Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Write a warm donor update or stewardship message that makes a supporter feel their gift mattered. Use when asked to write a donor update, a thank-you/stewardship email, a supporter newsletter, or a gift acknowledgement. Produces a donor-centred update — sincere thanks, the specific impact of their support, a brief story, and a light, optional next step — that strengthens the relationship and sets up the next gift.
.claude/skills/mohitagw15856-donor-update/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 38% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 67% | 0% |
| case-21 | ✗→✓ | ▲ Improved | 51% | 0% |
Donor retention is cheaper than acquisition and runs on one feeling: my gift mattered and I'm appreciated. A stewardship update delivers that — thank them sincerely, show the concrete impact of their support, and make them feel part of the work, without immediately asking for more. This skill writes that message so donors stay donors.
Given "write a thank-you update to our donors", produce the full message anyway — build it around the impact provided, and mark any invented figure or story as (example — replace with real data). Never fabricate impact as real; never withhold for missing detail.
Ask for these only if they aren't already provided (else infer and label for replacement):
Provide a short version (for SMS/social/quick email) and mark invented specifics for replacement.
Donor-stewardship practice — gratitude-first, impact attribution, storytelling, and relationship-building ahead of the next ask.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 9,946 | 10,116 | +2% | 1 | 1 | 0% | 1,845 | 2,288 | +24% | 0 | 0 | — |
case-02 | fail→pass | 9,828 | 10,777 | +10% | 1 | 1 | 0% | 1,881 | 2,604 | +38% | 0 | 0 | — |
case-03 | pass→pass | 14,695 | 9,410 | -36% | 1 | 1 | 0% | 2,518 | 2,420 | -4% | 0 | 0 | — |
case-04 | pass→pass | 9,344 | 10,416 | +11% | 1 | 1 | 0% | 1,697 | 2,326 | +37% | 0 | 0 | — |
case-05 | pass→pass | 11,955 | 14,900 | +25% | 1 | 1 | 0% | 1,998 | 3,143 | +57% | 0 | 0 | — |
case-06 | pass→pass | 11,783 | 10,327 | -12% | 1 | 1 | 0% | 1,733 | 2,238 | +29% | 0 | 0 | — |
case-07 | pass→pass | 9,306 | 10,968 | +18% | 1 | 1 | 0% | 1,478 | 2,352 | +59% | 0 | 0 | — |
case-08 | pass→pass | 11,114 | 9,336 | -16% | 1 | 1 | 0% | 1,688 | 2,094 | +24% | 0 | 0 | — |
case-09 | fail→pass | 12,580 | 9,703 | -23% | 1 | 1 | 0% | 1,795 | 2,120 | +18% | 0 | 0 | — |
case-10 | pass→pass | 8,841 | 8,075 | -9% | 1 | 1 | 0% | 1,400 | 2,149 | +54% | 0 | 0 | — |
case-11 | pass→pass | 9,352 | 9,905 | +6% | 1 | 1 | 0% | 1,418 | 2,209 | +56% | 0 | 0 | — |
case-12 | pass→pass | 9,339 | 10,970 | +17% | 1 | 1 | 0% | 1,261 | 2,389 | +89% | 0 | 0 | — |
case-13 | pass→pass | 13,477 | 11,726 | -13% | 1 | 1 | 0% | 1,915 | 2,348 | +23% | 0 | 0 | — |
case-14 | pass→pass | 11,684 | 9,853 | -16% | 1 | 1 | 0% | 1,777 | 2,193 | +23% | 0 | 0 | — |
case-15 | pass→pass | 12,621 | 10,511 | -17% | 1 | 1 | 0% | 1,821 | 2,261 | +24% | 0 | 0 | — |
case-16 | pass→pass | 11,578 | 9,397 | -19% | 1 | 1 | 0% | 1,693 | 2,075 | +23% | 0 | 0 | — |
case-17 | fail→pass | 9,787 | 11,317 | +16% | 1 | 1 | 0% | 1,402 | 2,342 | +67% | 0 | 0 | — |
case-18 | pass→pass | 12,371 | 10,085 | -18% | 1 | 1 | 0% | 1,673 | 2,269 | +36% | 0 | 0 | — |
case-19 | pass→pass | 11,940 | 11,864 | -1% | 1 | 1 | 0% | 1,856 | 2,437 | +31% | 0 | 0 | — |
case-20 | pass→pass | 10,608 | 10,196 | -4% | 1 | 1 | 0% | 1,622 | 2,037 | +26% | 0 | 0 | — |
case-21 | fail→pass | 11,709 | 11,089 | -5% | 1 | 1 | 0% | 1,576 | 2,386 | +51% | 0 | 0 | — |
case-22 | fail→pass | 11,186 | 11,302 | +1% | 1 | 1 | 0% | 1,634 | 2,312 | +41% | 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 +27 percentage points is the difference between those two pass rates over the 22 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.