Conciseness

The body is lean and protocol-style ("Don't test the whole product. Test specific tasks."), assuming Claude's competence with no concept explanations. Not 5: the Failure patterns section repeats points already made in Phase 4 (leading the participant, defending the design, helping too quickly, suggestions-as-features all appear twice); not 3: there is no explanatory padding of concepts Claude already knows.

Actionability

Fully executable instruction-only guidance: verbatim task examples ("You want to find a contractor near you who can install a fence..."), a timed session structure (warm-up 2-3 min through close 2 min), severity definitions, a copy-paste markdown report template, named tools (UserTesting, Maze, Lookback) and output filenames (usability-test-plan-[topic].md). Not 4: specific examples cover the common cases ready to use as-is.

Workflow Clarity

The 10-step Workflow has explicit validation checkpoints and feedback loops: "Pilot. 1 to 2 sessions before main batch. Refine tasks if needed" and "Re-test after fixes. Verify the fix worked, didn't introduce new issues." Not 4: checkpoints are explicit (pilot, refine, re-test, track fixes with owner and date), matching the 5 anchor; this is not a destructive/batch operation, so no cap applies.

Progressive Disclosure

A single one-level-deep reference, clearly signaled in a "Reference files" section with a one-line content description, and the file exists on disk with matching content (task framing patterns by product type with good/bad examples). The split is appropriate: the long-tail pattern library lives in the reference while the core protocol stays in the body. Not 4: navigation is easy and the reference is well-signaled with no buried or nested paths.

Specificity

"Plan and run usability tests on existing or prototype designs including test design, task scripts, moderation, observation, and findings synthesis" lists multiple concrete actions spanning the full lifecycle (design, execution, synthesis) with comprehensive coverage. Not 4: there are no gaps in capability coverage — every phase of a usability test is named.

Completeness

Explicitly answers both: what ("Plan and run usability tests... including test design, task scripts, moderation, observation, and findings synthesis") and when ("Use this skill whenever the user wants to test usability... Also triggers when the user has built something and wants to know if real users can use it before shipping"). Not 4: the when-clause is explicit and concrete, matching the 5-anchor example structure exactly.

Trigger Term Quality

Triggers cover natural user phrasing with synonyms: "usability test, usability testing, moderated test, unmoderated test, task script, think aloud, prototype testing, user testing, design validation, task completion" — all phrases a user would naturally say. Not 4: both base terms and common variations (usability testing / user testing / prototype testing) are present, matching the comprehensive-synonyms anchor.

Distinctiveness Conflict Risk

Clear niche — usability testing with the moderated/unmoderated distinction carves a specific territory. Not 5: a few triggers ("user testing", "design validation", "validate a design") are broad enough to overlap with adjacent design-research skills; not 3: the core triggers are firmly specific to this skill's domain.