Conciseness

The ~450-line body is dominated by definitions of concepts Claude already knows — e.g., 'Losses feel roughly twice as painful as equivalent gains feel good', 'People follow what others are doing. Popularity signals quality and safety', 'Roughly 80% of results come from 20% of efforts' — which is the 'extensively explains concepts Claude already knows' failure mode. It is not a 1 only because the one-line 'Marketing application' per model is genuine added value and the per-model format is tight rather than padded prose.

Actionability

There is some concrete guidance — '$3/day' feels different than '$90/month', 'Three pricing tiers beat seven', 'Show the higher price first' — plus a 4-step usage process and a challenge-to-models quick reference table. It stops at 3 because the skill describes and catalogues rather than instructs: no worked examples, copy snippets, pricing layouts, or procedures showing how to actually apply a model end-to-end.

Workflow Clarity

The 'How to Use This Skill' section lists a coherent 4-step sequence ('Identify which mental models apply... Explain the psychology... Provide specific marketing applications... Suggest how to implement ethically'), matching the anchor 'steps listed but validation gaps'. It is not 4 because there is no checkpoint for choosing among ~60 overlapping models (beyond the quick-reference table) and the closing question 'Have you tested this with real customers?' is posed to the user rather than built into the workflow; it is not 2 because the sequence that exists is clear and well-ordered, and the skill involves no risky operations requiring validation loops.

Progressive Disclosure

The body has real structure — seven themed sections, a 'Quick Reference' mapping challenges to models, and a 'Related Skills' list — but roughly 400 lines of reference catalog that clearly belongs in separate per-category files is inlined entirely in SKILL.md, with no references/, scripts/, or assets/ present at all. This matches 'some structure but could be better organized; content that should be separate is inline' rather than 2, which requires minimal structure.

Specificity

The description lists several concrete capability areas — 'persuasion, consumer behavior, decision-making, framing, and ethical nudges' — which parallels the anchor-4 example of several specific actions with minor gaps. It falls short of 5 because the single verb 'Apply' governs topic nouns rather than a comprehensive set of distinct concrete actions.

Completeness

It explicitly answers both questions: what it does ('Apply psychological principles, mental models, and behavioral science to marketing, including persuasion, consumer behavior, decision-making, framing, and ethical nudges') and when to use it ('Use for questions about why people buy or how people think in a marketing context') — a concrete, explicit trigger clause mirroring the anchor-5 example. A score of 4 would require the 'when' to be less explicit than it is.

Trigger Term Quality

It includes natural phrases users would say ('why people buy', 'persuasion', 'framing', 'nudges', 'consumer behavior'), matching the 'good keyword coverage; a few natural terms missing' anchor. Not 5 because common variations like 'behavioral economics', 'consumer psychology', 'pricing psychology', or 'influence' are absent.

Distinctiveness Conflict Risk

It carves a clear niche (psychology applied to marketing) with distinct triggers ('why people buy', 'how people think in a marketing context') that would not fire for unrelated skills; the voice is third-person ('Apply...'), so no voice penalty applies. Overlap with closely related sibling skills (cro, copywriting) is minor and those are explicitly cross-referenced, not competing on the same triggers.