Use when an agent is about to plan, choose an approach, do non-trivial coding, refactor, decompose work, or delegate and the quality of execution depends on exposing assumptions before acting. Run a concise Socratic self-Q&A to clarify the goal, surface unknowns, pressure-test risks, choose an approach, and define the next action. Default to one round and open a second round only when risk, ambiguity, missing constraints, or live tradeoffs remain unresolved.

Install

openclaw skills install @hongyi3/socrates