using-superpowers

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

Updated Aug 20, 2026
One-click install
npx skills add https://github.com/Pega88/agy-superpowers --skill using-superpowers-pega88
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: using-superpowers
Source: https://github.com/Pega88/agy-superpowers/tree/main/.agents/plugins/superpowers/skills/using-superpowers
Command: npx skills add https://github.com/Pega88/agy-superpowers --skill using-superpowers-pega88

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 located and 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, with a red-flags table that counters common rationalizations for skipping them. - Skill Priority Ordering: Defines that process skills (brainstorming, systematic-debugging) run before implementation skills when multiple skills apply. - Cross-Platform Tool Mapping: Ships reference files mapping skill actions to native tools on Antigravity CLI, Gemini CLI, Codex, Pi, and Hermes Agent. - Use Case: When a user says "fix this bug", the agent invokes the systematic-debugging skill first instead of immediately editing code, ensuring root-cause analysis precedes any fix. ## Quick Start Start any conversation by checking which superpowers 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 always use available skills before responding?

Install a meta-skill like using-superpowers that mandates skill invocation before any response, including clarifying questions. It instructs the agent to announce which skill it is using and follow that skill's checklist exactly.

What is the correct order when multiple agent skills apply to one 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 using-superpowers work with Gemini CLI and Antigravity CLI?

Yes, it includes reference files mapping skill actions to native tools on Antigravity CLI, Gemini CLI, Codex, Pi, and Hermes Agent. Each file translates actions like subagent dispatch and task tracking into that platform's actual tool calls.

How are subagents dispatched on Antigravity CLI from skills?

Skills dispatch subagents through Antigravity's invoke_subagent tool, using TypeName self for implementation work and research for read-only analysis. Subagents run asynchronously in the background and notify the parent agent on completion.

When should a subagent ignore the using-superpowers skill?

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