Conciseness

The body is dense and operational — exact grep patterns, fix snippets, and severity tables with almost no explanation of concepts Claude already knows — matching the "efficient; minor instances of over-explanation" anchor. Not a 5 because of padding: five invocation examples, a redundant terminal "Scope" section, and a "Tool Use Is Mandatory" preamble all add tokens without adding guidance.

Actionability

Guidance is fully executable: copy-paste grep regexes per category ("sleep\\(", "static var.*=", "\\.evaluates\\("), runnable Swift fix examples for confirmation-based waiting and nonisolated XCTestCase, exact skip-path lists, and a complete output-format template. Not below 5 because the common cases (flaky, speed, migration, Swift 6, quality) are each covered with concrete detection and fix guidance.

Workflow Clarity

Five phases are explicitly sequenced (map coverage → detect anti-patterns → reason about completeness → cross-reference compounds → health score) with validation checkpoints: "read surrounding context to verify it's a real issue before reporting", "Require evidence from the Phase 1 map — don't speculate", "Present this map in the output before proceeding", plus a false-positive checklist and output limits for error recovery. This is a read-only audit, so the destructive/batch cap does not apply.

Progressive Disclosure

Section structure (numbered phases, per-category subsections, tables) is good, but the ~370-line body is fully inlined with no bundle files at all (no references/, scripts/, or assets/ exist), matching the anchor for content that should be separate sitting inline. Not a 2 because organization and navigation within the file are clear; not a 4 because clearly separable material — the specialized OS27 AI-evaluation-gate rules (~40 lines) and the invocation examples — is not split out or referenced one level deep.

Specificity

The description lists several concrete actions — "audit test quality, find flaky test patterns, speed up test execution, or prepare for Swift Testing migration" — which are specific rather than generic, matching the anchor for several specific actions with minor gaps. It falls short of a 5 because the detection/mechanism side (coverage mapping, health scoring, anti-pattern detection) is never named, and it is above 3 because more than 1-2 concrete actions are given.

Completeness

Both what and when are present and the "Use when..." trigger clause is explicit with four concrete conditions, matching the score-4 anchor. It is not a 5 because the what and when are merged into a single clause rather than stated as an explicit capability sentence followed by explicit triggers; it is above 3 because the when-clause is explicit and specific, not merely implied.

Trigger Term Quality

Natural phrases users would say are well covered: "audit test quality", "flaky test", "speed up test execution", "Swift Testing migration" — good keyword coverage matching the score-4 anchor. Not a 5 because common variations like "flaky tests", "test coverage", "XCTest", or "test smells" are missing, which limits synonym coverage.

Distinctiveness Conflict Risk

"find flaky test patterns" and "prepare for Swift Testing migration" carve out a clear Swift/iOS test-auditing niche with minimal conflict risk, mostly distinct per the score-4 anchor. Not a 5 because "audit test quality" is broad enough to overlap with general code-review or testing skills.