Lean, well-organized prose that assumes Claude's competence without explaining basic concepts; every section earns its place (Purpose, Modes, Rules, Paradigm Mapping, Workflow).

Highly actionable instruction-only guidance: explicit classification vocabularies, a concrete output contract (Firm findings / Inferences / Open questions / build order), quoted prompt patterns, specified flow-audit fields, and exact persistence artifact names with prefixes.

A clearly sequenced 5-phase workflow (Orientation through Final Assessment) with provisional-validation checkpoints ('Treat this as provisional until the boundary audit is done', 'Only move the order around when the evidence is strong'); this interactive diagnostic does not require batch/destructive feedback loops.

A single cohesive diagnostic flow with clearly labeled sections and no nested/deep references; it needs no external bundle files and is well-organized as one overview.

Lists multiple concrete actions ('map their company to the right world-model paradigm', 'identify where the highest-fidelity signal lives', 'audit the boundary layer', 'flag simulated-judgment exposure', 'leave with a first/second/third build sequence'), matching the multi-action anchor; uses third person.

Explicitly answers both what ('Twenty-minute conversational diagnostic for assessing...') and when via a detailed 'Use when the user wants to...' clause.

Contains relevant terms ('world-model paradigm', 'boundary layer', 'simulated-judgment exposure') but leans on specialized jargon rather than natural phrasings a user would say verbatim; the body's trigger prompts show better natural phrasing that the description itself lacks.

A clearly defined niche (world-model readiness, boundary-layer auditing, simulated-judgment exposure) with distinct triggers unlikely to overlap with unrelated skills.