Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Build a debt-payoff plan across multiple debts using the avalanche or snowball method. Use when asked to pay off debt, tackle credit cards/loans, or choose between avalanche and snowball. Produces an ordered payoff schedule, the total interest and time for each method, and a clear recommendation. Educational, not regulated financial advice.
.claude/skills/mohitagw15856-debt-payoff-plan/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 64% | 0% |
| case-21 | ✗→✓ | ▲ Improved | 34% | 0% |
| case-15 | ✓→✗ | ▼ Worse | 86% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 32% | 0% |
Juggling several debts without a plan means paying more interest for longer. This skill turns a list of debts plus a monthly amount available into an ordered payoff plan — comparing the avalanche (highest rate first, least interest) and snowball (smallest balance first, fastest wins) methods so the person can pick with eyes open. Educational planning, not personalized financial advice.
Ask for these only if they aren't already provided:
Debts
| Debt | Balance | APR | Minimum | |---|---|---|---| | | $ | % | $ |
Method comparison (paying $X/month total):
| Method | Order | Debt-free in | Total interest paid | |---|---|---|---| | Avalanche (highest APR first) | … | ~N months | $ | | Snowball (smallest balance first) | … | ~N months | $ |
Recommended order — the chosen method's payoff sequence, with the "attack" target each phase and roughly when each debt clears (roll each freed-up minimum into the next debt — the snowball/avalanche effect).
The trade-off — avalanche saves $X in interest; snowball gives the first win ~N months sooner. State which fits their stated preference and why.
Watch-outs — keep paying every minimum (missed minimums = fees + credit damage), and avoid adding new debt mid-plan.
Debt-reduction methods — the debt avalanche (highest-interest-first) and debt snowball (smallest-balance-first).
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 21,667 | 17,334 | -20% | 1 | 1 | 0% | 5,130 | 5,107 | -0% | 0 | 0 | — |
case-02 | fail→pass | 21,503 | 22,960 | +7% | 1 | 1 | 0% | 5,073 | 5,814 | +15% | 0 | 0 | — |
case-03 | pass→pass | 17,208 | 15,329 | -11% | 1 | 1 | 0% | 2,656 | 3,518 | +32% | 0 | 0 | — |
case-04 | pass→pass | 13,231 | 12,712 | -4% | 1 | 1 | 0% | 2,328 | 3,030 | +30% | 0 | 0 | — |
case-05 | pass→pass | 12,867 | 14,004 | +9% | 1 | 1 | 0% | 2,664 | 3,229 | +21% | 0 | 0 | — |
case-06 | fail→fail | 12,614 | 15,036 | +19% | 1 | 1 | 0% | 2,297 | 3,754 | +63% | 0 | 0 | — |
case-07 | pass→pass | 12,997 | 15,665 | +21% | 1 | 1 | 0% | 2,308 | 3,780 | +64% | 0 | 0 | — |
case-08 | fail→pass | 13,069 | 19,089 | +46% | 1 | 1 | 0% | 2,789 | 4,563 | +64% | 0 | 0 | — |
case-09 | pass→pass | 9,160 | 18,413 | +101% | 1 | 1 | 0% | 1,813 | 4,486 | +147% | 0 | 0 | — |
case-10 | pass→pass | 8,457 | 11,378 | +35% | 1 | 1 | 0% | 1,487 | 2,900 | +95% | 0 | 0 | — |
case-15 | pass→fail | 14,956 | 21,900 | +46% | 1 | 1 | 0% | 2,907 | 5,408 | +86% | 0 | 0 | — |
case-11 | fail→fail | 14,081 | 21,718 | +54% | 1 | 1 | 0% | 3,466 | 5,014 | +45% | 0 | 0 | — |
case-12 | pass→pass | 6,449 | 10,766 | +67% | 1 | 1 | 0% | 1,231 | 2,710 | +120% | 0 | 0 | — |
case-13 | pass→pass | 16,313 | 16,152 | -1% | 1 | 1 | 0% | 3,439 | 3,799 | +10% | 0 | 0 | — |
case-14 | pass→pass | 7,590 | 13,004 | +71% | 1 | 1 | 0% | 1,417 | 3,218 | +127% | 0 | 0 | — |
case-16 | pass→pass | 8,132 | 13,861 | +70% | 1 | 1 | 0% | 1,554 | 3,344 | +115% | 0 | 0 | — |
case-17 | pass→pass | 14,383 | 15,281 | +6% | 1 | 1 | 0% | 2,388 | 3,203 | +34% | 0 | 0 | — |
case-18 | pass→pass | 8,329 | 21,477 | +158% | 1 | 1 | 0% | 1,914 | 5,696 | +198% | 0 | 0 | — |
case-19 | pass→pass | 12,444 | 20,025 | +61% | 1 | 1 | 0% | 2,532 | 4,113 | +62% | 0 | 0 | — |
case-20 | fail→fail | 12,420 | 17,910 | +44% | 1 | 1 | 0% | 2,279 | 4,860 | +113% | 0 | 0 | — |
case-21 | fail→pass | 14,334 | 16,904 | +18% | 1 | 1 | 0% | 2,802 | 3,746 | +34% | 0 | 0 | — |
case-22 | pass→pass | 7,689 | 17,114 | +123% | 1 | 1 | 0% | 1,511 | 4,945 | +227% | 0 | 0 | — |
case-23 | pass→pass | 14,821 | 15,761 | +6% | 1 | 1 | 0% | 2,349 | 4,073 | +73% | 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. 23 cases were attempted. The headline lift of +9 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is 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.