Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Turn a task you repeat every week into a reusable personal skill or prompt — so you say 'do this' instead of re-explaining it every time. Use when asked help me make a skill for, turn this repetitive task into a template, I do this every week, or create a reusable prompt for this. Produces a captured spec of the repetitive task (its inputs, steps, and what good output looks like), a reusable skill/prompt you can invoke by name, and guidance on saving and refining it — lowering the barrier from A
.claude/skills/mohitagw15856-make-me-a-skill/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 33% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 53% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 7% | 0% |
The biggest leverage in working with AI is turning your repeated tasks into reusable skills — so formatting the meeting notes, writing the weekly update, or organizing the tasks becomes "do the thing" instead of re-explaining it every time. This captures one such task into a clean, reusable skill or prompt you can invoke by name, and shows you how to save and improve it. Do it once and you'll do it for everything.
Ask for these if not provided:
What it does: one line]. Inputs it needs: the info you feed it]. The skill/prompt (reusable): > The invocable instruction — trigger, steps, and the output template it should follow.]
Save it as: SKILL.md / saved prompt / snippet], invoke with "trigger phrase]". Refine it: each time you use it, tweak the part that wasn't quite right. Then make one for your next repeated task.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 19,742 | 14,571 | -26% | 1 | 1 | 0% | 2,014 | 2,677 | +33% | 0 | 0 | — |
case-02 | fail→pass | 16,326 | 14,709 | -10% | 1 | 1 | 0% | 2,791 | 2,621 | -6% | 0 | 0 | — |
case-03 | pass→pass | 21,089 | 14,083 | -33% | 1 | 1 | 0% | 2,700 | 2,502 | -7% | 0 | 0 | — |
case-04 | pass→fail | 7,541 | 9,496 | +26% | 1 | 1 | 0% | 512 | 2,664 | +420% | 0 | 0 | — |
case-05 | pass→fail | 11,205 | 22,279 | +99% | 1 | 1 | 0% | 2,286 | 4,106 | +80% | 0 | 0 | — |
case-06 | pass→pass | 15,272 | 27,453 | +80% | 1 | 1 | 0% | 1,834 | 5,069 | +176% | 0 | 0 | — |
case-07 | fail→pass | 17,077 | 14,650 | -14% | 1 | 1 | 0% | 2,134 | 2,390 | +12% | 0 | 0 | — |
case-08 | pass→pass | 15,162 | 15,641 | +3% | 1 | 1 | 0% | 1,582 | 2,633 | +66% | 0 | 0 | — |
case-09 | fail→fail | 14,635 | 14,434 | -1% | 1 | 1 | 0% | 1,794 | 2,549 | +42% | 0 | 0 | — |
case-10 | fail→pass | 14,473 | 21,946 | +52% | 1 | 1 | 0% | 1,850 | 2,838 | +53% | 0 | 0 | — |
case-11 | fail→pass | 15,536 | 16,071 | +3% | 1 | 1 | 0% | 2,696 | 2,877 | +7% | 0 | 0 | — |
case-12 | pass→pass | 21,418 | 17,992 | -16% | 1 | 1 | 0% | 3,512 | 3,081 | -12% | 0 | 0 | — |
case-13 | fail→pass | 19,656 | 12,776 | -35% | 1 | 1 | 0% | 2,656 | 3,203 | +21% | 0 | 0 | — |
case-14 | fail→pass | 16,732 | 12,325 | -26% | 1 | 1 | 0% | 2,285 | 3,038 | +33% | 0 | 0 | — |
case-15 | fail→pass | 16,513 | 15,178 | -8% | 1 | 1 | 0% | 2,221 | 2,859 | +29% | 0 | 0 | — |
case-16 | fail→fail | 19,746 | 14,810 | -25% | 1 | 1 | 0% | 2,640 | 2,793 | +6% | 0 | 0 | — |
case-17 | fail→pass | 22,726 | 11,014 | -52% | 1 | 1 | 0% | 2,530 | 2,471 | -2% | 0 | 0 | — |
case-18 | fail→pass | 21,512 | 16,703 | -22% | 1 | 1 | 0% | 2,424 | 2,540 | +5% | 0 | 0 | — |
case-19 | fail→fail | 19,451 | 17,804 | -8% | 1 | 1 | 0% | 2,369 | 2,919 | +23% | 0 | 0 | — |
case-20 | fail→fail | 16,806 | 16,121 | -4% | 1 | 1 | 0% | 2,134 | 2,875 | +35% | 0 | 0 | — |
case-21 | fail→pass | 21,099 | 14,851 | -30% | 1 | 1 | 0% | 2,446 | 2,682 | +10% | 0 | 0 | — |
case-22 | fail→fail | 18,543 | 15,166 | -18% | 1 | 1 | 0% | 2,306 | 2,702 | +17% | 0 | 0 | — |
case-23 | fail→fail | 19,593 | 11,484 | -41% | 1 | 1 | 0% | 2,504 | 2,829 | +13% | 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. 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.