Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Audit your desk setup and fix what's hurting your neck, back, wrists, or eyes — with specific, mostly-free adjustments before you buy anything. Use when asked to check my desk setup, ergonomics help, my [wrists/neck/back] hurt from my desk, or how to set up my workstation. Produces a point-by-point setup check (chair, screen, keyboard, mouse, lighting), the specific fixes ranked free-first, cheap upgrades only if needed, and micro-break habits — with a 'see a professional for persistent pain/num
.claude/skills/mohitagw15856-desk-ergonomics-audit/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 56% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 66% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 66% | 0% |
Most desk pain comes from a handful of misalignments you can fix for free by moving things a few inches — a screen too low, a chair too high, wrists bent at the keyboard. This audits your setup point by point, gives the specific adjustment for each, and only suggests buying something when a free fix won't do.
Ask for these if not provided:
| Area | Target | Your fix | |---|---|---| | Monitor | top ~third at eye level | raise/lower] | | Chair | thighs level, feet supported | adjust] | | Keyboard/mouse | elbows ~90°, wrists straight | reposition] | | Lighting | no glare, screen not brightest thing | fix] | | Laptop | screen up + external input | if applicable] |
Free fixes first: list]. Worth buying (only if needed): item → why]. Move: micro-break every x] — cue].
> Persistent pain, numbness, or tingling isn't an ergonomics tweak — see a professional.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 23,043 | 17,341 | -25% | 1 | 1 | 0% | 2,708 | 2,829 | +4% | 0 | 0 | — |
case-02 | pass→pass | 25,006 | 22,529 | -10% | 1 | 1 | 0% | 2,809 | 3,688 | +31% | 0 | 0 | — |
case-03 | fail→pass | 28,001 | 23,377 | -17% | 1 | 1 | 0% | 3,495 | 3,607 | +3% | 0 | 0 | — |
case-04 | fail→pass | 21,639 | 20,533 | -5% | 1 | 1 | 0% | 2,750 | 3,214 | +17% | 0 | 0 | — |
case-05 | fail→pass | 26,547 | 18,217 | -31% | 1 | 1 | 0% | 1,749 | 2,720 | +56% | 0 | 0 | — |
case-06 | fail→pass | 16,037 | 18,314 | +14% | 1 | 1 | 0% | 1,823 | 3,033 | +66% | 0 | 0 | — |
case-07 | pass→pass | 15,813 | 16,282 | +3% | 1 | 1 | 0% | 1,643 | 2,660 | +62% | 0 | 0 | — |
case-08 | fail→fail | 17,598 | 17,182 | -2% | 1 | 1 | 0% | 1,867 | 2,632 | +41% | 0 | 0 | — |
case-09 | pass→pass | 12,360 | 17,581 | +42% | 1 | 1 | 0% | 2,090 | 2,849 | +36% | 0 | 0 | — |
case-10 | pass→pass | 19,204 | 19,534 | +2% | 1 | 1 | 0% | 1,988 | 3,036 | +53% | 0 | 0 | — |
case-11 | pass→pass | 16,967 | 17,760 | +5% | 1 | 1 | 0% | 1,680 | 2,968 | +77% | 0 | 0 | — |
case-12 | pass→pass | 14,307 | 13,871 | -3% | 1 | 1 | 0% | 1,542 | 3,288 | +113% | 0 | 0 | — |
case-13 | fail→pass | 16,382 | 18,612 | +14% | 1 | 1 | 0% | 1,773 | 2,947 | +66% | 0 | 0 | — |
case-14 | pass→pass | 16,856 | 15,626 | -7% | 1 | 1 | 0% | 1,838 | 2,547 | +39% | 0 | 0 | — |
case-15 | pass→pass | 16,516 | 16,108 | -2% | 1 | 1 | 0% | 1,825 | 2,632 | +44% | 0 | 0 | — |
case-16 | pass→pass | 18,871 | 16,589 | -12% | 1 | 1 | 0% | 1,998 | 2,841 | +42% | 0 | 0 | — |
case-17 | pass→fail | 13,149 | 14,938 | +14% | 1 | 1 | 0% | 1,325 | 2,539 | +92% | 0 | 0 | — |
case-18 | fail→pass | 11,715 | 15,030 | +28% | 1 | 1 | 0% | 1,192 | 2,372 | +99% | 0 | 0 | — |
case-19 | pass→pass | 15,792 | 10,750 | -32% | 1 | 1 | 0% | 1,647 | 2,642 | +60% | 0 | 0 | — |
case-20 | pass→pass | 19,958 | 17,256 | -14% | 1 | 1 | 0% | 2,469 | 2,790 | +13% | 0 | 0 | — |
case-21 | pass→pass | 31,451 | 40,215 | +28% | 1 | 1 | 0% | 3,548 | 3,844 | +8% | 0 | 0 | — |
case-22 | pass→pass | 31,967 | 24,855 | -22% | 1 | 1 | 0% | 3,553 | 4,128 | +16% | 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.