Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create advanced Excel pivot tables with calculated fields and slicers. Use when building data summaries or creating interactive dashboards. Trigger with phrases like 'excel pivot', 'create pivot table', 'data summary'.
.claude/skills/jeremylongshore-excel-pivot-wizard/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -51% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 3% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -42% | 0% |
| case-15 | ✓→✗ | ▼ Worse | 25% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 5% | 0% |
Creates advanced pivot tables with calculated fields, slicers, and dynamic dashboards for data analysis and reporting.
| Error | Cause | Solution | |-------|-------|----------| | Field not found | Changed source data | Refresh data connection | | Calculated field error | Invalid formula | Check field names match exactly | | Slicer not updating | Disconnected report | Reconnect slicer to pivot |
Example: Sales Dashboard Request: "Create a pivot summarizing sales by region and product" Result: Pivot with region rows, product columns, revenue values, and date slicer
Example: Financial Analysis Request: "Build a pivot showing monthly trends by cost center" Result: Time-series pivot with calculated YoY growth fields
${CLAUDE_SKILL_DIR}/references/pivot-formulas.md for calculated field syntax| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 39,042 | 18,672 | -52% | 1 | 1 | 0% | 6,668 | 3,241 | -51% | 0 | 0 | — |
case-02 | fail→pass | 12,095 | 10,605 | -12% | 1 | 1 | 0% | 2,185 | 2,252 | +3% | 0 | 0 | — |
case-03 | fail→fail | 11,935 | 9,185 | -23% | 1 | 1 | 0% | 2,031 | 1,974 | -3% | 0 | 0 | — |
case-04 | pass→pass | 9,901 | 8,391 | -15% | 1 | 1 | 0% | 1,699 | 1,779 | +5% | 0 | 0 | — |
case-05 | pass→pass | 9,458 | 9,215 | -3% | 1 | 1 | 0% | 1,635 | 1,534 | -6% | 0 | 0 | — |
case-06 | pass→pass | 10,833 | 6,851 | -37% | 1 | 1 | 0% | 1,748 | 1,477 | -16% | 0 | 0 | — |
case-07 | fail→pass | 15,981 | 5,903 | -63% | 1 | 1 | 0% | 2,382 | 1,393 | -42% | 0 | 0 | — |
case-08 | pass→pass | 9,230 | 8,037 | -13% | 1 | 1 | 0% | 1,834 | 1,872 | +2% | 0 | 0 | — |
case-09 | pass→pass | 9,194 | 7,023 | -24% | 1 | 1 | 0% | 1,755 | 1,654 | -6% | 0 | 0 | — |
case-10 | pass→pass | 5,330 | 6,973 | +31% | 1 | 1 | 0% | 1,058 | 1,308 | +24% | 0 | 0 | — |
case-11 | pass→pass | 10,221 | 10,109 | -1% | 1 | 1 | 0% | 1,939 | 2,173 | +12% | 0 | 0 | — |
case-12 | pass→pass | 5,674 | 4,733 | -17% | 1 | 1 | 0% | 929 | 1,128 | +21% | 0 | 0 | — |
case-13 | pass→pass | 11,457 | 8,069 | -30% | 1 | 1 | 0% | 1,832 | 1,668 | -9% | 0 | 0 | — |
case-14 | pass→pass | 6,864 | 6,452 | -6% | 1 | 1 | 0% | 1,130 | 1,285 | +14% | 0 | 0 | — |
case-15 | pass→fail | 11,562 | 9,097 | -21% | 1 | 1 | 0% | 1,569 | 1,959 | +25% | 0 | 0 | — |
case-16 | pass→pass | 8,326 | 6,759 | -19% | 1 | 1 | 0% | 1,278 | 1,658 | +30% | 0 | 0 | — |
case-17 | pass→pass | 9,091 | 11,233 | +24% | 1 | 1 | 0% | 1,651 | 2,105 | +27% | 0 | 0 | — |
case-18 | fail→fail | 9,581 | 7,484 | -22% | 1 | 1 | 0% | 1,477 | 1,608 | +9% | 0 | 0 | — |
case-19 | pass→pass | 11,868 | 7,222 | -39% | 1 | 1 | 0% | 1,659 | 1,504 | -9% | 0 | 0 | — |
case-20 | pass→pass | 8,577 | 4,980 | -42% | 1 | 1 | 0% | 1,264 | 1,175 | -7% | 0 | 0 | — |
case-21 | pass→pass | 5,414 | 7,061 | +30% | 1 | 1 | 0% | 1,025 | 1,549 | +51% | 0 | 0 | — |
case-22 | pass→pass | 8,322 | 7,547 | -9% | 1 | 1 | 0% | 1,186 | 1,481 | +25% | 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 +9 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is 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.