Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate plots, charts, and graphs from data with automatic visualization type selection. Use when requesting "visualization", "plot", "chart", or "graph". Trigger with phrases like 'generate', 'create', or 'scaffold'.
.claude/skills/jeremylongshore-creating-data-visualizations/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 51% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 99% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 153% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 187% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 79% | 0% |
Generate plots, charts, and graphs from data with automatic visualization type selection based on data characteristics.
This skill empowers Claude to transform raw data into compelling visual representations. It leverages intelligent automation to select optimal visualization types and generate informative plots, charts, and graphs. This skill helps users understand complex data more easily.
This skill activates when you need to:
User request: "Create a bar chart showing sales by region."
The skill will:
User request: "Plot the stock price of AAPL over the last year."
The skill will:
This skill can be integrated with other data processing and analysis tools within the Claude Code environment. It can receive data from other skills and provide visualizations for further analysis or reporting.
The skill produces structured output relevant to the task.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 6,197 | 6,929 | +12% | 1 | 1 | 0% | 1,127 | 1,753 | +56% | 0 | 0 | — |
case-02 | fail→pass | 7,728 | 9,103 | +18% | 1 | 1 | 0% | 1,358 | 2,055 | +51% | 0 | 0 | — |
case-03 | fail→fail | 4,386 | 4,841 | +10% | 1 | 1 | 0% | 806 | 1,361 | +69% | 0 | 0 | — |
case-04 | fail→fail | 7,080 | 6,852 | -3% | 1 | 1 | 0% | 1,208 | 1,770 | +47% | 0 | 0 | — |
case-05 | fail→fail | 5,397 | 5,283 | -2% | 1 | 1 | 0% | 945 | 1,469 | +55% | 0 | 0 | — |
case-06 | fail→pass | 7,390 | 9,690 | +31% | 1 | 1 | 0% | 1,151 | 2,285 | +99% | 0 | 0 | — |
case-07 | fail→fail | 6,612 | 5,779 | -13% | 1 | 1 | 0% | 1,132 | 1,555 | +37% | 0 | 0 | — |
case-08 | fail→fail | 3,050 | 3,439 | +13% | 1 | 1 | 0% | 475 | 1,164 | +145% | 0 | 0 | — |
case-09 | fail→fail | 4,490 | 3,848 | -14% | 1 | 1 | 0% | 711 | 1,222 | +72% | 0 | 0 | — |
case-10 | fail→fail | 5,434 | 8,781 | +62% | 1 | 1 | 0% | 830 | 2,028 | +144% | 0 | 0 | — |
case-11 | fail→fail | 3,523 | 5,443 | +54% | 1 | 1 | 0% | 517 | 1,521 | +194% | 0 | 0 | — |
case-12 | fail→pass | 5,235 | 9,364 | +79% | 1 | 1 | 0% | 952 | 2,406 | +153% | 0 | 0 | — |
case-13 | fail→fail | 4,035 | 8,277 | +105% | 1 | 1 | 0% | 666 | 2,179 | +227% | 0 | 0 | — |
case-14 | fail→fail | 3,986 | 6,884 | +73% | 1 | 1 | 0% | 640 | 1,590 | +148% | 0 | 0 | — |
case-15 | fail→pass | 3,537 | 5,802 | +64% | 1 | 1 | 0% | 597 | 1,711 | +187% | 0 | 0 | — |
case-16 | fail→pass | 6,141 | 6,253 | +2% | 1 | 1 | 0% | 980 | 1,753 | +79% | 0 | 0 | — |
case-17 | pass→pass | 7,991 | 6,491 | -19% | 1 | 1 | 0% | 1,438 | 1,669 | +16% | 0 | 0 | — |
case-18 | fail→fail | 8,586 | 6,933 | -19% | 1 | 1 | 0% | 1,487 | 1,698 | +14% | 0 | 0 | — |
case-19 | fail→fail | 7,774 | 9,005 | +16% | 1 | 1 | 0% | 1,419 | 2,013 | +42% | 0 | 0 | — |
case-20 | pass→pass | 9,431 | 15,215 | +61% | 1 | 1 | 0% | 1,730 | 3,186 | +84% | 0 | 0 | — |
case-21 | pass→pass | 10,716 | 9,769 | -9% | 1 | 1 | 0% | 2,688 | 3,054 | +14% | 0 | 0 | — |
case-22 | pass→pass | 21,055 | 17,872 | -15% | 1 | 1 | 0% | 812 | 1,247 | +54% | 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 +23 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.