Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Act as a body-double for a work session — a present, low-pressure companion that keeps you accountable and moving through the task without doing it for you. Use when asked be my body double, keep me company while I work, help me focus on this task, or I work better with someone there. Produces a session structure (goal, time block, check-in cadence), gentle presence and momentum nudges at intervals, distraction rescue when you drift, and an end-of-session acknowledgment — recreating the focus th
.claude/skills/mohitagw15856-body-doubling-partner/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 98% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -1% | 0% |
Many people — especially with ADHD — focus far better when someone else is simply present, even doing their own thing. It's called body-doubling. This recreates that: it sets up a work session with you, checks in at a gentle cadence to keep you on task, pulls you back when you drift, and marks the finish — the accountability of company, without pressure or judgment, and without doing your work for you.
Ask for these if not provided:
Goal this block: one thing]. We start… now. ⏱
Check-in cadence: every x] — I'll nudge with "still on it? what are you working on?" If you drift: no shame — I'll just say "back to it, what's the next small piece?" At the end: we mark what got done, however much.
(Tell me when you want the first check-in, or just report in as you go.)
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-09 | pass→pass | 9,255 | 7,618 | -18% | 1 | 1 | 0% | 1,432 | 2,044 | +43% | 0 | 0 | — |
case-01 | pass→fail | 10,320 | 10,514 | +2% | 1 | 1 | 0% | 1,741 | 1,775 | +2% | 0 | 0 | — |
case-02 | fail→pass | 10,918 | 6,685 | -39% | 1 | 1 | 0% | 1,806 | 1,853 | +3% | 0 | 0 | — |
case-03 | fail→fail | 8,515 | 6,148 | -28% | 1 | 1 | 0% | 1,386 | 1,890 | +36% | 0 | 0 | — |
case-08 | fail→pass | 7,080 | 9,099 | +29% | 1 | 1 | 0% | 1,109 | 2,193 | +98% | 0 | 0 | — |
case-04 | pass→fail | 13,081 | 18,712 | +43% | 1 | 1 | 0% | 2,138 | 3,110 | +45% | 0 | 0 | — |
case-05 | pass→pass | 9,361 | 8,435 | -10% | 1 | 1 | 0% | 1,517 | 2,185 | +44% | 0 | 0 | — |
case-06 | pass→fail | 15,033 | 18,595 | +24% | 1 | 1 | 0% | 2,388 | 4,016 | +68% | 0 | 0 | — |
case-07 | fail→pass | 9,147 | 7,822 | -14% | 1 | 1 | 0% | 1,514 | 1,919 | +27% | 0 | 0 | — |
case-10 | pass→pass | 3,009 | 5,493 | +83% | 1 | 1 | 0% | 536 | 1,778 | +232% | 0 | 0 | — |
case-11 | pass→pass | 7,469 | 6,183 | -17% | 1 | 1 | 0% | 1,017 | 1,788 | +76% | 0 | 0 | — |
case-12 | fail→pass | 8,111 | 3,891 | -52% | 1 | 1 | 0% | 1,256 | 1,478 | +18% | 0 | 0 | — |
case-13 | pass→pass | 10,781 | 6,931 | -36% | 1 | 1 | 0% | 1,637 | 1,860 | +14% | 0 | 0 | — |
case-14 | pass→pass | 6,638 | 5,744 | -13% | 1 | 1 | 0% | 992 | 1,796 | +81% | 0 | 0 | — |
case-15 | pass→pass | 7,458 | 4,246 | -43% | 1 | 1 | 0% | 1,096 | 1,471 | +34% | 0 | 0 | — |
case-16 | pass→pass | 4,177 | 3,927 | -6% | 1 | 1 | 0% | 692 | 1,458 | +111% | 0 | 0 | — |
case-17 | fail→pass | 9,878 | 4,043 | -59% | 1 | 1 | 0% | 1,529 | 1,514 | -1% | 0 | 0 | — |
case-18 | pass→pass | 5,477 | 4,794 | -12% | 1 | 1 | 0% | 876 | 1,684 | +92% | 0 | 0 | — |
case-19 | pass→pass | 8,803 | 8,087 | -8% | 1 | 1 | 0% | 1,474 | 2,100 | +42% | 0 | 0 | — |
case-20 | pass→pass | 3,815 | 4,162 | +9% | 1 | 1 | 0% | 594 | 1,473 | +148% | 0 | 0 | — |
case-21 | pass→pass | 10,237 | 8,571 | -16% | 1 | 1 | 0% | 1,545 | 2,073 | +34% | 0 | 0 | — |
case-22 | fail→pass | 8,959 | 8,488 | -5% | 1 | 1 | 0% | 1,648 | 2,357 | +43% | 0 | 0 | — |
case-23 | pass→pass | 9,843 | 9,784 | -1% | 1 | 1 | 0% | 1,512 | 2,221 | +47% | 0 | 0 | — |
case-24 | pass→pass | 7,699 | 6,585 | -14% | 1 | 1 | 0% | 1,239 | 1,726 | +39% | 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. 24 cases were attempted. The headline lift of +13 percentage points is the difference between those two pass rates over the 24 comparable cases. 3 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.