placements-targeting — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited placements-targeting (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Align placement structure with the selected ad-unit scope. Maintain the targeting taxonomy and audience-facing constraints.
Do not use if adUnitIds are not yet qualified — run inventory-ad-units first.
list_placements — read current state. [free]list_custom_targeting_keys + get_custom_targeting_values + geo/language/device lookups. [free]search_ad_units if needed. [free]validate_fluid for any Native or Fluid path. [free]get_inventory_forecast if tighter targeting could materially change supply. [variable]list_placements, list_custom_targeting_keys, get_custom_targeting_values, validate_fluid — [free]create_placement, update_placement — writes, confirm naming and ad-unit grouping firstcreate_custom_targeting_key, create_custom_targeting_values — writes, confirm taxonomy firstdelete_custom_targeting_key — destructive, explicit confirmation requiredarchive_placement, archive_ad_unit — destructive, human review requiredvalidate_fluid has not passed.Render placement coverage gap as an artifact table (existing vs. missing vs. proposed).
<handoff>
selectedAdUnitIds: [...]
placementIds: [...]
targetingKeyIds: [...]
fluidCompatible: true | false
nextRecommendedSkill: advertiser-order-line-items
</handoff>Use extended thinking when taxonomy changes have downstream impact on existing line items.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.