Conciseness

Assumes Claude's competence throughout — no explanations of known concepts — and every section is skill-specific, but the ~40-line inline worked example overlaps the external references/comparison-template.md and rhetorical flourishes like "Without it, the doc is a pile of bullets. With it, it's a decision" could be trimmed — anchor 4 rather than 5 because of these minor trim opportunities.

Actionability

Concrete throughout: exact library paths ("docs/ux-extracts/<app-name>/pattern-library.md"), output path and topic-slug convention, a fully worked output example, and even a citation format ("See claude.ai pattern library § Empty States, screenshot 502") — fully executable instruction-only guidance covering the common cases (anchor 5).

Workflow Clarity

Clear four-step sequence (read every library → walk category by category → cross-reference absences → synthesise recommendations) with explicit checkpoints: stop if fewer than 2 usable libraries, ask scope first, flag coverage gaps ("don't silently treat absent-from-library as absent-from-app"), and surface stale extraction dates — anchor 5; this is an analysis skill, so the destructive/batch validation cap does not apply.

Progressive Disclosure

references/comparison-template.md exists as a real one-level-deep reference, clearly signaled both inline ("See references/comparison-template.md for the full output shape") and in a When/Read table; the body keeps only a condensed example inline while the full template lives in the reference — clear overview, appropriate split, easy navigation (anchor 5).

Specificity

"Reads 2+ pattern-library.md files, walks them category by category, identifies where apps converge (strong signal), where they diverge (genuine design choice), what's unique to one app, and what's absent across the set. Produces an opinionated comparison document with recommendations" — multiple concrete actions covering input, process, and output with no notable coverage gaps, matching anchor 5 rather than the minor-gaps anchor 4.

Completeness

The what is explicit ("Compare UX patterns across multiple reference apps... Produces an opinionated comparison document with recommendations for a new build") and the when is explicit via "Trigger with 'compare UX patterns', 'how do top apps handle X', 'ux comparison', 'pattern comparison across reference apps'" with concrete trigger phrases — matches anchor 5; not 4, since the when-clause is fully explicit rather than merely present.

Trigger Term Quality

Trigger phrases "compare UX patterns", "how do top apps handle X", "ux comparison", and "pattern comparison across reference apps" are natural user phrasings with synonym coverage of compare/comparison, but common variations like "design conventions" or "how do other apps handle X" are missing — good coverage with a few natural terms absent (anchor 4), short of anchor 5's comprehensive synonym coverage.

Distinctiveness Conflict Risk

Clear niche — comparing multiple pattern libraries — with distinct triggers ("ux comparison", "pattern comparison across reference apps") and an explicit dependency "using pattern libraries produced by ux-extract" that delineates it from the sibling extraction skill; minimal conflict risk (anchor 5).