The body is lean with no padding of concepts Claude already knows; each test is compact and every section earns its place, matching the 'lean and efficient' anchor.

As an instruction-only skill, it gives concrete actionable guidance — three named tests each with a Question, Example, and Verdict, plus a copy-paste-ready Decision Matrix; per the scoring notes, the absence of code is not penalized because the guidance is actionable.

The three tests are clearly sequenced and the Validation section provides explicit checkpoints (confirm all three tests applied, verify exclusion of 非人情, check that passers proceed to further evaluation); this is not a destructive/batch operation so no feedback-loop cap applies.

This is a simple skill under 50 lines with no external references, and the content is well-organized into clear sections (Overview, Core Principle, Evaluation Criteria, Decision Matrix, Expected Outcomes, Validation), satisfying the guideline that such skills can score 3 on organization alone.

The description names the concrete method ("Applies Guan Zhong's humanity test (非人情)") and enumerates the specific bonds tested — "parental, family, and self-preservation" — matching the anchor for multiple specific concrete actions.

It explicitly answers both halves — what ("Applies Guan Zhong's humanity test... to identify dangerous individuals") and when ("Use when vetting subordinates or appointees for trustworthiness") — with an explicit trigger clause.

It leads with the natural trigger phrasing "Use when vetting subordinates or appointees for trustworthiness", terms a user would plausibly say; it is not at score 2 because it covers common variations rather than a single narrow term.

The Guan Zhong humanity test / 非人情 framing is a highly distinctive niche unlikely to trigger for unrelated skills; it would not be at score 2 because the trigger is specific rather than broadly overlapping.