$ loading_
Match marketing preferences to reward options for review without issuing benefits.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "review-only-reward-options" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/aibast-agents-library/main/solutions/customer-loyalty-rewards/manual/skills/reward-recommendations/SKILL.md 2. Save it as ~/.claude/skills/reward-recommendations/SKILL.md 3. Reload skills and tell me it's ready
Based on these preferences, provide reward options for review only. Do not create offers or issue benefits: target audience is newly registered users, preferences are low-friction, digital, and suitable for brand acquisition; also list policy questions that should be reviewed.
A set of reward option concepts matched to the preferences, plus policy and compliance questions for further review.
For student users and high-value existing users, list reward options that fit each audience. This is for review only; do not redeem, purchase, or place any orders.
Reward option suggestions grouped by audience, helping a marketing lead compare strategic directions.
I need to discuss a reward strategy in an internal review meeting. Using a preference-matched reward options approach, list candidate options and the questions that legal, finance, or operations should confirm; do not contact anyone or create formal offers.
A shortlist of reward candidates for internal discussion, plus key cross-functional questions to verify.
When a team is planning campaign incentives, a marketing leader can first review reward options matched to user preferences and decide which directions are worth exploring. It is for early evaluation, not direct reward issuance.
Before legal, finance, or operations review, a team can organize candidate reward concepts and policy questions to reduce unproductive discussion. This skill only presents options and does not execute follow-up actions.
The README describes a review-only skill for matching reward options. It maps broad, synthetic stated preferences to catalog concepts within a synthetic balance and presents possible options along with policy questions for discussion. It explicitly does not contact anyone, create offers, issue rewards, redeem points, process refunds, place orders, or make purchases, making it suitable for early-stage marketing evaluation.
Match broad stated synthetic preferences to catalog concepts within the synthetic balance. Present options and policy questions. Do not contact anyone, create an offer, issue a reward, redeem points, refund, order, or purchase.
It matches broad stated preferences to conceptual reward options in a catalog and surfaces policy questions to consider. It is meant for reviewing and discussing reward directions.
No. The documentation explicitly says it will not contact anyone, create offers, issue rewards, redeem points, refund, order, or purchase.
Based on the description, you need to provide broad preference information so it can match reward options. For more specific setup or integration requirements, see the source repository.
Draft prioritized amendment positions and legal escalation points for contract renegotiations.
Rank a fictional contract portfolio to prioritize legal review attention.
Analyze loyalty tier thresholds, perks, progress, and tradeoffs without changing status.
Compare contract clauses against internal policy requirements and identify gaps.
Generate a synthetic points summary explanation without changing the ledger.
Scan synthetic customer records to find evidence-backed cross-sell product gaps.
Prepare reviewable retention and service-recovery options for churn-related customer cases.
Review product metrics, spot trends, and get actionable improvement recommendations.
Review contracts against playbooks with redlines, deviation flags, and impact analysis.
Review pipeline health, surface risks, and plan weekly deal priorities.
Create marketing performance reports with metrics, insights, and optimization recommendations.
Prioritize churn reviews with transparent evidence and suggested next steps.