using-superpowers

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

1|Updated May 3, 2021
One-click install
npx skills add https://github.com/leogurja/dotfiles --skill using-superpowers-leogurja
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/leogurja/dotfiles/tree/main/home/dot_agents/skills/using-superpowers
Command: npx skills add https://github.com/leogurja/dotfiles --skill using-superpowers-leogurja

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, clarifying question, or codebase exploration. ## Core Features & Use Cases - Mandatory Skill Invocation: Requires checking for and invoking applicable skills before any action, with a red-flags table that counters common rationalizations for skipping them. - Skill Priority Ordering: Defines that process skills (like brainstorming or systematic-debugging) run before implementation skills when multiple skills apply. - Cross-Platform Tool Mapping: Ships reference files mapping generic skill actions (subagent dispatch, task tracking, file operations) to concrete tools on Codex, Gemini CLI, Pi, Antigravity, and Hermes Agent. - Use Case: When a user says "fix this bug", the agent first invokes the systematic-debugging skill rather than immediately editing code, ensuring a disciplined debugging process. ## Quick Start Start a new conversation and ask the agent to build or fix something, and it will invoke the relevant 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 skills before responding?▼

Install this skill so it loads at conversation start. It instructs the agent to check for and invoke any relevant skill before responding, asking clarifying questions, or exploring files, and to announce which skill it is using.

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 when building something new, and systematic-debugging runs before domain skills when fixing a bug.

Does this skill work with Codex, Gemini CLI, and other AI coding tools?▼

Yes, it includes reference files mapping generic skill actions to platform-specific tools for Codex, Gemini CLI, Pi, Antigravity, and Hermes Agent. The agent reads the reference file matching its harness for correct tool usage.

How do I dispatch subagents on Gemini CLI from a skill?▼

Use the invoke_agent tool with agent_name set to generalist, passing a filled prompt template. Multiple invoke_agent calls in one response enable parallel subagent dispatch for independent tasks.

When should a skill not be invoked according to these rules?▼

Subagents dispatched to execute a specific task should ignore this skill, per the SUBAGENT-STOP block. User instructions in files like CLAUDE.md or AGENTS.md also take precedence over skill workflows.