Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Understand which type of investment/savings account to use for your goal — the tax-advantaged vs taxable question, and which wrapper fits which money — so you don't leave free tax benefits on the table. Use when asked which account should I invest in, what's the difference between these account types, where should I put my savings, or tax-advantaged accounts explained. Produces a plain-language explainer of the common account categories (retirement/tax-advantaged, general/taxable, education, sho
.claude/skills/mohitagw15856-investment-account-picker/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -17% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 15% | 0% |
Where you hold your investments can matter as much as what you invest in — the right tax-advantaged account can save you thousands, and using the wrong wrapper (or missing free ones) leaves money on the table. But account types are a confusing, jurisdiction-specific alphabet soup. This explains the common categories in plain language, matches them to your goals, and gives a sensible priority order — then sends you to verify the specifics locally. Not financial advice.
Ask for these if not provided:
Your money, by purpose | This money (goal/timeline) | Suits this kind of account | |---|---| | retirement] | tax-advantaged retirement type] | | a specific goal] | goal-specific or general] | | general investing] | taxable/general] | | near-term/cash] | cash/safe — not market risk] |
Priority order: grab employer match (free) → tax-advantaged space → taxable/general. Free benefits you might be missing: unclaimed match · unused tax-advantaged room · long-term money sitting in cash]. Verify for region]: exact account names, limits, and tax rules.
> Not financial advice. Account types, names, limits, and tax treatment are jurisdiction-specific — confirm locally or with a fee-only adviser.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-12 | pass→pass | 14,098 | 16,926 | +20% | 1 | 1 | 0% | 2,409 | 3,072 | +28% | 0 | 0 | — |
case-01 | fail→pass | 23,460 | 22,248 | -5% | 1 | 1 | 0% | 3,224 | 3,665 | +14% | 0 | 0 | — |
case-02 | fail→pass | 26,118 | 18,761 | -28% | 1 | 1 | 0% | 3,615 | 3,371 | -7% | 0 | 0 | — |
case-03 | fail→pass | 27,341 | 18,608 | -32% | 1 | 1 | 0% | 3,704 | 3,080 | -17% | 0 | 0 | — |
case-04 | fail→pass | 23,444 | 15,136 | -35% | 1 | 1 | 0% | 1,875 | 2,681 | +43% | 0 | 0 | — |
case-05 | fail→pass | 19,173 | 17,819 | -7% | 1 | 1 | 0% | 2,738 | 3,161 | +15% | 0 | 0 | — |
case-11 | fail→fail | 16,408 | 20,099 | +22% | 1 | 1 | 0% | 1,809 | 3,529 | +95% | 0 | 0 | — |
case-06 | fail→fail | 16,627 | 19,422 | +17% | 1 | 1 | 0% | 1,883 | 3,319 | +76% | 0 | 0 | — |
case-07 | pass→pass | 17,559 | 16,375 | -7% | 1 | 1 | 0% | 2,296 | 3,106 | +35% | 0 | 0 | — |
case-08 | pass→pass | 19,638 | 17,101 | -13% | 1 | 1 | 0% | 2,581 | 3,163 | +23% | 0 | 0 | — |
case-09 | pass→fail | 24,641 | 17,467 | -29% | 1 | 1 | 0% | 3,268 | 3,278 | +0% | 0 | 0 | — |
case-10 | pass→pass | 23,749 | 19,646 | -17% | 1 | 1 | 0% | 3,021 | 3,446 | +14% | 0 | 0 | — |
case-13 | pass→pass | 24,509 | 18,270 | -25% | 1 | 1 | 0% | 3,136 | 3,300 | +5% | 0 | 0 | — |
case-14 | pass→fail | 20,930 | 14,916 | -29% | 1 | 1 | 0% | 2,845 | 2,752 | -3% | 0 | 0 | — |
case-15 | fail→pass | 26,942 | 17,643 | -35% | 1 | 1 | 0% | 3,828 | 3,853 | +1% | 0 | 0 | — |
case-16 | pass→pass | 14,352 | 16,576 | +15% | 1 | 1 | 0% | 2,680 | 3,116 | +16% | 0 | 0 | — |
case-17 | fail→pass | 18,864 | 13,708 | -27% | 1 | 1 | 0% | 2,693 | 2,789 | +4% | 0 | 0 | — |
case-18 | pass→pass | 22,468 | 18,727 | -17% | 1 | 1 | 0% | 3,033 | 3,583 | +18% | 0 | 0 | — |
case-19 | fail→pass | 21,239 | 13,429 | -37% | 1 | 1 | 0% | 2,876 | 3,331 | +16% | 0 | 0 | — |
case-20 | pass→pass | 12,702 | 19,827 | +56% | 1 | 1 | 0% | 2,279 | 3,146 | +38% | 0 | 0 | — |
case-21 | fail→pass | 15,543 | 17,278 | +11% | 1 | 1 | 0% | 2,888 | 3,577 | +24% | 0 | 0 | — |
case-22 | pass→pass | 14,654 | 19,677 | +34% | 1 | 1 | 0% | 2,549 | 3,320 | +30% | 0 | 0 | — |
case-23 | fail→pass | 22,036 | 20,891 | -5% | 1 | 1 | 0% | 3,127 | 3,406 | +9% | 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 +35 percentage points is the difference between those two pass rates over the 23 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.