Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jaechang-hits/general-figure-guide
Universal QA checklist for generated scientific plots: overlapping labels, clipped text, missing axes/legends, overcrowded data, and cross-journal resolution/format guidance.
Passed 16 of 24 test cases with the skill, and 15 of 24 without it.
1 fixed15 passed either way8 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
I'm reviewing figures generated by our team and noticing several formatting glitches across our charts. Can you create a reference guide table mapping common figure visual defects (like text cutoffs, illegible labels, or dense point overlapping) to how to detect them and the general strategies to fix them?
| Checked | Without skill | With skill |
|---|---|---|
| Includes an explicit defect entry for empty plot areas. | Missed | Passed |
| Recommends tight_layout() or constrained_layout as the fix for clipped text. | Passed | Passed |
| Recommends checking data filtering and column names when diagnosing empty plot defects. | Missed | Passed |
The instructions your model reads when the skill loads.
This guide provides a universal quality checklist for evaluating scientific figures, whether generated programmatically (matplotlib, seaborn, R/ggplot2) or assembled manually. It focuses on visual readability issues that are common across all journals and easily missed during automated plot generation.
A figure must communicate its data without requiring the reader to guess. The most common readability failures are overlapping labels, clipped text that runs outside the figure boundary, missing or unlabeled axes, absent legends, empty plot areas from incorrect data filtering, and overcrowded data points that merge into an unreadable mass.
Scientific figures generally require 300+ DPI for raster output (TIFF, PNG, JPEG) and vector formats (PDF, EPS, SVG) for line art and graphs. Vector formats are preferred for plots because they scale without quality loss. Raster formats are appropriate for photographs and micrographs.
Approximately 8% of males have some form of color vision deficiency. Figures that rely solely on red-green color differences exclude these readers. Use colorblind-friendly palettes (blue-orange, or viridis/cividis colormaps), add pattern or shape differentiation, and test figures with a colorblindness simulator before submission.
All major journals require that brightness, contrast, and color adjustments be applied uniformly to the entire image. Selective enhancement of specific regions (e.g., adjusting one gel lane) is considered data manipulation and grounds for rejection across all journals. Always document processing steps in the Methods section and retain original unprocessed files.
Is the figure a generated plot or a photograph?
├── Generated plot (matplotlib, ggplot2, seaborn)
│ ├── Export as vector (PDF, SVG, EPS) → preferred
│ └── Export as raster → 300+ DPI minimum, PNG or TIFF
├── Photograph or micrograph
│ └── Export as raster → 300+ DPI, TIFF preferred
└── Multi-panel composite
├── Assemble panels first, then export as single file
└── Use consistent font sizes and label styles across panels
| Issue | How to Detect | Fix |
|---|
test cases passed, vs 15 / 24 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.