Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Team-management dashboard skill in the FlowAI aesthetic — three tabs (Team Members, Team Details, Activity Log), KPI stat row, member table, role distribution bar chart, online presence and activity sparklines, and a top-contributors panel, all in a single self-contained HTML file with light/dark theming, hoverable chart tooltips, click-to-zoom panels, and CSV export. Use when the brief asks for a team / workspace admin dashboard, an interactive admin dashboard with charts, or names FlowAI.
.claude/skills/nexu-io-flowai-live-dashboard-template/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-13 | ✗→✓ | ▲ Improved | 26% | 0% |
| case-10 | ✓→✗ | ▼ Worse | 8% | 0% |
| case-14 | ✓→✗ | ▼ Worse | 37% | 0% |
| case-22 | ✓→✗ | ▼ Worse | 87% | 0% |
| case-20 | ✓→✗ | ▼ Worse | 8% | 0% |
Produce a single-screen, multi-tab team management dashboard inspired by the FlowAI aesthetic. The output is a self-contained HTML file (no external runtime dependencies) with built-in interactions: tab switching, an animated bar chart, hover tooltips on charts, click-to-zoom panels, dark mode toggle, and CSV export of the visible team table.
flowai-live-dashboard-template/
├── SKILL.md
├── assets/
│ └── template.html # reference seed used as the starting structure
├── references/
│ └── checklist.md # P0/P1/P2 quality gates
└── example.html # complete hand-built sample (gallery preview)spacing, and component styling tokens to the CSS variables used by assets/template.html. Do not invent new tokens.
assets/template.html; never generate the shell from blank.Team Members, Team Details, Activity Log. Tabs mustactually switch and only one view is visible at a time.
departments, dates, percentages). No Member A / Metric B placeholders.
#members | #details | #activity)including the Workflow column
references/checklist.md before final output.Emit one short orientation sentence, then the artifact:
xml<artifact identifier="flowai-team-dashboard" type="text/html" title="FlowAI Team Dashboard"> <!doctype html> <html>...</html> </artifact>
The artifact must render correctly when opened directly from disk with no build step and no network access.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | fail→fail | 28,223 | 26,584 | -6% | 1 | 1 | 0% | 6,197 | 6,717 | +8% | 0 | 0 | — |
case-07 | fail→fail | 26,516 | 28,382 | +7% | 1 | 1 | 0% | 6,186 | 6,706 | +8% | 0 | 0 | — |
case-08 | fail→fail | 29,259 | 24,956 | -15% | 1 | 1 | 0% | 6,191 | 6,711 | +8% | 0 | 0 | — |
case-04 | fail→fail | 26,457 | 42,605 | +61% | 1 | 1 | 0% | 6,196 | 6,716 | +8% | 0 | 0 | — |
case-05 | fail→fail | 35,112 | 33,027 | -6% | 1 | 1 | 0% | 6,199 | 6,719 | +8% | 0 | 0 | — |
case-01 | fail→fail | 28,891 | 26,350 | -9% | 1 | 1 | 0% | 6,211 | 6,731 | +8% | 0 | 0 | — |
case-02 | fail→fail | 27,487 | 28,928 | +5% | 1 | 1 | 0% | 6,206 | 6,726 | +8% | 0 | 0 | — |
case-03 | fail→fail | 56,606 | 35,346 | -38% | 1 | 1 | 0% | 6,202 | 6,722 | +8% | 0 | 0 | — |
case-09 | fail→fail | 34,096 | 26,997 | -21% | 1 | 1 | 0% | 6,180 | 6,700 | +8% | 0 | 0 | — |
case-10 | pass→fail | 26,076 | 38,124 | +46% | 1 | 1 | 0% | 6,192 | 6,712 | +8% | 0 | 0 | — |
case-11 | fail→fail | 28,039 | 24,471 | -13% | 1 | 1 | 0% | 6,187 | 6,707 | +8% | 0 | 0 | — |
case-12 | fail→fail | 28,126 | 25,767 | -8% | 1 | 1 | 0% | 6,188 | 6,708 | +8% | 0 | 0 | — |
case-13 | fail→pass | 22,648 | 26,184 | +16% | 1 | 1 | 0% | 5,304 | 6,694 | +26% | 0 | 0 | — |
case-14 | pass→fail | 20,673 | 27,024 | +31% | 1 | 1 | 0% | 4,904 | 6,712 | +37% | 0 | 0 | — |
case-15 | pass→pass | 20,578 | 26,428 | +28% | 1 | 1 | 0% | 4,587 | 6,706 | +46% | 0 | 0 | — |
case-16 | fail→fail | 26,477 | 31,161 | +18% | 1 | 1 | 0% | 6,179 | 6,699 | +8% | 0 | 0 | — |
case-17 | fail→fail | 22,512 | 22,404 | -0% | 1 | 1 | 0% | 4,364 | 6,689 | +53% | 0 | 0 | — |
case-22 | pass→fail | 14,480 | 26,582 | +84% | 1 | 1 | 0% | 3,571 | 6,684 | +87% | 0 | 0 | — |
case-18 | pass→pass | 31,244 | 27,530 | -12% | 1 | 1 | 0% | 5,646 | 6,702 | +19% | 0 | 0 | — |
case-19 | fail→fail | 27,756 | 26,750 | -4% | 1 | 1 | 0% | 6,175 | 6,694 | +8% | 0 | 0 | — |
case-20 | pass→fail | 27,075 | 24,802 | -8% | 1 | 1 | 0% | 6,173 | 6,693 | +8% | 0 | 0 | — |
case-21 | pass→fail | 20,243 | 26,909 | +33% | 1 | 1 | 0% | 4,693 | 6,697 | +43% | 0 | 0 | — |
case-23 | pass→pass | 11,793 | 17,681 | +50% | 1 | 1 | 0% | 2,320 | 3,750 | +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. 23 cases were attempted. The headline lift of -17 percentage points is the difference between those two pass rates over the 23 comparable cases. 6 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.