mcpField
A
ad-monetization-review

ad-monetization-review

github.com/sylphxaiMarketing & growth152 installsUpdated today
Repository

About ad-monetization-review

Ad Monetization Review is a skill for product teams planning ads as part of a measured monetization system. It maps placements to user intent and risk, then structures a revenue plan with consent, analytics, caps, and experiment guardrails.

Key features

  1. 01Ad placement mapping
  2. 02Audience segmentation
  3. 03Revenue plan structure
  4. 04Consent and analytics considerations
  5. 05Experiment and fatigue guardrails

Use cases

  1. 01Reviewing ad placements in a product
  2. 02Planning frequency caps and rewards
  3. 03Accounting for children-sensitive contexts
  4. 04Setting retention and complaint guardrails

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/sylphxai/skills --skill ad-monetization-review

After installing, type/ad-monetization-reviewin Claude Code to confirm it loaded.

Bundled filesagents/openai.yamlreferences/ad-monetization-systems.md

Details

From the project README

Ad Monetization Review

Use this skill to make ads a measured monetization system rather than an interruption tax.

Workflow

  1. Identify product type, session loop, monetization mix, audience age/privacy constraints, and ad formats.
  2. Read references/ad-monetization-systems.md.
  3. Map ad placements to user intent, natural breaks, reward value, and fatigue risk.
  4. Define segmentation: new users, engaged users, payers, subscribers, lapsed users, children-sensitive contexts, and high-frustration states.
  5. Produce a revenue plan with caps, consent, analytics, suppression rules, support cases, and experiment guardrails.

When not to use

  • Do not use for generic advice the base model already handles without this skill's specific artifact contract.

Guardrails

  • Do not place interstitials during critical tasks, payment, onboarding trust-building, or error recovery.
  • Do not make rewards ambiguous before an ad starts.
  • Do not optimize ad impressions without retention, payer conversion, privacy, and complaint guardrails.

Output format

Ad context:
Monetization mix:

Placement map:
- <placement> -> format, trigger, user state, cap, reward, risk

Policy/trust constraints:
- <constraint> -> product response

Experiment plan:
- hypothesis, variants, success metric, guardrail metric, stop rule

Instrumentation:
- <event> with key properties

Comments

Markdown supported