Conciseness

Every line is instruction ("Show one set at a time. Never preview or list the other sets. Stop and wait.", "One short sentence per question."); there is no concept explanation, padding, or reiteration of what Claude already knows. Lean throughout, matching the top anchor.

Actionability

Concrete, executable guidance throughout: a literal message-format template, exact workflow steps, and specific rules ("Vague or skipped answer: move on and use your judgment"). Not a 5 because the format example uses "..." placeholders instead of one fully worked example set of four real questions, leaving a minor gap in covering the common case.

Workflow Clarity

The 6-step workflow is clearly sequenced with explicit stop-and-wait checkpoints ("Stop and wait. Show the next set only after the user answers") and error-recovery feedback loops in the Rules section (bad question → replace or drop; answer contradicts an ADR → point it out in the plan). Not a 4 because checkpoints are explicit rather than implicit; the destructive/batch validation cap does not apply to this interactive elicitation skill.

Progressive Disclosure

The body is under 50 lines with no external references needed, organized into well-labeled sections (The 4 sets, Workflow, Message format, Rules), which per the rubric's simple-skill guideline earns the top score. There are no buried or nested references.

Specificity

"Pull 16 fast decisions out of the user with 4 sets of 4 open questions, then present an implementation plan" names concrete, quantified actions (elicit 16 decisions via 4 sets of open questions, present a plan). Not a 5 because coverage is limited to two core actions rather than several; not a 3 because the detail ("16", "4 sets of 4", "open questions", "implementation plan") is noticeably more concrete than the 1-2 generic-action anchor.

Completeness

The "what" is explicit ("Pull 16 fast decisions out of the user with 4 sets of 4 open questions, then present an implementation plan") and the "when" is explicit ("Only for risky changes, large product decisions, or large refactors. Run when the user types /4x4") — both answered with concrete trigger phrases, matching the top anchor.

Trigger Term Quality

Natural triggers include "/4x4", "risky changes", "large product decisions", "large refactors" — phrases a user would plausibly say. Not a 5 because common variations ("big decision", "major refactor", "big change") are missing; not a 3 because coverage goes beyond a bare minimum with multiple distinct natural terms.

Distinctiveness Conflict Risk

Clear niche (structured user-decision elicitation before planning) with a distinct trigger ("/4x4"), and the clause "Agents may suggest it in one line but never start it on their own" explicitly limits conflict with other skills. Only minor, sub-anchor-level overlap with general planning skills.