Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Exports publication-ready figures in various formats with proper resolution, sizing, and typography. Use when preparing figures for journal submission, creating vector graphics for presentations, or ensuring consistent figure styling across analyses.
.claude/skills/bio-reporting-figure-export/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | -23% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -40% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 32% | 0% |
| case-21 | ✓→✗ | ▼ Worse | 32% | 0% |
| case-03 | ✓→✓ | = Same ✓ | 43% | 0% |
<!--
#
#
-->
pythonimport matplotlib.pyplot as plt # Set publication defaults plt.rcParams.update({ 'font.size': 8, 'font.family': 'Arial', 'axes.linewidth': 0.5, 'lines.linewidth': 1, 'figure.dpi': 300 }) fig, ax = plt.subplots(figsize=(3.5, 3)) # Single column width # ... create plot ... # Save in multiple formats fig.savefig('figure1.pdf', bbox_inches='tight', dpi=300) fig.savefig('figure1.png', bbox_inches='tight', dpi=300) fig.savefig('figure1.svg', bbox_inches='tight')
rlibrary(ggplot2) p <- ggplot(data, aes(x, y)) + geom_point() + theme_classic(base_size = 8) + theme(text = element_text(family = 'Arial')) # PDF for vector graphics ggsave('figure1.pdf', p, width = 3.5, height = 3, units = 'in') # High-res PNG ggsave('figure1.png', p, width = 3.5, height = 3, units = 'in', dpi = 300) # TIFF (some journals require) ggsave('figure1.tiff', p, width = 3.5, height = 3, units = 'in', dpi = 300, compression = 'lzw')
| Journal Type | Format | Resolution | Width | |--------------|--------|------------|-------| | Most journals | PDF/EPS | Vector | 3.5" (1-col), 7" (2-col) | | Online-only | PNG | 300 DPI | Variable | | Print | TIFF | 300-600 DPI | Column width |
pythonimport matplotlib.pyplot as plt from matplotlib.gridspec import GridSpec fig = plt.figure(figsize=(7, 5)) # Two-column width gs = GridSpec(2, 3, figure=fig) ax1 = fig.add_subplot(gs[0, 0]) ax2 = fig.add_subplot(gs[0, 1:]) ax3 = fig.add_subplot(gs[1, :]) # Add panel labels for ax, label in zip([ax1, ax2, ax3], ['A', 'B', 'C']): ax.text(-0.1, 1.1, label, transform=ax.transAxes, fontsize=10, fontweight='bold') fig.savefig('figure_multipanel.pdf', bbox_inches='tight')
<!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE -->
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | pass→pass | 13,827 | 12,920 | -7% | 1 | 1 | 0% | 2,533 | 3,630 | +43% | 0 | 0 | — |
case-01 | fail→fail | 19,056 | 15,774 | -17% | 1 | 1 | 0% | 3,933 | 4,066 | +3% | 0 | 0 | — |
case-02 | fail→fail | 14,410 | 16,506 | +15% | 1 | 1 | 0% | 2,901 | 2,712 | -7% | 0 | 0 | — |
case-04 | pass→pass | 6,457 | 2,792 | -57% | 1 | 1 | 0% | 1,143 | 1,341 | +17% | 0 | 0 | — |
case-05 | fail→fail | 27,842 | 14,426 | -48% | 1 | 1 | 0% | 6,175 | 3,991 | -35% | 0 | 0 | — |
case-06 | pass→pass | 14,185 | 9,665 | -32% | 1 | 1 | 0% | 2,717 | 2,765 | +2% | 0 | 0 | — |
case-07 | pass→pass | 9,362 | 4,753 | -49% | 1 | 1 | 0% | 1,584 | 1,668 | +5% | 0 | 0 | — |
case-08 | pass→pass | 10,364 | 5,477 | -47% | 1 | 1 | 0% | 2,095 | 1,239 | -41% | 0 | 0 | — |
case-09 | pass→pass | 13,635 | 14,637 | +7% | 1 | 1 | 0% | 2,189 | 3,671 | +68% | 0 | 0 | — |
case-10 | pass→pass | 7,004 | 2,738 | -61% | 1 | 1 | 0% | 1,194 | 1,366 | +14% | 0 | 0 | — |
case-11 | fail→pass | 9,253 | 2,372 | -74% | 1 | 1 | 0% | 1,580 | 1,221 | -23% | 0 | 0 | — |
case-12 | fail→pass | 11,875 | 3,037 | -74% | 1 | 1 | 0% | 2,336 | 1,400 | -40% | 0 | 0 | — |
case-13 | pass→pass | 13,414 | 4,029 | -70% | 1 | 1 | 0% | 2,063 | 1,538 | -25% | 0 | 0 | — |
case-14 | pass→pass | 5,368 | 2,790 | -48% | 1 | 1 | 0% | 1,130 | 1,359 | +20% | 0 | 0 | — |
case-15 | pass→pass | 4,127 | 2,093 | -49% | 1 | 1 | 0% | 688 | 1,235 | +80% | 0 | 0 | — |
case-16 | pass→pass | 5,203 | 4,898 | -6% | 1 | 1 | 0% | 862 | 1,699 | +97% | 0 | 0 | — |
case-17 | fail→pass | 7,292 | 6,370 | -13% | 1 | 1 | 0% | 1,347 | 1,779 | +32% | 0 | 0 | — |
case-18 | pass→pass | 8,510 | 1,570 | -82% | 1 | 1 | 0% | 1,452 | 1,137 | -22% | 0 | 0 | — |
case-19 | pass→pass | 6,639 | 7,753 | +17% | 1 | 1 | 0% | 1,284 | 2,450 | +91% | 0 | 0 | — |
case-20 | pass→pass | 10,083 | 11,108 | +10% | 1 | 1 | 0% | 2,020 | 3,204 | +59% | 0 | 0 | — |
case-21 | pass→fail | 14,891 | 16,006 | +7% | 1 | 1 | 0% | 3,206 | 4,220 | +32% | 0 | 0 | — |
case-22 | pass→pass | 5,137 | 3,590 | -30% | 1 | 1 | 0% | 945 | 1,562 | +65% | 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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 7/26/2026 | +36% |
Other measured skills in the registry, with their headline benchmark lift.