Conciseness

The body assumes Claude's intelligence throughout — no filler explaining what prose or voice is, and nearly every sentence carries an editorial judgment. A few abstract summarizing lines ('Neither roughness nor polish is a virtue by itself', 'Recognition matters more than grammatical perfection') restate nearby points and could be trimmed. Matches the 4 anchor: efficient with minor over-explanation; not 5 because of those few redundant aphoristic closers.

Actionability

Guidance is concrete and executable for an instruction-only skill: the deletion test ('would removing it preserve meaning, movement, and human posture?'), 'Read connected passages at speaking speed', a worked example ('"And then there's just a lot of Asian food" can earn its own paragraph'), a specific transformation warning ('changing "I would argue" into "I wonder whether" can weaken the thought'), and explicit punctuation rules ('Avoid en dashes; default away from em dashes'). Mostly executable with minor gaps — some directives remain abstract ('Hear what the writing is doing, then judge it by what this piece needs'), so 4 rather than 5; well above pseudocode-level guidance, so not 3.

Workflow Clarity

A coherent editorial sequence is present: find the expression, hear the whole passage under four named tests, 'rehear the passage under that correction and revise at the scope it illuminates', reread in context, then after a whole-piece pass 'check that the opening, strongest concrete detail, and ending still serve the same thought'. The rehear-and-revise step is an explicit feedback loop. Scored 4 not 5 because checkpoints are embedded in prose rather than laid out as explicit, ordered steps with validation gating; not 3 because the sequence and recovery loop are both clearly stated. No destructive/batch validation cap applies to prose editing.

Progressive Disclosure

The body is well-sectioned with clear headers, and the single bundle file is a well-signaled, one-level-deep reference that exists and is on point: 'For work intended to be heard, read [spoken destinations](references/spoken-destinations.md) for the extra judgments a listener's experience requires.' Core craft lives in SKILL.md while listener-specific material is appropriately split out with no nested references — the 5 anchor. Not 4 because navigation is unambiguous and the split is clean.

Specificity

The description enumerates several specific capabilities and modes — 'conversational precision, rhythm, humor, and earned poetic turns', 'substantial drafting or revision, an ear pass, and explicit voice or tone work in prose, UI copy, documentation, or messages' — though the umbrella action 'shape prose' leaves minor coverage gaps. Not 5 because the actions are attributes of one shaping verb rather than a comprehensive list of distinct operations; not 3 because it goes well beyond naming a domain with 1-2 actions.

Completeness

It explicitly answers both questions: the 'what' ('Shape prose so it sounds like Braden, with conversational precision, rhythm, humor, and earned poetic turns') and the 'when' ('Use for substantial drafting or revision, an ear pass, and explicit voice or tone work...'), plus a negative trigger boundary ('Do not use to reopen wording selected for exact use'). Clearly matches the 5 anchor with concrete trigger phrases; 4 would require the 'when' to be less explicit than it is.

Trigger Term Quality

Natural phrases a user would say are present with synonyms — 'drafting or revision', 'an ear pass', 'voice or tone work', 'UI copy', 'documentation', 'messages'. Not 5 because common variants users would naturally say, such as 'rewrite', 'edit', or 'style', are missing; not 3 because coverage is good rather than partial.

Distinctiveness Conflict Risk

Distinctive triggers like 'sounds like Braden', 'an ear pass', and 'voice or tone work' carve a clear niche, but 'substantial drafting or revision' broadly overlaps general writing and editing skills. Mostly distinct with minor overlap risk — the 4 anchor; not 5 because of that drafting/revision breadth, not 3 because the named voice and ear-pass triggers are unmistakable.