conflict with system prompts during agent execution?

Priority rules dictate that user instructions always override both the superpowers layer and the default system prompt. This hierarchy ensures the agent respects explicit user commands while still attempting to apply specialized skill workflows where applicable.

When should I run a skill discovery check during an agent conversation?

You should run a skill discovery check at the start of every conversation and before any plan or execution steps. This mandatory check determines whether to load specialized skills, dispatch subagents, or follow specific workflows before proceeding.