rtp-ao-optimizer

To tune RTP and AO targets with guardrails, you provide target values and defined constraints, and the skill returns tuned parameters within bounded changes. It enforces explicit targets and validation gates to ensure stable, auditable payout settings across mode mixes.

RTP and AO target optimization is a validation-driven workflow that adjusts payout structures under statistical validation. It generates parameter diffs, validation evidence, and handoff artifacts to produce compliant, traceable run context for sign-off ready reporting.

You validate payout structures by running the skill's validation-driven workflow, which captures metrics, run budgets, and release blockers. This provides statistical validation and traceable context for feature-rate adjustments across various mode mixes.

Yes, you can adjust RTP and AO targets within specific tolerance bands and hard constraints. The skill performs targeted optimization by enforcing bounded changes and explicit targets to ensure compliant payout structures without violating defined limits.

The limitation when tuning RTP and AO targets is that all adjustments must operate within defined tolerance bands and hard constraints. The skill enforces bounded changes and validation gates, meaning parameters cannot exceed the explicit targets you configure.

The best way to ensure compliant payout settings is to use a validation-driven workflow that enforces explicit targets and traceable run context. This generates parameter diffs and validation results, producing sign-off ready handoff artifacts for compliance reviews.