Conciseness

The body is lean and dense — nearly all content is domain-specific data Claude does not reliably know (funnel healthy ranges, red-flag thresholds, sample-size floors, test priority order), delivered as compact tables and checklists rather than prose. It assumes competence ("You are a paywall conversion specialist...") and contains essentially no explanation of concepts Claude already knows. It does not fit anchor 4 because there is no over-explanation to trim.

Actionability

Mostly concrete and executable: the 7-element audit has specific criteria ("annual default-selected, savings %", "3–5 max, scannable in <3 seconds"), sample-size floors are quantified, test priorities are ordered, tools are named (Superwall, RevenueCat Experiments, Adapty), and a full output template is provided. It sits between anchors 4 and 5 because a few steps are soft — "If RevenueCat is connected, pull subscription metrics first" and "If `asc-metrics` is available, cross-check trial counts" give no concrete method, command, or screen for pulling the data.

Workflow Clarity

The sequence is clear and gated — Initial Assessment → "Diagnose Before You Redesign" (funnel table with red-flag thresholds, "Optimization targets that stage only") → audit → test playbook ("Test ONE element at a time", "ship one per cycle") → output template — with a checklist for the complex audit. It is not 5 because there is no explicit post-test feedback loop (no step for reading experiment results, deciding significance, or rolling back a losing variant), so validation is front-loaded but the recovery/checkpoint side is thinner than the anchor-5 example.

Progressive Disclosure

Good structure: well-organized sections with clear headers, a self-contained 135-line body, and clearly signaled cross-skill handoffs. At over 50 lines with several conditional lookup tables (placement strategy, pricing display patterns, sample sizes) and a full output template, the skill is somewhat larger than a lean overview, and this content could arguably live in one-level-deep reference files — a minor organization gap consistent with anchor 4 rather than the cleanly split, reference-navigated anchor-5 shape.

Specificity

The description enumerates comprehensive, concrete capability areas — "design, test, or optimize their app's paywall — layout, copy, pricing display, trial offers, plan structure, hard vs soft paywall, paywall placement, or paywall A/B tests" — covering the full scope of the niche with no significant gaps. It is not below 4 because the coverage is exhaustive within the domain, not just 'several specific actions with minor gaps'.

Completeness

Both 'what' (design/test/optimize paywalls across layout, copy, pricing display, trial offers, plan structure, placement, A/B tests) and 'when' (an explicit "Use when the user mentions..." clause with concrete trigger phrases) are clearly and explicitly stated. It cannot be 4 because the 'when' guidance is not merely present but maximally explicit with enumerated triggers.

Trigger Term Quality

Trigger terms are extensive and natural: "paywall", "paywall conversion", "trial-to-paid", "soft paywall", "hard paywall", "plan picker", "annual vs monthly display", "best paywall", "RevenueCat paywall", "Superwall", "Adapty", and even the colloquial "my paywall isn't converting". Includes synonyms, tool names, and a natural user complaint phrase — matching the anchor-5 standard of comprehensive natural-term coverage.

Distinctiveness Conflict Risk

A clear niche (paywall conversion) with distinct triggers, and it actively disambiguates from adjacent skills — "For overall pricing strategy and monetization model choice, see monetization-strategy. For trial nurture, dunning, and churn, see subscription-lifecycle. For where in the onboarding the paywall fires, see onboarding-optimization." This routing minimizes conflict risk with closely related skills, fitting the anchor-5 'clear niche with distinct triggers; minimal conflict risk'.