Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cut your home energy bills with a prioritized plan — the free and cheap fixes first, then the upgrades that actually pay back. Use when asked how to lower my energy bill, make my home more energy efficient, reduce heating/cooling costs, or save energy at home. Produces a read on where your energy (and money) likely goes, a ranked list of fixes from free behavior changes to low-cost improvements to bigger investments with payback estimates, quick wins to start today, and what to measure — flaggin
.claude/skills/mohitagw15856-home-energy-savings/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -17% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -33% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 20% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 61% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 41% | 0% |
Energy advice usually jumps to expensive upgrades, but the biggest early wins are free or cheap: sealing drafts, adjusting the thermostat, tackling the handful of appliances that dominate the bill. This finds where your energy likely goes and gives a ranked plan — free behavior changes first, then low-cost fixes, then the bigger investments with honest payback — so you save without overspending to save.
Ask for these if not provided:
Where it likely goes: heating/cooling · water heating · appliances].
Do now (free): thermostat · phantom loads · washing · unused rooms]. Cheap fixes (high return): seal drafts · weatherstrip · LEDs · smart thermostat · water heater]. Bigger investments (payback): insulation ~payback] · windows ~payback] · heating upgrade ~payback]] — owners only. Check rebates: local incentives can change the math]. Measure: track the bill / usage].
> Savings and rebates depend on your home and region — treat estimates as guides and check local incentives.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 36,551 | 31,374 | -14% | 1 | 1 | 0% | 5,712 | 4,767 | -17% | 0 | 0 | — |
case-02 | fail→pass | 40,364 | 23,108 | -43% | 1 | 1 | 0% | 6,045 | 4,026 | -33% | 0 | 0 | — |
case-03 | pass→pass | 39,893 | 29,434 | -26% | 1 | 1 | 0% | 6,526 | 5,134 | -21% | 0 | 0 | — |
case-04 | fail→pass | 21,487 | 19,270 | -10% | 1 | 1 | 0% | 2,736 | 3,285 | +20% | 0 | 0 | — |
case-05 | pass→pass | 23,654 | 22,144 | -6% | 1 | 1 | 0% | 2,985 | 3,781 | +27% | 0 | 0 | — |
case-06 | fail→pass | 19,244 | 22,871 | +19% | 1 | 1 | 0% | 2,592 | 4,186 | +61% | 0 | 0 | — |
case-07 | pass→fail | 22,847 | 21,196 | -7% | 1 | 1 | 0% | 2,654 | 3,763 | +42% | 0 | 0 | — |
case-08 | fail→pass | 22,381 | 20,151 | -10% | 1 | 1 | 0% | 2,475 | 3,482 | +41% | 0 | 0 | — |
case-09 | fail→pass | 18,373 | 20,159 | +10% | 1 | 1 | 0% | 2,210 | 2,997 | +36% | 0 | 0 | — |
case-10 | fail→pass | 21,187 | 20,611 | -3% | 1 | 1 | 0% | 2,734 | 3,756 | +37% | 0 | 0 | — |
case-11 | fail→pass | 21,411 | 24,983 | +17% | 1 | 1 | 0% | 2,657 | 4,111 | +55% | 0 | 0 | — |
case-12 | pass→pass | 19,470 | 20,000 | +3% | 1 | 1 | 0% | 2,197 | 2,906 | +32% | 0 | 0 | — |
case-13 | pass→pass | 17,500 | 20,397 | +17% | 1 | 1 | 0% | 2,109 | 3,455 | +64% | 0 | 0 | — |
case-14 | pass→pass | 21,070 | 19,683 | -7% | 1 | 1 | 0% | 2,043 | 2,804 | +37% | 0 | 0 | — |
case-15 | pass→pass | 24,708 | 25,608 | +4% | 1 | 1 | 0% | 3,160 | 3,483 | +10% | 0 | 0 | — |
case-16 | pass→pass | 24,916 | 24,149 | -3% | 1 | 1 | 0% | 3,080 | 4,046 | +31% | 0 | 0 | — |
case-17 | pass→pass | 20,684 | 15,475 | -25% | 1 | 1 | 0% | 2,124 | 3,286 | +55% | 0 | 0 | — |
case-18 | pass→pass | 19,902 | 20,920 | +5% | 1 | 1 | 0% | 2,282 | 3,008 | +32% | 0 | 0 | — |
case-19 | fail→pass | 21,703 | 16,196 | -25% | 1 | 1 | 0% | 3,042 | 3,492 | +15% | 0 | 0 | — |
case-20 | fail→pass | 18,268 | 16,162 | -12% | 1 | 1 | 0% | 2,019 | 3,111 | +54% | 0 | 0 | — |
case-21 | pass→fail | 25,034 | 23,886 | -5% | 1 | 1 | 0% | 4,575 | 4,635 | +1% | 0 | 0 | — |
case-22 | pass→pass | 21,130 | 22,503 | +6% | 1 | 1 | 0% | 2,623 | 3,466 | +32% | 0 | 0 | — |
case-23 | pass→pass | 29,144 | 17,988 | -38% | 1 | 1 | 0% | 3,704 | 3,494 | -6% | 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.