← ClaudeAtlas

ad-monetization-reviewlisted

Design or audit one complete in-product advertising system for apps, games, web, and content products: rewarded ads, interstitials, banners/native placements, offerwalls, mediation, payer suppression, reward authority, consent, age/territory modes, frequency and fatigue budgets, IAP/IAA cannibalization, fraud, experiments, and shutdown. Use when deciding ad formats, placements, rewards, provider portfolio, or ad economics; combine with an App or Game Blueprint only when whole-product coherence is also unresolved.
SylphxAI/skills · ★ 1 · Code & Development · score 74
Install: claude install-skill SylphxAI/skills
# Ad Monetization Review Produce an **Ad Monetization Contract** that maximizes incremental retained contribution without turning attention, privacy, gameplay, or core utility into an interruption tax. ## Atomic boundary Own ad-side placement semantics, eligible audiences, reward authority, frequency/fatigue, provider/mediation portfolio, economics, experiments, and shutdown. Own the ad domain's required measurement meanings, but let `product-analytics-instrumentation-review` own the shared event identity, schema/versioning, collection, and product-metric contract. Do not own whole-app/game design, buyer payment ledgers, the broader game economy, one marketing campaign, or provider SDK implementation details. Use a draft artifact ID and consume sibling decisions by owner and explicit contract. Let deterministic delivery tooling seal serialized versions and digests later; never fabricate them in a design response. ## Agent-first invariant Construct the complete production-shaped system now: provider adapters, consent/age/territory modes, reward ledger, caps, payer states, mediation, fraud, observability, experiments, kill switches, and reconciliation. Separate construction from exposure. A disabled placement or provider performs zero SDK initialization, request, tracking, asset download, background work, or public call until its exact authority and exposure gate pass. ## Workflow 1. Label inputs `given`, `observed`, `assumed`, `hypothesis`, or `decision`. 2. Define pro