Conciseness

Every line instructs: the 'Cut or rewrite' bullets each name a pattern with quoted examples ("Here's the thing:", "Not X. Y.", "delve," "tapestry"), the 'Keep' section is one dense sentence, and the example is a minimal before/after. No concept explanations Claude already knows and no padding — matches 'lean and efficient; every token earns its place'; not 4 because there is nothing to trim.

Actionability

Instruction-only skill with directly applicable guidance: a governing rule ("Fix each tell by stating the underlying claim plainly, not by swapping in a new flourish"), a concrete catalog of tells with example phrases, explicit keep rules, and a worked before/after example. This is the actionable equivalent of copy-paste code for an editing skill; not 4 because the specific examples cover the common cases with no gaps.

Workflow Clarity

This is a simple single-task skill under 50 lines, so the simple-skill exception applies: the single action is unambiguous — identify the listed tells, rewrite by stating the underlying claim, respect the Keep list and the author's voice. No destructive or batch operations exist, so the validation cap does not apply; not 4 because nothing about the action is ambiguous.

Progressive Disclosure

Under 50 lines with no need for external references; per the rubric guideline this scores 5 with just well-organized sections, and the three sections (Cut or rewrite / Keep / Example) are exactly that. The only external link is source attribution, not content; not 4 because there is no organization gap.

Specificity

"Remove AI writing patterns from prose so it reads like a person wrote it" names the domain and one concrete action, matching the 'names domain and 1-2 concrete actions' anchor. Not 4: it does not list several distinct actions (e.g., identifying tells, rewriting them, preserving the author's voice are folded into one clause); not 2: the action named is concrete, not generic.

Completeness

Explicitly answers both: what ("Remove AI writing patterns from prose so it reads like a person wrote it") and when ("Use when writing, editing, or reviewing user-facing text... or when asked to 'deslop'...") with concrete trigger phrases. Matches the top anchor exactly; the 'when' is neither missing nor weakly implied, so not 4.

Trigger Term Quality

Quote: "Use when writing, editing, or reviewing user-facing text (blog posts, docs, marketing copy, PR descriptions), or when asked to 'deslop', 'de-AI', or 'make it sound human'" — three exact natural user phrasings (synonyms for the same request) plus activity contexts and artifact types. This is comprehensive natural-term coverage for the domain; not 4 because no common way of requesting this skill is missing.

Distinctiveness Conflict Risk

The niche is distinct — "Remove AI writing patterns" with triggers like "deslop" and "de-AI" would not fire for unrelated skills. However "Use when writing, editing, or reviewing user-facing text" is broad enough to overlap with general writing/editing skills, which fits 'mostly distinct; minor overlap risk' rather than the 'minimal conflict risk' of 5.