meta

Use at the start of any session or when a task has no clear skill assignment—routes the request to the correct skill family and establishes workflow chain context.

Compresses domain mastery using Ultralearning and Metacognition principles — moving from passive consumption to active production through directness, retrieval practice, and feedback loops. Use when learning a new domain rapidly, building a study plan, or preparing for a high-stakes professional skill.

Use when a problem spans multiple disciplines or when single-domain thinking has produced stale analysis—applies Munger's latticework of mental models across physics, biology, and psychology.

Engineers prompts into clear, structured, model-optimized instructions using the 4-D methodology (Deconstruct, Diagnose, Develop, Deliver) with architecture-specific tuning. Use when a draft prompt, instruction set, or agent skill description needs refinement for clarity or improved performance.

Invoke before responding to any non-trivial task—enforces the 1% rule that if any skill has even a 1% chance of improving output, it must be invoked first.

Enforces a test-driven approach to skill authoring — defining what a skill must achieve before writing content to prevent hallucinated utility or ungrounded advice. Use when creating new skills, editing existing ones, or verifying skill quality before deployment.