using-superpowers
The using-superpowers skill enforces a mandatory protocol for AI agents to identify and invoke relevant skills before performing any action, including clarifying questions or information gathering.
Is using-superpowers safe to install?
Safe to install: our audit of using-superpowers's source files found 0 shell commands, 0 external URLs, no file writes (none risk). Every command and URL listed appears verbatim in the skill's source. This skill consists of behavioral instructions for the agent and does not perform file operations or network requests.
How we audit skills: our security review methodology.
Who is this skill for?
AI agents operating within a system that utilizes a library of specialized skills.
What can you do with it?
- Establishing a mandatory skill-check protocol at the start of every conversation.
- Prioritizing process-oriented skills like brainstorming or systematic-debugging before implementation tasks.
- Preventing agent rationalization that attempts to bypass formal skill workflows.
- Integrating platform-specific instructions from reference files like codex-tools.md or pi-tools.md.
How good is this skill?
Quality score: 5/10. The skill provides clear, actionable behavioral constraints for agents. The documentation is concise and includes specific red flags to prevent common agent errors.
What does the skill file contain?
<SUBAGENT-STOP> If you were dispatched as a subagent to execute a specific task, ignore this skill. </SUBAGENT-STOP> <EXTREMELY-IMPORTANT> If you think there is even a 1% chance a skill might apply to what you are doing, you ABSOLUTELY MUST invoke the skill. IF A SKILL APPLIES TO YOUR TASK, YOU DO NOT HAVE A CHOICE. YOU MUST USE IT. This is not negotiable. You cannot rationalize your way out of this. </EXTREMELY-IMPORTANT> ## The Rule **Invoke relevant or requested skills BEFORE any response or action** — including clarifying questions, exploring the codebase, or checking files. If it tur...
Frequently asked questions
When must an agent invoke a skill?
The agent must invoke a skill before any response or action, including clarifying questions, codebase exploration, or file checks.
What happens if multiple skills apply to a task?
The agent must process skills first to set the approach, followed by implementation skills.
Can an agent skip a skill if it seems like overkill?
No. The instructions state that if a skill exists, the agent must use it.
Do user instructions override these skill requirements?
Yes. Direct user instructions take precedence over skills.