The body is lean and instructional — exact commands, assertions, and expected values with no padding or explanations of concepts Claude already knows — so every token earns its place, matching the 'lean and efficient' anchor 3.

It provides fully executable, copy-paste-ready commands (npx iwsdk ... --input-json '...') with specific assertions and concrete expected values, matching the 'fully executable code/commands; copy-paste ready' anchor 3.

A clear five-step sequence with explicit validation checkpoints (parse JSON and verify assertions before proceeding, connectivity check, logs assertion) and a Recovery feedback loop with retry limits, matching the 'clear sequence with explicit validation steps and feedback loops' anchor 3.

No bundle files exist, so scoring is based on organization: the document is well-sectioned (Steps 1-5, Suites 1-5, Recovery, Known Issues) with clear navigation and no nested-reference problem, and the self-contained test procedure has no genuine need for external files.

The description lists multiple concrete, specific actions/targets ('LevelRoot, LevelTag, default lighting, scene hierarchy') against a concrete example using a named CLI, matching the 'lists multiple specific concrete actions' anchor rather than the partial anchor 2.

It clearly states what the skill does but lacks any 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2 ('has what, but when is missing or only implied').

Terms a user of this toolchain would naturally say ('test level system', 'LevelRoot', 'LevelTag', 'iwsdk CLI') give good coverage of natural trigger language for this niche, matching the high-coverage anchor 3.

The description carves out a clear niche (testing a specific level system in a specific SDK against a named example) with distinct triggers unlikely to conflict with other skills, matching the 'clear niche with distinct triggers' anchor.