domains / families / agent-tooling / using-superpowers

using-superpowers

combined

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

When to use

• This skill is applicable to execute the workflow or actions described in the overview.

When not to use

• Use this skill only when the task clearly matches the scope described above.
• Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
• Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

Skill page

Conflict

The copies overlap heavily on the core rule (invoke skills before any response), the red flags table, and skill priority. However, they disagree on the mechanism and contain material steps the others lack. The obra/superpowers copy is the canonical source but uses a different invocation model (announce and follow, no explicit Skill tool) and includes a Platform Adaptation section and a Subagent Stop guard. The other three copies (sickn33, LeoYeAI, FreedomIntelligence) are near-identical mirrors that explicitly mandate the use of the `Skill` tool and include a Graphviz flowchart. Crowning one would hide the real alternative between the 'announce/follow' model and the 'Skill tool' model.