Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Build a real plan to make friends as an adult — where to meet people you'd actually click with, how to turn acquaintances into friends, and past the awkwardness. Use when asked how do I make friends as an adult, I'm lonely and want more friends, help me build a social life, or I have no friends here. Produces a read on where to meet the right people for you (shared interests + repeated exposure), the specific move that converts acquaintances to friends (initiate + consistency + vulnerability), a
.claude/skills/mohitagw15856-make-friends-as-an-adult/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 2% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 61% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 54% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 30% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 30% | 0% |
Friendship happened automatically as a kid — forced proximity and endless repeated contact. As an adult, that scaffolding disappears, so friends have to be built on purpose, which feels awkward and vulnerable and stops most people. This gives a real plan: where to find people you'd genuinely click with, the specific moves that turn a friendly acquaintance into an actual friend, and permission for it to feel a bit awkward — because it does for everyone.
Ask for these if not provided:
Where to meet your people: shared-interest + repeated-exposure settings for you]. Turn acquaintance → friend: initiate (suggest the plan) · repeat (consistency) · a little vulnerability (go past small talk). Low-pressure plan: small doable steps — join / follow up / invite once]. The reframe: the awkwardness is normal and shared; most people want more friends too. Follow through: the specific "text them by when]" nudge].
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 24,504 | 18,920 | -23% | 1 | 1 | 0% | 3,147 | 3,199 | +2% | 0 | 0 | — |
case-02 | pass→pass | 26,919 | 19,445 | -28% | 1 | 1 | 0% | 3,010 | 3,205 | +6% | 0 | 0 | — |
case-03 | pass→pass | 24,468 | 21,664 | -11% | 1 | 1 | 0% | 2,654 | 3,169 | +19% | 0 | 0 | — |
case-04 | pass→pass | 25,665 | 37,351 | +46% | 1 | 1 | 0% | 2,676 | 5,221 | +95% | 0 | 0 | — |
case-05 | pass→pass | 24,027 | 26,781 | +11% | 1 | 1 | 0% | 2,363 | 3,630 | +54% | 0 | 0 | — |
case-06 | pass→pass | 20,588 | 24,465 | +19% | 1 | 1 | 0% | 2,235 | 3,700 | +66% | 0 | 0 | — |
case-07 | pass→pass | 22,819 | 24,301 | +6% | 1 | 1 | 0% | 2,141 | 2,945 | +38% | 0 | 0 | — |
case-08 | pass→pass | 23,763 | 21,575 | -9% | 1 | 1 | 0% | 2,175 | 2,897 | +33% | 0 | 0 | — |
case-09 | pass→pass | 21,490 | 17,840 | -17% | 1 | 1 | 0% | 1,940 | 2,899 | +49% | 0 | 0 | — |
case-10 | pass→pass | 17,500 | 16,785 | -4% | 1 | 1 | 0% | 1,689 | 2,837 | +68% | 0 | 0 | — |
case-11 | fail→pass | 18,325 | 17,756 | -3% | 1 | 1 | 0% | 1,588 | 2,563 | +61% | 0 | 0 | — |
case-12 | fail→pass | 17,259 | 19,952 | +16% | 1 | 1 | 0% | 1,834 | 2,825 | +54% | 0 | 0 | — |
case-13 | pass→pass | 22,446 | 18,767 | -16% | 1 | 1 | 0% | 2,527 | 2,628 | +4% | 0 | 0 | — |
case-14 | pass→pass | 20,493 | 27,714 | +35% | 1 | 1 | 0% | 1,792 | 2,866 | +60% | 0 | 0 | — |
case-15 | fail→pass | 18,726 | 16,929 | -10% | 1 | 1 | 0% | 1,951 | 2,529 | +30% | 0 | 0 | — |
case-16 | pass→fail | 19,582 | 16,242 | -17% | 1 | 1 | 0% | 1,911 | 2,264 | +18% | 0 | 0 | — |
case-17 | pass→pass | 21,276 | 15,303 | -28% | 1 | 1 | 0% | 1,997 | 2,844 | +42% | 0 | 0 | — |
case-18 | fail→pass | 16,884 | 21,333 | +26% | 1 | 1 | 0% | 2,300 | 2,996 | +30% | 0 | 0 | — |
case-19 | fail→pass | 12,135 | 19,517 | +61% | 1 | 1 | 0% | 1,737 | 2,607 | +50% | 0 | 0 | — |
case-20 | pass→pass | 24,173 | 16,995 | -30% | 1 | 1 | 0% | 2,388 | 3,349 | +40% | 0 | 0 | — |
case-21 | pass→pass | 22,272 | 16,870 | -24% | 1 | 1 | 0% | 2,141 | 2,585 | +21% | 0 | 0 | — |
case-22 | pass→pass | 19,906 | 21,945 | +10% | 1 | 1 | 0% | 2,163 | 3,161 | +46% | 0 | 0 | — |
case-23 | fail→fail | 26,279 | 22,080 | -16% | 1 | 1 | 0% | 2,503 | 2,947 | +18% | 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 +22 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.