Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Break the paralysis on the thing you keep not starting with a 2-minute launch sequence — a countdown into motion before the resistance can win. Use when asked I keep putting this off, help me finally start, I've been avoiding this for days, or I can't make myself begin. Produces a diagnosis of what flavor of resistance is stopping you, a 2-minute launch move matched to it, a literal countdown into action, and a bare-minimum win definition — designed to convert avoidance into motion in the next 1
.claude/skills/mohitagw15856-the-2-minute-launch/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 50% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 45% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 61% | 0% |
Some tasks you've avoided for days aren't hard — they're un-started, and every day of avoidance adds dread. Planning more doesn't help; launching does. This diagnoses what's actually blocking you (boredom? fear? fuzziness?), gives a 2-minute move matched to it, and counts you into motion right now. The goal isn't a schedule — it's you, in action, within the next two minutes.
Ask for these if not provided:
What's actually blocking you: boredom / fear / fuzziness / overwhelm / perfectionism]. Your 2-minute launch: the matched move]. Minimum win (guaranteed): the tiniest "started" counts].
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 9,736 | 10,830 | +11% | 1 | 1 | 0% | 1,276 | 1,821 | +43% | 0 | 0 | — |
case-02 | fail→fail | 13,102 | 9,203 | -30% | 1 | 1 | 0% | 1,302 | 1,991 | +53% | 0 | 0 | — |
case-13 | fail→pass | 8,656 | 11,905 | +38% | 1 | 1 | 0% | 1,162 | 1,742 | +50% | 0 | 0 | — |
case-03 | pass→pass | 17,013 | 9,065 | -47% | 1 | 1 | 0% | 1,427 | 2,052 | +44% | 0 | 0 | — |
case-04 | fail→pass | 13,150 | 6,525 | -50% | 1 | 1 | 0% | 1,210 | 1,758 | +45% | 0 | 0 | — |
case-05 | fail→pass | 18,203 | 5,565 | -69% | 1 | 1 | 0% | 1,641 | 1,752 | +7% | 0 | 0 | — |
case-06 | fail→pass | 12,472 | 13,763 | +10% | 1 | 1 | 0% | 1,196 | 1,930 | +61% | 0 | 0 | — |
case-07 | fail→fail | 14,013 | 5,297 | -62% | 1 | 1 | 0% | 1,326 | 1,696 | +28% | 0 | 0 | — |
case-08 | fail→fail | 7,732 | 11,733 | +52% | 1 | 1 | 0% | 1,286 | 2,029 | +58% | 0 | 0 | — |
case-09 | fail→pass | 13,591 | 5,484 | -60% | 1 | 1 | 0% | 1,241 | 1,939 | +56% | 0 | 0 | — |
case-10 | fail→pass | 15,548 | 12,811 | -18% | 1 | 1 | 0% | 1,402 | 1,903 | +36% | 0 | 0 | — |
case-11 | fail→fail | 10,770 | 11,196 | +4% | 1 | 1 | 0% | 1,358 | 1,893 | +39% | 0 | 0 | — |
case-12 | fail→pass | 16,055 | 11,159 | -30% | 1 | 1 | 0% | 1,683 | 1,807 | +7% | 0 | 0 | — |
case-14 | fail→pass | 16,219 | 10,847 | -33% | 1 | 1 | 0% | 1,433 | 1,803 | +26% | 0 | 0 | — |
case-15 | fail→pass | 12,181 | 11,739 | -4% | 1 | 1 | 0% | 1,137 | 1,755 | +54% | 0 | 0 | — |
case-16 | fail→fail | 14,654 | 10,097 | -31% | 1 | 1 | 0% | 1,388 | 1,677 | +21% | 0 | 0 | — |
case-17 | fail→pass | 15,241 | 12,875 | -16% | 1 | 1 | 0% | 1,310 | 1,832 | +40% | 0 | 0 | — |
case-18 | fail→pass | 16,598 | 13,007 | -22% | 1 | 1 | 0% | 1,476 | 2,182 | +48% | 0 | 0 | — |
case-19 | fail→pass | 13,032 | 10,807 | -17% | 1 | 1 | 0% | 1,143 | 1,693 | +48% | 0 | 0 | — |
case-20 | pass→fail | 27,395 | 25,335 | -8% | 1 | 1 | 0% | 3,770 | 4,153 | +10% | 0 | 0 | — |
case-21 | pass→fail | 25,406 | 33,286 | +31% | 1 | 1 | 0% | 3,413 | 4,309 | +26% | 0 | 0 | — |
case-22 | pass→fail | 16,866 | 30,949 | +83% | 1 | 1 | 0% | 3,070 | 4,678 | +52% | 0 | 0 | — |
case-23 | pass→fail | 28,608 | 22,357 | -22% | 1 | 1 | 0% | 3,625 | 3,239 | -11% | 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 +39 percentage points is the difference between those two pass rates over the 23 comparable cases. 4 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.