What problem does it solve? Recruiting and assessment products often overclaim leadership potential from thin evidence like a single conversation, a resume, or a screenshot. This Skill applies Claudio Fernández-Aráoz's publicly documented potential model (motivation, curiosity, insight, engagement, determination) to review whether evidence actually supports potential-related claims, and forces abstention when it does not. ## Core Features & Use Cases - Evidence Sufficiency Gate: Requires a defined target role, multiple independent behavioral episodes, concrete outcomes, corroboration beyond self-description, and disconfirming evidence before any potential judgment is allowed. - Structured Review Workflow: Separates current performance, readiness for a named next role, and long-term potential, then scores each trait against a 0-4 rubric with explicit anti-patterns (e.g., verbosity is not curiosity, overwork is not determination). - Product and UI Review: Evaluates assessment interfaces for provenance, longitudinal views, counterevidence, and prominent uncertainty, rejecting single composite potential scores. - Use Case: A recruiter reviews a candidate profile generated from one interview transcript. The Skill returns abstain with score: null, flags the insufficient evidence, and recommends a structured follow-up question and an independent reference source instead of a speculative trait label. ## Quick Start Use executive-potential-evidence to review whether the evidence in this candidate file supports any claim about leadership potential, and abstain if it does not.
