Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Write a compelling nonprofit impact or annual report that shows donors what their money achieved. Use when asked to write an impact report, an annual report, a grant outcomes report, or to report results to funders/donors. Produces a structured report — mission and year in brief, outcomes with real numbers and a beneficiary story, financials at a glance, and a forward ask — that builds trust and renews giving.
.claude/skills/mohitagw15856-impact-report/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 53% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 47% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 92% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 54% | 0% |
Donors give again when they can see what their last gift did. An impact report turns activity into outcomes — not "we ran 40 workshops" but "320 people found work, here's one of them" — and pairs the numbers with a human story and honest financials. This skill structures that report so it earns trust and the next gift.
Given "write our annual impact report" with a few stats, produce the full report anyway — structure it around the outcomes provided, and mark any figure or story you invent as (example — replace with real data) so the org swaps in true numbers. Never fabricate results as if real; never withhold for missing detail.
Ask for these only if they aren't already provided (else infer and label for replacement):
Mark invented numbers/stories as (example — replace with real data).
Nonprofit reporting and donor-stewardship practice — outcomes over activities, evidence plus story, transparent financials, and a stewardship 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 | 10,969 | 12,614 | +15% | 1 | 1 | 0% | 2,279 | 2,835 | +24% | 0 | 0 | — |
case-02 | pass→pass | 14,123 | 13,750 | -3% | 1 | 1 | 0% | 2,975 | 3,629 | +22% | 0 | 0 | — |
case-03 | pass→pass | 19,224 | 16,782 | -13% | 1 | 1 | 0% | 3,319 | 3,556 | +7% | 0 | 0 | — |
case-04 | pass→fail | 29,263 | 23,700 | -19% | 1 | 1 | 0% | 5,194 | 4,918 | -5% | 0 | 0 | — |
case-05 | pass→pass | 11,073 | 8,995 | -19% | 1 | 1 | 0% | 2,165 | 2,475 | +14% | 0 | 0 | — |
case-06 | pass→fail | 8,929 | 12,541 | +40% | 1 | 1 | 0% | 1,758 | 3,096 | +76% | 0 | 0 | — |
case-07 | pass→pass | 14,693 | 11,383 | -23% | 1 | 1 | 0% | 2,349 | 2,774 | +18% | 0 | 0 | — |
case-08 | pass→pass | 11,591 | 14,069 | +21% | 1 | 1 | 0% | 2,100 | 3,006 | +43% | 0 | 0 | — |
case-09 | pass→pass | 12,321 | 12,313 | -0% | 1 | 1 | 0% | 2,082 | 2,829 | +36% | 0 | 0 | — |
case-10 | pass→pass | 13,088 | 12,942 | -1% | 1 | 1 | 0% | 2,318 | 2,990 | +29% | 0 | 0 | — |
case-11 | fail→pass | 11,842 | 12,864 | +9% | 1 | 1 | 0% | 1,961 | 2,997 | +53% | 0 | 0 | — |
case-12 | fail→pass | 13,221 | 14,329 | +8% | 1 | 1 | 0% | 2,246 | 3,304 | +47% | 0 | 0 | — |
case-13 | pass→pass | 16,736 | 13,146 | -21% | 1 | 1 | 0% | 2,716 | 2,891 | +6% | 0 | 0 | — |
case-14 | fail→fail | 12,204 | 11,600 | -5% | 1 | 1 | 0% | 2,059 | 2,713 | +32% | 0 | 0 | — |
case-15 | pass→pass | 10,053 | 13,004 | +29% | 1 | 1 | 0% | 1,969 | 3,025 | +54% | 0 | 0 | — |
case-16 | pass→pass | 15,744 | 12,606 | -20% | 1 | 1 | 0% | 2,816 | 2,920 | +4% | 0 | 0 | — |
case-17 | fail→pass | 8,271 | 12,918 | +56% | 1 | 1 | 0% | 1,465 | 2,820 | +92% | 0 | 0 | — |
case-18 | fail→fail | 11,345 | 14,507 | +28% | 1 | 1 | 0% | 1,923 | 3,034 | +58% | 0 | 0 | — |
case-19 | pass→pass | 14,046 | 14,664 | +4% | 1 | 1 | 0% | 2,356 | 3,222 | +37% | 0 | 0 | — |
case-20 | fail→pass | 11,068 | 15,397 | +39% | 1 | 1 | 0% | 2,116 | 3,250 | +54% | 0 | 0 | — |
case-21 | pass→pass | 14,728 | 13,304 | -10% | 1 | 1 | 0% | 2,572 | 2,986 | +16% | 0 | 0 | — |
case-22 | pass→pass | 9,727 | 12,837 | +32% | 1 | 1 | 0% | 1,751 | 2,844 | +62% | 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 +14 percentage points is the difference between those two pass rates over the 22 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.