using-superpowers
Bootstrap skill that forces skill discovery and invocation before any response, even clarifying questions.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for using-superpowers, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
The superpowers meta-skill loaded at conversation start. It establishes how to find and invoke other skills and demands the agent invoke any potentially-applicable skill (even at 1% relevance) before responding. High security relevance: it is an EXTREMELY-IMPORTANT instruction that reshapes the agent's control flow for the whole session.
Key features and capabilities
- Forces pre-response skill invocation
- Skill-discovery bootstrap
- Subagent opt-out clause
Use cases
- Establishing skill usage at session start
- Ensuring relevant skills are always applied