Conciseness

Every sentence either instructs or supplies domain-specific judgment calibration ("A campaign name is not targeting evidence", "Missing fields mean UNVERIFIED, not worldwide delivery", "signals to investigate, not proof of fraud"); nothing explains concepts Claude already knows, matching the lean-and-efficient anchor. It exceeds the 4 anchor because there is no over-explanation to trim.

Actionability

Concrete tool calls are named for every step (`list_campaigns`, `audit_account_structure`, `pull_meta_ads_performance`, `ga4_get_report`, `run_launch_preflight`) along with a specified per-campaign report structure — mostly executable with minor gaps. It falls short of 5 because the comparison criteria and anomaly thresholds (e.g., what counts as "unusually cheap clicks") are left to judgment.

Workflow Clarity

A clear ordered sequence runs from workspace confirmation through evidence gathering, anomaly investigation, reporting, correction, and an explicit re-verification loop ("Re-read settings and delivery after the change") with UNVERIFIED semantics acting as a check rule. It is below the 5 anchor because validation checkpoints are implicit in prose rather than explicit gates, and above the 3 anchor because the feedback loop and failure semantics are present.

Progressive Disclosure

The skill is ~16 lines with no external files needed, so keeping everything inline is appropriate, and no references exist to bury. It misses the 5 anchor (which for short skills requires well-organized sections) because there are no section headers beyond the H1 to make the flow scannable, and it is well above the 3 anchor since no content belongs in a separate file.

Specificity

Names the domain (campaign geography) and two concrete actions — "Check intended geography against available campaign settings and delivery evidence" and "identify unverified targeting before launch" — which matches the 1-2 concrete actions anchor; coverage is not comprehensive enough for 4, and the actions are far too concrete for 2.

Completeness

The "what" is clear, but there is no "Use when..." clause or equivalent explicit trigger guidance; "before launch" only weakly implies timing, and the rubric caps completeness at 3 in that case. It is well above the vague-what anchor at 2 because the action description is concrete.

Trigger Term Quality

Relevant keywords are present ("geography", "targeting", "campaign", "launch"), but the natural phrases ad-ops users actually say — "geo", "location targeting", "countries", "regions" — are missing, matching the some-keywords-with-missing-synonyms anchor rather than the good-coverage anchor at 4.

Distinctiveness Conflict Risk

The geo-integrity verification niche (intended geography vs. settings and delivery evidence, pre-launch) is mostly distinct with clear triggers; minor overlap risk remains with general campaign-launch or campaign-performance skills, keeping it below the minimal-conflict anchor at 5.