Install any skill in seconds. Free to start, no credit card required.
Get Started Free →borski/trip-calculator
Cash vs points trip cost comparison. Factors in transfer ratios, taxes, fees, CPP valuations, and opportunity cost to recommend the best redemption strategy for flights and hotels.
Passed 16 of 20 test cases with the skill, and 15 of 20 without it.
3 fixed15 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
A hotel costs $120 cash or 30,000 Marriott Bonvoy points per night with no taxes. With Marriott's floor valuation at 0.6 cpp, evaluate the CPP and assign the rating tier.
| Checked | Without skill | With skill |
|---|---|---|
| Computes the redemption CPP as 0.4 cpp. | Passed | Passed |
| Classifies the redemption as Poor because 0.4 cpp is below 0.8x of the floor valuation. | Missed | Passed |
The instructions your model reads when the skill loads.
"Should I pay cash or use points?" answered with math.
Compares the true cost of booking with cash versus each available points currency, accounting for transfer ratios, taxes/fees, and the opportunity cost of burning your points.
No API key needed. Uses local JSON data files plus flight/hotel search results.
| File | Purpose |
|---|---|
data/points-valuations.json | CPP valuations per program (floor/ceiling) |
data/transfer-partners.json | Credit card → loyalty program transfer ratios |
The value you're getting per point when redeeming:
cpp = (cash_price - taxes_on_award) / points_needed × 100
A CPP above the floor valuation from points-valuations.json means you're getting above-average value. Below floor = poor redemption.
Points have value even when unspent. Burning 100K Chase UR at 1.7 cpp (floor) means you're "spending" $1,700 in future travel flexibility:
opportunity_cost = points_needed × floor_cpp / 100
test cases passed, vs 15 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.