Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Review chart choice, labeling, accessibility, and storytelling quality for existing visualizations. Use as an explicit/manual helper for critique and cleanup, not as the main owner for scientific figure production or general chart generation.
.claude/skills/foryourhealth111-pixel-visualization-best-practices/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 100% | 1 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | -47% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 49% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | -3% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | -15% | 0% |
Treat this skill as an explicit/manual review helper.
Use this skill when:
creating-data-visualizationsscientific-visualizationscientific-schematicscreating-data-visualizations for general chart productionscientific-visualization when the figure must meet publication standards| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | pass→pass | 26,371 | 13,548 | -49% | 1 | 1 | 0% | 5,443 | 2,910 | -47% | 0 | 0 | — |
case-01 | pass→pass | 7,964 | 10,653 | +34% | 1 | 1 | 0% | 1,598 | 2,377 | +49% | 0 | 0 | — |
case-03 | pass→pass | 21,552 | 18,729 | -13% | 1 | 1 | 0% | 4,296 | 4,169 | -3% | 0 | 0 | — |
case-04 | pass→pass | 11,157 | 7,790 | -30% | 1 | 1 | 0% | 1,840 | 1,566 | -15% | 0 | 0 | — |
case-05 | fail→pass | 14,391 | 12,002 | -17% | 1 | 1 | 0% | 2,180 | 2,001 | -8% | 0 | 0 | — |
case-06 | pass→pass | 11,501 | 11,743 | +2% | 1 | 1 | 0% | 2,034 | 2,273 | +12% | 0 | 0 | — |
case-07 | pass→pass | 8,543 | 13,893 | +63% | 1 | 1 | 0% | 1,541 | 2,103 | +36% | 0 | 0 | — |
case-21 | pass→pass | 17,284 | 8,251 | -52% | 1 | 1 | 0% | 1,527 | 1,505 | -1% | 0 | 0 | — |
case-08 | pass→pass | 9,046 | 9,077 | +0% | 1 | 1 | 0% | 1,638 | 1,525 | -7% | 0 | 0 | — |
case-09 | pass→pass | 10,196 | 8,915 | -13% | 1 | 1 | 0% | 1,653 | 1,492 | -10% | 0 | 0 | — |
case-10 | pass→pass | 11,820 | 12,623 | +7% | 1 | 1 | 0% | 2,035 | 2,151 | +6% | 0 | 0 | — |
case-11 | pass→pass | 9,233 | 5,448 | -41% | 1 | 1 | 0% | 1,500 | 1,081 | -28% | 0 | 0 | — |
case-12 | pass→pass | 13,567 | 10,512 | -23% | 1 | 1 | 0% | 2,099 | 1,977 | -6% | 0 | 0 | — |
case-13 | pass→pass | 8,505 | 9,511 | +12% | 1 | 1 | 0% | 1,444 | 1,763 | +22% | 0 | 0 | — |
case-14 | pass→pass | 13,238 | 11,103 | -16% | 1 | 1 | 0% | 2,072 | 2,135 | +3% | 0 | 0 | — |
case-15 | pass→pass | 7,929 | 6,133 | -23% | 1 | 1 | 0% | 1,490 | 1,346 | -10% | 0 | 0 | — |
case-16 | pass→pass | 10,269 | 13,203 | +29% | 1 | 1 | 0% | 1,791 | 2,232 | +25% | 0 | 0 | — |
case-17 | pass→pass | 10,060 | 11,448 | +14% | 1 | 1 | 0% | 1,699 | 2,302 | +35% | 0 | 0 | — |
case-18 | pass→pass | 10,336 | 12,813 | +24% | 1 | 1 | 0% | 1,794 | 2,319 | +29% | 0 | 0 | — |
case-19 | pass→pass | 10,091 | 8,232 | -18% | 1 | 1 | 0% | 1,798 | 1,640 | -9% | 0 | 0 | — |
case-20 | pass→pass | 8,298 | 8,258 | -0% | 1 | 1 | 0% | 1,271 | 1,340 | +5% | 0 | 0 | — |
case-22 | pass→pass | 10,336 | 10,185 | -1% | 1 | 1 | 0% | 1,788 | 1,906 | +7% | 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 +5 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.