Conciseness

The body is dense and mostly application-focused (tables mapping situations to models, concrete fixes like "Show customer count, testimonials, logos"), but it spends tokens on one-line definitions of biases Claude already knows ("Loss Aversion — People feel losses 2x more than gains", "Social Proof — People follow others"). This matches anchor 4 (efficient with minor over-explanation that could be trimmed) rather than 5; it is above anchor 3 because the padding is limited to the model definitions and the rest earns its place.

Actionability

For an instruction-only skill, the guidance is largely concrete: specific before/after CTA wording ("'Submit' or 'Get started' vs 'Start my free trial""), quantified rules ("Under $100: show % discount. Over $100: show $ discount", "Limit to 3 tiers"), and a situation-to-models quick reference covering common cases. It falls short of anchor 5 because the Communication section is underspecified ("Self-verify: source attribution, assumption audit, confidence scoring" gives no concrete procedure) and the 'Explain [principle]' mode depends on a catalog file that is not present in the bundle, leaving gaps in executable guidance.

Workflow Clarity

The three modes (Diagnose, Apply, Reference) and the five Task-Specific Questions provide a rough sequence, but there is no guidance on how to proceed through a mode (e.g., what steps a 'Diagnose' analysis follows), and validation is only vaguely present via "Self-verify: source attribution, assumption audit, confidence scoring" with no checkpoints or feedback loops. This matches anchor 3 (steps listed, checkpoints missing or implicit); it is above anchor 2 because the modes and questions do form a coherent rough sequence.

Progressive Disclosure

The body signals a single one-level-deep reference ("The full catalog lives in [references/mental-models-catalog.md]... Load it when you need to look up specific models or browse the full list"), but the bundle contains no references/ directory — the referenced file does not exist, so the skill's core detailed content is inaccessible. Judged against the actual bundle structure, this is a broken primary reference, fitting anchor 2 (minimal effective structure; the content that should be reachable is missing) rather than anchor 3, where references are at least present and real.

Specificity

The description names the domain ("apply psychological principles, mental models, or behavioral science to marketing") and one action ("apply"), plus a resource description ("provides 70+ mental models organized for marketing application"), but does not list the several concrete actions the skill actually performs (diagnose, recommend, explain). It matches anchor 3 (domain and 1-2 concrete actions, not comprehensive) rather than 4, which requires several specific actions; it exceeds anchor 2 because it goes beyond merely naming the domain.

Completeness

It explicitly answers both questions: what ("This skill provides 70+ mental models organized for marketing application") and when ("When the user wants to apply psychological principles... Also use when the user mentions..." with concrete trigger phrases). This matches anchor 5 exactly; it is not anchor 4 because the 'when' is fully explicit with enumerated concrete phrases rather than merely adequate.

Trigger Term Quality

It lists eight natural trigger phrases users would genuinely say: 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' 'consumer behavior.' Coverage including synonyms like 'why people buy' and 'consumer behavior' is comprehensive for this domain, matching anchor 5; only a marginal term like 'buyer psychology' is missing, which does not drop it to anchor 4.

Distinctiveness Conflict Risk

The description is clearly scoped to a niche ("behavioral science to marketing", "for marketing application") with distinct triggers, but broad terms like 'decision-making' and 'persuasion' could fire on non-marketing requests (career decisions, negotiation, general copywriting), creating minor overlap risk with closely related skills. This fits anchor 4 rather than anchor 5, whose conflict risk is minimal; it is well above anchor 3 because the marketing framing constrains most triggers.