Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Set up a spaced-repetition system to actually remember what you learn — good cards, the right review rhythm, and the mistakes that make flashcards useless. Use when asked help me memorize, set up flashcards / Anki, how do I remember what I study, or spaced repetition for. Produces card-writing guidance (atomic, one-fact, testable — not walls of text), a review cadence that leverages the forgetting curve, what's worth making cards for vs not, and the common failure modes that make people quit — t
.claude/skills/mohitagw15856-spaced-repetition-setup/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 29% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 2% | 0% |
You forget most of what you learn within days — unless you review it at expanding intervals, right as you're about to forget. Spaced repetition exploits that. But most people make terrible cards (whole paragraphs, ambiguous prompts) and quit. This sets up a system that works: how to write cards that stick, the review rhythm, what's even worth memorizing, and the traps that kill the habit.
Ask for these if not provided:
Write cards like this: atomic (one fact) · clear question · unambiguous answer · your own words. Example: a good card vs a bad one for your topic]. Review rhythm: daily short reviews; intervals expand as you succeed] — don't let them pile up. Make cards for: facts/vocab/formulas]. Don't card: procedural stuff — learn by doing]. Avoid: giant cards · vague prompts · memorizing without understanding · binge-and-lapse. Starter batch: a few well-formed cards for your topic].
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 19,826 | 12,815 | -35% | 1 | 1 | 0% | 3,077 | 3,101 | +1% | 0 | 0 | — |
case-02 | fail→fail | 22,118 | 16,878 | -24% | 1 | 1 | 0% | 3,256 | 3,261 | +0% | 0 | 0 | — |
case-03 | fail→pass | 20,051 | 15,209 | -24% | 1 | 1 | 0% | 2,983 | 3,203 | +7% | 0 | 0 | — |
case-04 | fail→fail | 18,388 | 14,760 | -20% | 1 | 1 | 0% | 3,000 | 3,322 | +11% | 0 | 0 | — |
case-05 | fail→pass | 22,384 | 16,829 | -25% | 1 | 1 | 0% | 2,947 | 3,791 | +29% | 0 | 0 | — |
case-06 | fail→pass | 26,213 | 17,304 | -34% | 1 | 1 | 0% | 3,499 | 3,733 | +7% | 0 | 0 | — |
case-07 | fail→pass | 24,221 | 15,542 | -36% | 1 | 1 | 0% | 3,091 | 3,150 | +2% | 0 | 0 | — |
case-08 | fail→fail | 24,617 | 13,604 | -45% | 1 | 1 | 0% | 3,153 | 3,076 | -2% | 0 | 0 | — |
case-09 | fail→fail | 23,578 | 13,711 | -42% | 1 | 1 | 0% | 3,486 | 2,825 | -19% | 0 | 0 | — |
case-10 | fail→fail | 21,908 | 14,738 | -33% | 1 | 1 | 0% | 3,285 | 3,235 | -2% | 0 | 0 | — |
case-11 | fail→pass | 24,421 | 14,201 | -42% | 1 | 1 | 0% | 3,198 | 2,887 | -10% | 0 | 0 | — |
case-12 | fail→fail | 17,433 | 15,832 | -9% | 1 | 1 | 0% | 2,653 | 3,321 | +25% | 0 | 0 | — |
case-13 | pass→pass | 34,791 | 13,929 | -60% | 1 | 1 | 0% | 3,064 | 3,008 | -2% | 0 | 0 | — |
case-14 | fail→fail | 22,390 | 14,487 | -35% | 1 | 1 | 0% | 3,184 | 2,833 | -11% | 0 | 0 | — |
case-15 | fail→pass | 16,729 | 12,500 | -25% | 1 | 1 | 0% | 2,432 | 2,983 | +23% | 0 | 0 | — |
case-16 | fail→fail | 27,806 | 18,858 | -32% | 1 | 1 | 0% | 3,696 | 3,248 | -12% | 0 | 0 | — |
case-17 | fail→pass | 25,789 | 15,738 | -39% | 1 | 1 | 0% | 2,917 | 3,229 | +11% | 0 | 0 | — |
case-18 | fail→pass | 15,019 | 14,479 | -4% | 1 | 1 | 0% | 2,690 | 3,202 | +19% | 0 | 0 | — |
case-19 | fail→pass | 19,593 | 24,041 | +23% | 1 | 1 | 0% | 3,413 | 3,899 | +14% | 0 | 0 | — |
case-20 | pass→fail | 21,487 | 28,796 | +34% | 1 | 1 | 0% | 3,188 | 5,472 | +72% | 0 | 0 | — |
case-21 | pass→pass | 17,183 | 24,817 | +44% | 1 | 1 | 0% | 3,056 | 5,174 | +69% | 0 | 0 | — |
case-22 | pass→fail | 13,316 | 19,724 | +48% | 1 | 1 | 0% | 2,199 | 3,809 | +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. 22 cases were attempted. The headline lift of +36 percentage points is the difference between those two pass rates over the 22 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.