Conciseness

The ~20-line body is lean and dense: every step adds non-obvious domain guidance (e.g., 'Normalize spend and outcomes to comparable windows and definitions', 'Compare hold, reallocate, scale, reduce, or experiment options using marginal evidence rather than blended averages alone') with zero padding or explanation of concepts Claude already knows. It clearly matches the anchor-5 example of assuming Claude's competence, not anchor 4, since there is no over-explanation to trim.

Actionability

Each step gives concrete, executable direction — 'Calculate break-even boundaries and show formulas, inputs, uncertainty, and sensitivity cases' and a deliverable spec of 'platform/campaign amount, timing, owner, guardrails, success measure, and rollback trigger'. It sits at anchor 4 rather than 5 because no worked example, formulas, or output template are provided inline; not anchor 3 since the guidance is specific and directly executable rather than incomplete.

Workflow Clarity

The six steps form a clear, coherent sequence from establishing inputs through normalization, calculation, option comparison, to a decision-complete plan, and step 6 embeds checkpoints ('guardrails, success measure, and rollback trigger'). It is anchor 4 rather than 5 because there is no explicit validation/verification step in the process itself (e.g., sanity-checking computed break-even boundaries against platform data). The destructive/batch cap at 3 does not apply since this is analytical planning, not a destructive or batch operation.

Progressive Disclosure

The skill is under 50 lines with no bundle files (references/, scripts/, assets/ are absent) and no content that warrants external references; the single 'Budget and Bidding' section is well organized. Per the simple-skill guideline, this matches anchor 5 for a short, well-organized single-file skill.

Specificity

'Plan and review paid-media budgets, bidding, pacing, marginal return, targets, constraints, and allocation across supported platforms' lists multiple specific concrete actions with comprehensive coverage of the domain. This matches anchor 5; it is not anchor 4 because there are no meaningful gaps in the action coverage, and each action is concrete rather than generic.

Completeness

It clearly answers what ('Plan and review paid-media budgets, bidding, pacing, marginal return, targets, constraints, and allocation') and when via an explicit 'Use for ad budget allocation, media budget, bidding strategy, scaling, spend pacing, ROAS target, or investment tradeoffs' trigger clause with concrete trigger phrases. This matches anchor 5 exactly; the 'Use for' clause satisfies the explicit-trigger requirement so no cap applies.

Trigger Term Quality

'ad budget allocation, media budget, bidding strategy, scaling, spend pacing, ROAS target, or investment tradeoffs' provides good coverage of natural phrases users would say. It fits anchor 4 rather than 5 because common synonyms like 'ad spend', 'media buying', 'paid search/social', or 'increase/decrease budget' are missing; it is above anchor 3 since keyword coverage is strong, not merely partial.

Distinctiveness Conflict Risk

Niche terms ('paid-media', 'ROAS target', 'spend pacing', 'bidding strategy') and the delegation 'Use ads-math for calculations and forecasts' give it a clear advertising niche. It is anchor 4 rather than 5 because broader phrases like 'investment tradeoffs', 'targets', and 'constraints' carry minor overlap risk with general finance or budgeting skills.