Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Audit spending to find leaks — recurring subscriptions, creep, and cuttable costs — ranked by impact. Use when asked to cut expenses, review subscriptions, find where money is going, or free up cash. Produces a categorized spend breakdown, a ranked list of cuts with dollar amounts, and the annualized savings. Educational, not regulated financial advice.
.claude/skills/mohitagw15856-expense-audit/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 20% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 50% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 28% | 0% |
Money leaks quietly — forgotten subscriptions, lifestyle creep, small daily costs that annualize into a lot. This skill audits someone's spending, surfaces the leaks ranked by annual impact, and proposes specific cuts with dollar amounts — so they free up cash without a vague "spend less". Educational, not personalized financial advice.
Ask for these only if they aren't already provided:
Where the money goes
| Category | Monthly | % of spend | Annualized | |---|---|---|---| | | $ | % | $ |
🔁 Recurring / subscriptions — every recurring charge found, with monthly + annual cost, and a verdict (keep / downgrade / cancel / negotiate). Flag duplicates and "haven't used it" candidates.
✂️ Ranked cuts — the highest-impact opportunities first, each with the annual dollar saving and how to do it:
| Cut | Monthly saved | Annual saved | How | |---|---|---|---| | | $ | $ | |
Total opportunity: $X/year if all suggested cuts are made (and a realistic "easy wins only" subtotal).
Notes — what was assumed; the "small daily cost" reframed annually (e.g. "$6 coffee × workdays ≈ $1,500/yr"); anything to verify on a statement.
Spending-audit / subscription-audit practice (categorize, annualize, rank cuts by impact).
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | pass→pass | 16,369 | 17,161 | +5% | 1 | 1 | 0% | 2,918 | 3,436 | +18% | 0 | 0 | — |
case-11 | pass→pass | 14,263 | 13,386 | -6% | 1 | 1 | 0% | 2,573 | 2,907 | +13% | 0 | 0 | — |
case-01 | fail→pass | 18,105 | 18,563 | +3% | 1 | 1 | 0% | 3,807 | 4,520 | +19% | 0 | 0 | — |
case-02 | fail→pass | 18,189 | 17,909 | -2% | 1 | 1 | 0% | 3,598 | 4,213 | +17% | 0 | 0 | — |
case-03 | fail→pass | 19,865 | 19,985 | +1% | 1 | 1 | 0% | 3,815 | 4,574 | +20% | 0 | 0 | — |
case-05 | pass→pass | 13,007 | 14,223 | +9% | 1 | 1 | 0% | 2,466 | 3,041 | +23% | 0 | 0 | — |
case-06 | pass→pass | 11,029 | 9,216 | -16% | 1 | 1 | 0% | 1,913 | 2,150 | +12% | 0 | 0 | — |
case-07 | pass→pass | 11,655 | 15,612 | +34% | 1 | 1 | 0% | 2,250 | 3,305 | +47% | 0 | 0 | — |
case-08 | fail→pass | 13,112 | 15,963 | +22% | 1 | 1 | 0% | 2,483 | 3,727 | +50% | 0 | 0 | — |
case-09 | fail→pass | 12,326 | 12,401 | +1% | 1 | 1 | 0% | 2,350 | 3,009 | +28% | 0 | 0 | — |
case-10 | fail→pass | 12,242 | 11,120 | -9% | 1 | 1 | 0% | 2,166 | 2,830 | +31% | 0 | 0 | — |
case-12 | fail→fail | 13,331 | 11,705 | -12% | 1 | 1 | 0% | 2,252 | 2,636 | +17% | 0 | 0 | — |
case-13 | pass→pass | 5,122 | 11,241 | +119% | 1 | 1 | 0% | 1,075 | 2,673 | +149% | 0 | 0 | — |
case-14 | pass→pass | 14,401 | 14,946 | +4% | 1 | 1 | 0% | 2,514 | 3,391 | +35% | 0 | 0 | — |
case-15 | pass→fail | 15,249 | 11,825 | -22% | 1 | 1 | 0% | 2,503 | 2,754 | +10% | 0 | 0 | — |
case-16 | fail→pass | 16,636 | 13,756 | -17% | 1 | 1 | 0% | 2,766 | 3,107 | +12% | 0 | 0 | — |
case-17 | fail→pass | 13,279 | 12,677 | -5% | 1 | 1 | 0% | 2,535 | 2,954 | +17% | 0 | 0 | — |
case-18 | fail→pass | 10,754 | 14,560 | +35% | 1 | 1 | 0% | 2,185 | 3,505 | +60% | 0 | 0 | — |
case-19 | fail→pass | 15,544 | 14,296 | -8% | 1 | 1 | 0% | 2,836 | 3,177 | +12% | 0 | 0 | — |
case-20 | fail→pass | 6,566 | 10,321 | +57% | 1 | 1 | 0% | 1,299 | 2,595 | +100% | 0 | 0 | — |
case-21 | pass→pass | 14,486 | 13,944 | -4% | 1 | 1 | 0% | 2,626 | 3,189 | +21% | 0 | 0 | — |
case-22 | pass→pass | 8,837 | 9,464 | +7% | 1 | 1 | 0% | 1,657 | 2,579 | +56% | 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. 22 cases were attempted. The headline lift of +45 percentage points is the difference between those two pass rates over the 22 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.