using-superpowers

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

Updated Aug 3, 2026
One-click install
npx skills add https://github.com/Yvesdefaria/GymLab --skill using-superpowers-yvesdefaria
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/Yvesdefaria/GymLab/tree/main/.opencode/skills/using-superpowers
Command: npx skills add https://github.com/Yvesdefaria/GymLab --skill using-superpowers-yvesdefaria

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 Rules: Defines ordering so process skills (like brainstorming or systematic-debugging) run before implementation skills. - Platform Adaptation: Ships reference files mapping generic skill actions (subagent dispatch, task tracking) 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 jumping straight into editing code. ## Quick Start Start any conversation by invoking the relevant skill before responding, then announce which skill you are using and follow it exactly.

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?

Invoke the relevant skill before any response, including clarifying questions or file exploration. Announce which skill you are using and follow its instructions exactly, creating a todo per checklist item if one exists.

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 precedes frontend-design when building a feature, and systematic-debugging precedes domain skills when fixing a bug.

Does this skill work with Gemini CLI and Codex?

Yes, it includes reference files mapping skill actions to platform tools. Gemini CLI uses activate_skill and invoke_agent, while Codex requires enabling multi_agent in config.toml and uses spawn_agent for subagent dispatch.

When should a subagent ignore this skill?

A subagent dispatched to execute a specific task should ignore this skill entirely, as stated in the SUBAGENT-STOP block. The skill governs top-level conversation behavior, not delegated task execution.

Do user instructions override skill workflows?

Yes, user instructions from files like CLAUDE.md, AGENTS.md, or direct requests take precedence over skills. Only skip skill workflows when the human partner has explicitly told you to.