Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Understand index-fund investing and how to actually get started with the simplest evidence-backed approach — plus the details that quietly matter (fees, account, automation). Use when asked how do index funds work, are index funds good, how do I buy index funds, or set up index fund investing. Produces a plain explanation of what index funds are and why they beat most active investing over time, what to check before buying (expense ratio, what it tracks, the account/wrapper), how to automate con
.claude/skills/mohitagw15856-index-fund-starter/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 9% | 0% |
Index funds are the closest thing investing has to a free lunch: own a tiny slice of a whole market, at rock-bottom cost, and outperform most professional stock-pickers over the long run — because low fees and diversification quietly win. This explains how they work, what to actually check before buying, and how to set up automatic investing — the boring approach that works. Education, not financial advice.
Ask for these if not provided:
What it is: own the whole market cheaply → market return minus a tiny fee → beats most active picking over time]. Before you buy, check: expense ratio (low! — fees compound) · what it tracks (broad & diversified) · fund vs ETF. Account: tax-advantaged vs taxable — research for your region] before choosing where to hold it. Automate: recurring auto-contributions — the habit that does the work]. Avoid: chasing past performance · tinkering · high-fee "index" funds · panic-selling in dips.
> Educational only — not financial advice. Account types, tax, and available funds vary by country. Confirm specifics 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-01 | fail→pass | 29,611 | 22,397 | -24% | 1 | 1 | 0% | 4,143 | 3,399 | -18% | 0 | 0 | — |
case-02 | fail→pass | 31,912 | 21,271 | -33% | 1 | 1 | 0% | 3,064 | 3,216 | +5% | 0 | 0 | — |
case-03 | fail→pass | 22,529 | 16,981 | -25% | 1 | 1 | 0% | 2,969 | 2,889 | -3% | 0 | 0 | — |
case-04 | fail→pass | 22,800 | 18,540 | -19% | 1 | 1 | 0% | 2,952 | 3,068 | +4% | 0 | 0 | — |
case-05 | pass→pass | 20,321 | 19,393 | -5% | 1 | 1 | 0% | 3,294 | 3,256 | -1% | 0 | 0 | — |
case-06 | fail→pass | 23,905 | 19,456 | -19% | 1 | 1 | 0% | 3,162 | 3,431 | +9% | 0 | 0 | — |
case-07 | pass→pass | 22,915 | 18,193 | -21% | 1 | 1 | 0% | 3,086 | 3,164 | +3% | 0 | 0 | — |
case-08 | pass→fail | 21,857 | 23,058 | +5% | 1 | 1 | 0% | 3,848 | 4,848 | +26% | 0 | 0 | — |
case-09 | pass→pass | 10,988 | 13,681 | +25% | 1 | 1 | 0% | 1,405 | 2,796 | +99% | 0 | 0 | — |
case-10 | pass→pass | 10,323 | 15,295 | +48% | 1 | 1 | 0% | 1,154 | 2,861 | +148% | 0 | 0 | — |
case-11 | pass→pass | 18,278 | 13,383 | -27% | 1 | 1 | 0% | 2,998 | 3,190 | +6% | 0 | 0 | — |
case-12 | pass→pass | 22,932 | 19,682 | -14% | 1 | 1 | 0% | 3,063 | 3,415 | +11% | 0 | 0 | — |
case-13 | fail→pass | 22,434 | 19,787 | -12% | 1 | 1 | 0% | 3,034 | 3,427 | +13% | 0 | 0 | — |
case-14 | fail→fail | 22,813 | 19,163 | -16% | 1 | 1 | 0% | 3,007 | 3,324 | +11% | 0 | 0 | — |
case-15 | pass→pass | 26,099 | 12,533 | -52% | 1 | 1 | 0% | 3,442 | 3,024 | -12% | 0 | 0 | — |
case-16 | fail→pass | 13,447 | 15,849 | +18% | 1 | 1 | 0% | 1,504 | 2,735 | +82% | 0 | 0 | — |
case-17 | fail→fail | 14,342 | 16,561 | +15% | 1 | 1 | 0% | 2,741 | 3,044 | +11% | 0 | 0 | — |
case-18 | pass→pass | 25,845 | 17,151 | -34% | 1 | 1 | 0% | 3,913 | 3,152 | -19% | 0 | 0 | — |
case-19 | pass→pass | 22,249 | 13,997 | -37% | 1 | 1 | 0% | 2,918 | 2,846 | -2% | 0 | 0 | — |
case-20 | fail→pass | 15,886 | 16,200 | +2% | 1 | 1 | 0% | 2,631 | 3,179 | +21% | 0 | 0 | — |
case-21 | fail→pass | 17,808 | 18,495 | +4% | 1 | 1 | 0% | 3,183 | 3,066 | -4% | 0 | 0 | — |
case-22 | fail→pass | 20,299 | 13,942 | -31% | 1 | 1 | 0% | 2,612 | 3,173 | +21% | 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 +41 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.