Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Write in-product onboarding copy that gets users to value fast. Use when asked to write onboarding copy, a welcome flow, product tour/tooltips, setup steps, or activation messaging. Produces the copy for an onboarding flow — welcome, the guided steps/tooltips toward the first win, progress and empty-to-active nudges, and a success moment — focused on the activation outcome, not a feature tour.
.claude/skills/mohitagw15856-onboarding-copy/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 45% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 81% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 21% | 0% |
The best onboarding doesn't tour features — it walks the user to their first real win (the "aha" where the product's value clicks). This skill writes the copy for that path: a welcome that sets the outcome, tooltips that guide the few steps that matter, and a success moment that confirms it worked — concise, encouraging, and skippable.
Given "onboarding for a habit-tracking app", write the flow copy anyway — infer the activation moment (the first win), the minimal steps to reach it, and the voice, labelling assumptions. Focus the copy on the outcome, not a feature list. Never hand back a question instead of copy.
Ask for these only if they aren't already provided (else infer and label):
Keep every piece concise, encouraging, and outcome-focused; note where copy must fit a tight space.
Product onboarding & activation practice — outcome-led welcome, guided path to the first win, progress nudges, and a celebrated activation moment.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | fail→pass | 14,931 | 14,706 | -2% | 1 | 1 | 0% | 2,602 | 3,238 | +24% | 0 | 0 | — |
case-01 | fail→pass | 9,926 | 10,672 | +8% | 1 | 1 | 0% | 1,951 | 2,826 | +45% | 0 | 0 | — |
case-02 | fail→pass | 16,864 | 10,570 | -37% | 1 | 1 | 0% | 3,223 | 2,893 | -10% | 0 | 0 | — |
case-03 | fail→pass | 6,904 | 10,632 | +54% | 1 | 1 | 0% | 1,367 | 2,477 | +81% | 0 | 0 | — |
case-04 | fail→pass | 12,144 | 12,437 | +2% | 1 | 1 | 0% | 2,377 | 2,882 | +21% | 0 | 0 | — |
case-06 | fail→fail | 6,270 | 9,276 | +48% | 1 | 1 | 0% | 1,133 | 2,262 | +100% | 0 | 0 | — |
case-07 | fail→pass | 6,266 | 10,868 | +73% | 1 | 1 | 0% | 1,240 | 2,679 | +116% | 0 | 0 | — |
case-08 | fail→fail | 16,461 | 12,856 | -22% | 1 | 1 | 0% | 2,964 | 2,976 | +0% | 0 | 0 | — |
case-09 | fail→pass | 12,520 | 10,038 | -20% | 1 | 1 | 0% | 2,211 | 2,673 | +21% | 0 | 0 | — |
case-10 | pass→pass | 14,075 | 9,683 | -31% | 1 | 1 | 0% | 2,542 | 2,554 | +0% | 0 | 0 | — |
case-11 | fail→pass | 13,334 | 10,078 | -24% | 1 | 1 | 0% | 2,455 | 2,594 | +6% | 0 | 0 | — |
case-12 | fail→pass | 14,506 | 10,522 | -27% | 1 | 1 | 0% | 2,568 | 2,742 | +7% | 0 | 0 | — |
case-13 | fail→pass | 15,497 | 11,225 | -28% | 1 | 1 | 0% | 2,509 | 2,699 | +8% | 0 | 0 | — |
case-14 | fail→fail | 12,027 | 9,597 | -20% | 1 | 1 | 0% | 1,919 | 2,403 | +25% | 0 | 0 | — |
case-15 | fail→pass | 11,082 | 11,152 | +1% | 1 | 1 | 0% | 1,999 | 2,728 | +36% | 0 | 0 | — |
case-16 | fail→pass | 16,305 | 11,838 | -27% | 1 | 1 | 0% | 2,859 | 2,870 | +0% | 0 | 0 | — |
case-17 | fail→pass | 14,930 | 12,626 | -15% | 1 | 1 | 0% | 2,679 | 2,909 | +9% | 0 | 0 | — |
case-18 | fail→pass | 12,046 | 7,551 | -37% | 1 | 1 | 0% | 2,222 | 2,026 | -9% | 0 | 0 | — |
case-19 | fail→pass | 10,382 | 7,674 | -26% | 1 | 1 | 0% | 1,720 | 2,064 | +20% | 0 | 0 | — |
case-20 | pass→pass | 7,022 | 8,850 | +26% | 1 | 1 | 0% | 1,067 | 2,215 | +108% | 0 | 0 | — |
case-21 | pass→pass | 9,602 | 10,736 | +12% | 1 | 1 | 0% | 1,549 | 2,441 | +58% | 0 | 0 | — |
case-22 | pass→pass | 10,368 | 13,220 | +28% | 1 | 1 | 0% | 1,738 | 2,829 | +63% | 0 | 0 | — |
case-23 | pass→pass | 10,650 | 7,382 | -31% | 1 | 1 | 0% | 1,729 | 1,900 | +10% | 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 +65 percentage points is the difference between those two pass rates over the 23 comparable cases.
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.