The description names the domain (in-app paywalls, upgrade screens) and some actions ('create or optimize'), but doesn't list multiple specific concrete actions like 'design paywall layouts, write upgrade copy, A/B test conversion flows.' The actions remain somewhat high-level.

Clearly answers both 'what' (create/optimize in-app paywalls, upgrade screens, upsell modals, feature gates) and 'when' with an extensive explicit trigger list and a 'Use when' equivalent clause. Also explicitly distinguishes from related skills (page-cro, pricing-strategy).

Excellent coverage of natural trigger terms including 'paywall,' 'upgrade screen,' 'upsell,' 'feature gate,' 'freemium conversion,' 'trial expiration screen,' 'limit reached screen,' 'how do I get users to pay,' and many more variations that users would naturally say.

Explicitly carves out its niche by distinguishing from 'page-cro' (public pricing pages) and 'pricing-strategy,' and focuses specifically on in-product upgrade moments. The boundary 'where the user has already experienced value' is a clear differentiator.

The skill is reasonably organized but includes some unnecessary framing ('You are an expert...') and sections that could be tightened. The core principles section states things Claude already understands about UX (e.g., 'Don't trap or pressure'). Some bullet points are vague filler rather than actionable content.

The wireframe-style templates for feature lock, usage limit, and trial expiration paywalls provide concrete patterns, which is good. However, much of the content remains at the level of general advice ('Show, Don't Just Tell', 'Friction-Free Path') rather than specific, executable guidance. There are no real code examples, copy formulas with fill-in variables, or detailed implementation steps.

The initial assessment section provides a reasonable sequence (check context file → understand upgrade context → product model → user journey), and there's a logical flow from trigger points to screen components to optimization. However, there are no explicit validation checkpoints or feedback loops — for instance, no step to verify the paywall design against anti-patterns before shipping, or to validate A/B test setup before launch.

There is one reference to an external file (references/experiments.md) and related skills are listed at the bottom, which is good. However, the main file is quite long with sections like anti-patterns, timing rules, and A/B testing that could be split into reference files. The content is somewhat monolithic for its length.