Conciseness

Nearly every line carries a specific number, threshold, or directive — "~1,000 matched users", "frequency climbing past ~3-4/week", "E.164 phone numbers with country code", "top-20%-by-LTV" — with no generic explanation of concepts Claude already knows. It matches the 'lean and efficient; assumes Claude's competence; every token earns its place' anchor, including its one-sentence framing opener that motivates the ladder model used throughout.

Actionability

Guidance is fully executable for an instruction-only skill: concrete tool invocations (list_audiences, optimize_budget, pull_*_performance), a tier ladder with percentage ranges and CPA multipliers, numeric fatigue and kill criteria, seed-quality ranking with a 90-day recency rule, match-rate formatting rules, and platform-specific conversion thresholds (50+/week Meta, 30+/month Google). Not 4 because there are no meaningful gaps in the concrete guidance.

Workflow Clarity

Sections 1-6 form a clear audit-first sequence (audit, climb ladder, build seeds, layer/exclude, algorithm handoff, monitor/rebalance) with explicit validation checkpoints: fatigue thresholds define audit criteria, each tier gets a pre-set CPA ceiling with a kill rule, every new campaign is prefighted, and the weekly monitor/rebalance step is a genuine feedback loop. The Rules section doubles as a checklist. Not 4 because both checkpoints and error-recovery paths (kill the rung, refresh creative, rebalance) are explicit.

Progressive Disclosure

A single ~50-line, well-sectioned file with no content that warrants separate bundle files and no nested references; bold cross-links to companion skills (launch, attribution, campaign-preflight) are one level deep and clearly signaled. Per the rubric's simple-skill guidance, a compact skill with no need for external references and well-organized sections scores 5.

Specificity

Names several concrete capability areas — "lookalike ladders, seed quality, audience layering, and exclusion hygiene across platforms" — which matches the 'several specific actions; minor gaps in coverage' anchor. It falls short of 5 because body capabilities like monitoring/rebalancing and algorithmic-targeting handoff are not covered, and exceeds 3 because it lists four distinct actions rather than 1-2.

Completeness

Explicitly answers both: what it does ("Expand targeting without wrecking CPA — lookalike ladders, seed quality, audience layering, and exclusion hygiene") and when to use it ("Use when a user wants to scale beyond exhausted audiences, build lookalikes, fix audience fatigue, or set up exclusion lists"), with concrete trigger phrases matching the 5 anchor. Not 4 because the 'when' clause is already explicit and trigger-specific.

Trigger Term Quality

"scale beyond exhausted audiences", "build lookalikes", "fix audience fatigue", and "set up exclusion lists" are phrases a paid-media user would naturally say, giving good keyword coverage. Not 5 because common synonyms like Google's "similar audiences", "prospecting", or "broaden audiences" are missing; not 3 because the natural phrase coverage goes well beyond 'some relevant keywords'.

Distinctiveness Conflict Risk

A clear paid-media audience-expansion niche with distinct triggers (lookalikes, exclusion lists, audience fatigue), so mostly distinct with only minor overlap risk against closely related skills such as a dedicated suppression-list or lookalike-building skill. Not 5 because "set up exclusion lists" and broad "scale" could collide with adjacent media-buying skills.