Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Professional trading analysis dashboard template (single-file HTML) with light/dark theme switch, dense market panels, chart interactions, demo/live playback, and command palette behavior. Use when users ask for a Wall-Street-style analytics terminal, trading cockpit, or high-tech financial dashboard template with realistic data layout.
.claude/skills/nexu-io-trading-analysis-dashboard-template/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-21 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-04 | ✓→✗ | ▼ Worse | 156% | 0% |
| case-06 | ✓→✗ | ▼ Worse | 65% | 0% |
| case-08 | ✓→✗ | ▼ Worse | 4% | 0% |
| case-11 | ✓→✗ | ▼ Worse | 4% | 0% |
Produce a premium, data-dense, Wall-Street style trading dashboard as a self-contained HTML artifact.
texttrading-analysis-dashboard-template/ ├── SKILL.md ├── assets/ │ └── template.html ├── references/ │ └── checklist.md └── example.html
DESIGN.md, then map typography/color/layout into CSS variables.assets/template.html to index.html./)— or neutral labels) where real numbers are unknown.references/checklist.md before emitting.One sentence before artifact, then:
xml<artifact identifier="trading-analysis-dashboard" type="text/html" title="Trading Analysis Dashboard"> <!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-01 | fail→fail | 41,776 | 44,218 | +6% | 1 | 1 | 0% | 8,258 | 8,558 | +4% | 0 | 0 | — |
case-02 | fail→fail | 38,959 | 47,016 | +21% | 1 | 1 | 0% | 8,247 | 8,547 | +4% | 0 | 0 | — |
case-03 | fail→fail | 41,218 | 59,570 | +45% | 1 | 1 | 0% | 8,246 | 8,546 | +4% | 0 | 0 | — |
case-04 | pass→fail | 22,088 | 86,456 | +291% | 1 | 1 | 0% | 3,335 | 8,528 | +156% | 0 | 0 | — |
case-05 | pass→pass | 27,121 | 60,197 | +122% | 1 | 1 | 0% | 4,275 | 8,397 | +96% | 0 | 0 | — |
case-06 | pass→fail | 31,182 | 57,161 | +83% | 1 | 1 | 0% | 5,145 | 8,512 | +65% | 0 | 0 | — |
case-07 | fail→fail | 52,969 | 43,052 | -19% | 1 | 1 | 0% | 8,242 | 8,542 | +4% | 0 | 0 | — |
case-08 | pass→fail | 40,389 | 40,345 | -0% | 1 | 1 | 0% | 8,227 | 8,527 | +4% | 0 | 0 | — |
case-09 | fail→fail | 35,612 | 39,700 | +11% | 1 | 1 | 0% | 8,250 | 8,550 | +4% | 0 | 0 | — |
case-10 | fail→fail | 42,853 | 50,044 | +17% | 1 | 1 | 0% | 8,237 | 8,537 | +4% | 0 | 0 | — |
case-11 | pass→fail | 49,738 | 54,367 | +9% | 1 | 1 | 0% | 8,240 | 8,540 | +4% | 0 | 0 | — |
case-12 | pass→pass | 50,899 | 41,449 | -19% | 1 | 1 | 0% | 8,233 | 8,533 | +4% | 0 | 0 | — |
case-13 | fail→fail | 53,159 | 49,573 | -7% | 1 | 1 | 0% | 8,230 | 8,530 | +4% | 0 | 0 | — |
case-14 | fail→fail | 35,912 | 37,845 | +5% | 1 | 1 | 0% | 8,226 | 8,526 | +4% | 0 | 0 | — |
case-15 | fail→fail | 69,635 | 38,444 | -45% | 1 | 1 | 0% | 8,222 | 8,522 | +4% | 0 | 0 | — |
case-16 | fail→fail | 53,735 | 39,212 | -27% | 1 | 1 | 0% | 8,230 | 8,530 | +4% | 0 | 0 | — |
case-17 | fail→fail | 50,535 | 39,741 | -21% | 1 | 1 | 0% | 8,234 | 8,534 | +4% | 0 | 0 | — |
case-18 | fail→fail | 106,907 | 41,306 | -61% | 1 | 1 | 0% | 8,222 | 8,522 | +4% | 0 | 0 | — |
case-19 | fail→fail | 36,951 | 49,456 | +34% | 1 | 1 | 0% | 8,234 | 8,534 | +4% | 0 | 0 | — |
case-20 | fail→fail | 39,568 | 39,907 | +1% | 1 | 1 | 0% | 8,229 | 8,529 | +4% | 0 | 0 | — |
case-21 | fail→pass | 38,246 | 36,636 | -4% | 1 | 1 | 0% | 8,223 | 8,523 | +4% | 0 | 0 | — |
case-22 | fail→fail | 53,215 | 37,686 | -29% | 1 | 1 | 0% | 8,229 | 8,529 | +4% | 0 | 0 | — |
case-23 | fail→fail | 39,564 | 51,840 | +31% | 1 | 1 | 0% | 8,222 | 8,522 | +4% | 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 -13 percentage points is the difference between those two pass rates over the 23 comparable cases. 5 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.