Conciseness

The body is largely lean and instructional — counts, tables, and checklists rather than padded prose — but a few lines explain rationale Claude doesn't need or duplicate the reference bundle: "The 'not' half is what saves writers from overshooting. 'Confident' alone produces swagger..." restates voice-frameworks.md's 'Why the not Y matters' section, and "Voice stays consistent across all of these. Tone is what shifts." repeats the section's opening claim. This fits anchor 4 ('Efficient; minor instances of over-explanation that could be trimmed') — better than 3 because the padding is a handful of lines, not sections.

Actionability

For an instruction-only skill the guidance is fully concrete: exact counts ("Pick 3 to 5 attributes", "List 8 to 15 contexts", "The floor is 15 paired examples" with a stated practical ceiling of 25), a 14-row tone-shift table, a 7-section output format, and a worked attribute-pairing list. This matches anchor 5's 'specific examples cover the common cases' — the rubric's code-vs-instruction note says executable guidance without code is not penalized.

Workflow Clarity

The 9-step workflow is clearly sequenced with an entry-point decision (step 1 delegates to the 'Choosing a framework' section in references/voice-frameworks.md, which exists) and an explicit validation loop: step 7's stress test scores output '1 to 5 against each attribute' with failure interpretation ('anything scoring below 3... Below 3 means the doc is incomplete, not that the copy needs another pass'). This matches anchor 5 ('explicit validation steps; feedback loops').

Progressive Disclosure

SKILL.md is an overview of the method with exactly two one-level-deep references, both real files (references/voice-document-template.md and references/voice-frameworks.md), each clearly signaled with its purpose, plus a dedicated 'Reference files' section. Content splitting is deliberate — the template owns the content-type list ('one list to maintain rather than two that drift apart'). This matches anchor 5 ('Clear overview with well-signaled one-level-deep references; content appropriately split; easy navigation'); the inline tone table and attribute pairs are core method patterns, not misplaced reference material.

Specificity

"Develop or document a complete brand voice and tone system covering voice attributes, tone shifts by context, vocabulary preferences, grammar rules, and copy examples" names the domain and enumerates five concrete deliverable components, with additional actions ("audit existing copy for voice consistency, train a team or AI assistant on brand voice, or refine the personality of brand writing"). This matches the anchor 'Lists multiple specific concrete actions; comprehensive coverage' — not 4, since coverage of the skill's actions is comprehensive rather than having minor gaps.

Completeness

The description explicitly answers both questions: 'what' via "Develop or document a complete brand voice and tone system covering..." and 'when' via "Use this skill whenever the user wants to..." plus an explicit trigger-term list. This matches the anchor 'Clearly and explicitly answers both what AND when with concrete trigger phrases'; a score of 4 would require the 'when' to be less explicit, which it is not.

Trigger Term Quality

"Triggers on brand voice, voice and tone, tone of voice, writing voice, brand personality, copy voice, voice document, voice guidelines, how should we write, voice training, voice audit" provides comprehensive natural-term coverage including synonyms users would actually say. It stays at 5 rather than dropping to 4 because no common variation (audit, training, document, personality, tone) is missing; file extensions are inapplicable to a non-file skill.

Distinctiveness Conflict Risk

The skill has a clear niche (defining and documenting brand voice) and explicitly resolves the nearest conflict: "On a voice consistency check, this skill owns defining and documenting the voice system; use `editorial-qa` when a specific draft needs checking against an existing system before it publishes." This matches anchor 5 ('Clear niche with distinct triggers; minimal conflict risk') — the disambiguation goes beyond the minor-overlap profile of a 4.