Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Work down the cost of a prescription systematically — the generic and therapeutic-alternative conversation, discount programs vs insurance math, pharmacy price variance, and manufacturer/assistance programs, in the order that saves the most first. Use when asked my prescription is too expensive, how do I save on my meds, is there a cheaper version of this drug, or I can't afford my medication. Produces the cost-reduction ladder for the specific prescription, the scripts for pharmacist and prescr
.claude/skills/mohitagw15856-prescription-cost-navigator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 90% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 141% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 110% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 41% | 0% |
Prescription pricing is the only market where the cash price can beat the insurance price, the same bottle varies severalfold between pharmacies on the same street, and the manufacturer will sometimes pay your share themselves — but nobody at the counter is required to mention any of it. This skill runs the reduction ladder in savings order for the specific medication, scripts the two conversations that unlock most of it (pharmacist, prescriber), and holds one line absolutely: the dose is medical; only the price is negotiable.
Ask for these if not provided:
| Rung | The move | Typical impact | Effort | Script/where | |---|---|---|---|---|
Pharmacist: "cash-price question · discount program · 90-day ask — verbatim]" Prescriber: "generic/alternative ask framed as cost, not compliance · the bridge question if switching]"
Current vs cash-discount vs alt-pharmacy vs mail-order — filled where numbers exist, marked look-up where they don't · deductible-credit tradeoff noted]
Skipping/splitting/stretching doses — the medical risk named · unverified online sources · stopping without the prescriber — each with why it costs more than it saves]
> Prices, programs, and insurance rules change constantly and vary by location and plan — verify each rung before relying on it. The dose is medical: cost changes route through the prescriber, always.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 27,916 | 30,019 | +8% | 1 | 1 | 0% | 3,176 | 4,583 | +44% | 0 | 0 | — |
case-02 | fail→fail | 32,711 | 33,719 | +3% | 1 | 1 | 0% | 4,389 | 5,091 | +16% | 0 | 0 | — |
case-03 | fail→pass | 32,575 | 27,473 | -16% | 1 | 1 | 0% | 3,652 | 4,194 | +15% | 0 | 0 | — |
case-04 | pass→fail | 20,543 | 33,996 | +65% | 1 | 1 | 0% | 2,596 | 6,063 | +134% | 0 | 0 | — |
case-05 | pass→pass | 16,995 | 21,403 | +26% | 1 | 1 | 0% | 2,061 | 3,956 | +92% | 0 | 0 | — |
case-06 | pass→fail | 19,576 | 28,656 | +46% | 1 | 1 | 0% | 2,430 | 5,056 | +108% | 0 | 0 | — |
case-07 | fail→pass | 22,183 | 21,613 | -3% | 1 | 1 | 0% | 2,173 | 4,133 | +90% | 0 | 0 | — |
case-08 | pass→pass | 28,244 | 26,857 | -5% | 1 | 1 | 0% | 2,328 | 4,280 | +84% | 0 | 0 | — |
case-09 | fail→pass | 17,147 | 26,952 | +57% | 1 | 1 | 0% | 1,867 | 4,507 | +141% | 0 | 0 | — |
case-10 | pass→pass | 16,917 | 28,156 | +66% | 1 | 1 | 0% | 1,712 | 4,366 | +155% | 0 | 0 | — |
case-11 | fail→fail | 19,616 | 28,827 | +47% | 1 | 1 | 0% | 2,001 | 4,138 | +107% | 0 | 0 | — |
case-12 | fail→pass | 43,931 | 23,865 | -46% | 1 | 1 | 0% | 1,911 | 4,015 | +110% | 0 | 0 | — |
case-13 | pass→pass | 20,252 | 24,746 | +22% | 1 | 1 | 0% | 1,975 | 3,866 | +96% | 0 | 0 | — |
case-14 | fail→pass | 24,753 | 23,903 | -3% | 1 | 1 | 0% | 3,200 | 4,509 | +41% | 0 | 0 | — |
case-15 | fail→pass | 24,432 | 65,650 | +169% | 1 | 1 | 0% | 1,987 | 4,251 | +114% | 0 | 0 | — |
case-16 | pass→pass | 16,639 | 18,522 | +11% | 1 | 1 | 0% | 2,422 | 4,087 | +69% | 0 | 0 | — |
case-17 | pass→pass | 10,378 | 32,474 | +213% | 1 | 1 | 0% | 1,768 | 4,544 | +157% | 0 | 0 | — |
case-18 | fail→pass | 18,027 | 20,153 | +12% | 1 | 1 | 0% | 2,289 | 4,255 | +86% | 0 | 0 | — |
case-19 | fail→fail | 28,737 | 24,967 | -13% | 1 | 1 | 0% | 3,842 | 4,513 | +17% | 0 | 0 | — |
case-20 | fail→pass | 25,294 | 20,593 | -19% | 1 | 1 | 0% | 3,476 | 4,742 | +36% | 0 | 0 | — |
case-21 | pass→pass | 15,415 | 29,018 | +88% | 1 | 1 | 0% | 2,068 | 5,026 | +143% | 0 | 0 | — |
case-22 | pass→pass | 14,306 | 22,009 | +54% | 1 | 1 | 0% | 2,471 | 4,827 | +95% | 0 | 0 | — |
case-23 | fail→fail | 31,624 | 32,363 | +2% | 1 | 1 | 0% | 3,147 | 4,874 | +55% | 0 | 0 | — |
case-24 | fail→pass | 14,541 | 19,220 | +32% | 1 | 1 | 0% | 2,182 | 4,046 | +85% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted. The headline lift of +29 percentage points is the difference between those two pass rates over the 24 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.