Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Declutter a room (or a whole home) with a plan that actually finishes — a sensible order, quick decision rules, and a way to keep it from creeping back. Use when asked how to declutter, help me declutter my [room], I'm overwhelmed by clutter, or a decluttering plan. Produces a room-by-room order, a decision framework for keep/donate/sell/toss, time-boxed sessions sized to your energy, where to route the outflow, and habits to stop the clutter returning — without demanding you become a minimalist
.claude/skills/mohitagw15856-declutter-by-room/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 21% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 57% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 66% | 0% |
Decluttering stalls for two reasons: it's overwhelming to start, and the stuff creeps back. This gives you a finishable plan — a sensible order, fast keep-or-go rules so you're not agonizing over each item, sessions sized to your actual energy, and maintenance habits — so the space stays clear without requiring a personality transplant into minimalism.
Ask for these if not provided:
Order: start with easy win] → next] → … (momentum-first). Decision rules: keep use/love] · donate/sell good, unused] · toss/recycle broken/expired] · "might need it" → simple test] · sentimental → test/box]. Sessions: chunk size + cadence for your energy]. Route the outflow: donate where · sell how · recycle/dispose] — get it out fast. Keep it clear: one-in-one-out · weekly reset · a home for everything].
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 25,653 | 25,242 | -2% | 1 | 1 | 0% | 3,180 | 3,936 | +24% | 0 | 0 | — |
case-02 | pass→pass | 29,822 | 26,616 | -11% | 1 | 1 | 0% | 3,697 | 4,242 | +15% | 0 | 0 | — |
case-03 | fail→pass | 23,513 | 21,054 | -10% | 1 | 1 | 0% | 2,818 | 3,397 | +21% | 0 | 0 | — |
case-04 | fail→fail | 23,469 | 25,377 | +8% | 1 | 1 | 0% | 2,741 | 3,736 | +36% | 0 | 0 | — |
case-05 | fail→fail | 20,152 | 13,904 | -31% | 1 | 1 | 0% | 2,370 | 3,140 | +32% | 0 | 0 | — |
case-06 | fail→fail | 20,153 | 17,004 | -16% | 1 | 1 | 0% | 3,316 | 3,800 | +15% | 0 | 0 | — |
case-07 | pass→pass | 20,522 | 20,969 | +2% | 1 | 1 | 0% | 2,383 | 3,372 | +42% | 0 | 0 | — |
case-08 | pass→pass | 18,120 | 14,291 | -21% | 1 | 1 | 0% | 2,087 | 3,013 | +44% | 0 | 0 | — |
case-09 | fail→fail | 22,912 | 19,466 | -15% | 1 | 1 | 0% | 2,663 | 3,090 | +16% | 0 | 0 | — |
case-10 | fail→pass | 19,278 | 19,538 | +1% | 1 | 1 | 0% | 2,211 | 3,158 | +43% | 0 | 0 | — |
case-11 | pass→pass | 15,433 | 16,017 | +4% | 1 | 1 | 0% | 1,621 | 2,807 | +73% | 0 | 0 | — |
case-12 | pass→fail | 13,040 | 16,923 | +30% | 1 | 1 | 0% | 2,078 | 2,821 | +36% | 0 | 0 | — |
case-13 | pass→pass | 19,749 | 17,186 | -13% | 1 | 1 | 0% | 2,295 | 2,892 | +26% | 0 | 0 | — |
case-14 | fail→pass | 18,789 | 19,826 | +6% | 1 | 1 | 0% | 2,086 | 3,271 | +57% | 0 | 0 | — |
case-15 | fail→fail | 16,350 | 15,191 | -7% | 1 | 1 | 0% | 1,818 | 2,661 | +46% | 0 | 0 | — |
case-16 | pass→pass | 14,979 | 20,115 | +34% | 1 | 1 | 0% | 2,371 | 3,325 | +40% | 0 | 0 | — |
case-17 | fail→pass | 19,339 | 15,591 | -19% | 1 | 1 | 0% | 2,181 | 3,619 | +66% | 0 | 0 | — |
case-18 | pass→pass | 21,069 | 23,024 | +9% | 1 | 1 | 0% | 2,155 | 3,650 | +69% | 0 | 0 | — |
case-19 | pass→pass | 16,327 | 10,048 | -38% | 1 | 1 | 0% | 1,714 | 2,628 | +53% | 0 | 0 | — |
case-20 | fail→pass | 20,993 | 20,803 | -1% | 1 | 1 | 0% | 2,329 | 3,247 | +39% | 0 | 0 | — |
case-21 | pass→pass | 17,718 | 18,335 | +3% | 1 | 1 | 0% | 1,791 | 2,902 | +62% | 0 | 0 | — |
case-22 | fail→fail | 23,192 | 22,158 | -4% | 1 | 1 | 0% | 2,772 | 3,751 | +35% | 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 +23 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.