Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Quarterly / monthly financial report — masthead with KPIs, revenue and burn charts, P&L summary table, top-line highlights, and an outlook paragraph. Use when the brief mentions "financial report", "Q3 report", "MRR review", "P&L", or "财报".
.claude/skills/nexu-io-finance-report/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-13 | ✓→✗ | ▼ Worse | 6% | 0% |
| case-20 | ✓→✗ | ▼ Worse | 79% | 0% |
Produce a single-screen financial report in one self-contained HTML file.
palette tokens — never invent new ones.
(startup, division, project) from the brief. If unspecified, assume a quarterly SaaS report and pick believable numbers.
<style> block).show direction and percentage; accent colour used at most twice.
<artifact identifier="finance-report-q3" type="text/html" title="Q3 Finance Report">
<!doctype html>
<html>...</html>
</artifact>| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | fail→fail | 26,243 | 27,593 | +5% | 1 | 1 | 0% | 6,187 | 6,531 | +6% | 0 | 0 | — |
case-01 | fail→pass | 27,575 | 25,895 | -6% | 1 | 1 | 0% | 6,199 | 6,543 | +6% | 0 | 0 | — |
case-02 | fail→fail | 27,084 | 25,861 | -5% | 1 | 1 | 0% | 6,204 | 6,548 | +6% | 0 | 0 | — |
case-03 | fail→fail | 28,216 | 25,980 | -8% | 1 | 1 | 0% | 6,188 | 6,532 | +6% | 0 | 0 | — |
case-04 | pass→pass | 25,871 | 32,491 | +26% | 1 | 1 | 0% | 6,179 | 6,523 | +6% | 0 | 0 | — |
case-06 | fail→pass | 27,887 | 26,951 | -3% | 1 | 1 | 0% | 6,194 | 6,538 | +6% | 0 | 0 | — |
case-07 | fail→fail | 26,966 | 26,908 | -0% | 1 | 1 | 0% | 6,178 | 6,522 | +6% | 0 | 0 | — |
case-08 | fail→fail | 26,668 | 28,229 | +6% | 1 | 1 | 0% | 6,167 | 6,511 | +6% | 0 | 0 | — |
case-09 | fail→fail | 25,148 | 24,789 | -1% | 1 | 1 | 0% | 6,174 | 6,518 | +6% | 0 | 0 | — |
case-10 | fail→fail | 28,418 | 26,901 | -5% | 1 | 1 | 0% | 6,172 | 6,516 | +6% | 0 | 0 | — |
case-11 | fail→fail | 24,024 | 26,079 | +9% | 1 | 1 | 0% | 6,173 | 6,517 | +6% | 0 | 0 | — |
case-12 | fail→pass | 26,085 | 32,814 | +26% | 1 | 1 | 0% | 6,173 | 6,517 | +6% | 0 | 0 | — |
case-13 | pass→fail | 26,449 | 25,722 | -3% | 1 | 1 | 0% | 6,173 | 6,517 | +6% | 0 | 0 | — |
case-14 | pass→pass | 27,487 | 24,763 | -10% | 1 | 1 | 0% | 6,175 | 6,519 | +6% | 0 | 0 | — |
case-15 | pass→pass | 30,291 | 26,417 | -13% | 1 | 1 | 0% | 6,168 | 6,512 | +6% | 0 | 0 | — |
case-16 | pass→pass | 27,186 | 24,797 | -9% | 1 | 1 | 0% | 6,174 | 6,518 | +6% | 0 | 0 | — |
case-17 | fail→fail | 25,110 | 25,390 | +1% | 1 | 1 | 0% | 6,183 | 6,527 | +6% | 0 | 0 | — |
case-18 | fail→fail | 24,246 | 25,940 | +7% | 1 | 1 | 0% | 6,173 | 6,517 | +6% | 0 | 0 | — |
case-19 | fail→fail | 29,454 | 26,653 | -10% | 1 | 1 | 0% | 6,165 | 6,509 | +6% | 0 | 0 | — |
case-20 | pass→fail | 19,511 | 26,399 | +35% | 1 | 1 | 0% | 3,640 | 6,509 | +79% | 0 | 0 | — |
case-21 | pass→fail | 20,678 | 26,571 | +28% | 1 | 1 | 0% | 3,302 | 6,506 | +97% | 0 | 0 | — |
case-22 | pass→pass | 9,255 | 27,189 | +194% | 1 | 1 | 0% | 1,874 | 6,509 | +247% | 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 0 percentage points is the difference between those two pass rates over the 22 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.