Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/visualize
Create publication-quality figures that meet journal submission standards. APA 7th defaults with journal-specific overrides. Supports interaction plots, mediation path diagrams, forest plots, marginal effects, Johnson-Neyman plots, correlation heatmaps, and coefficient plots. All figures are colorblind-safe, high DPI, and exported in multiple formats (PDF, PNG, SVG, TIFF).
Passed 13 of 21 test cases with the skill, and 8 of 21 without it.
and 6 more in the full report
6 fixed8 passed either way8 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
The user ran `/visualize` with no arguments specified. What action should be taken regarding figure generation?
| Checked | Without skill | With skill |
|---|---|---|
| The response inspects analysis outputs to determine required figures | Missed | Passed |
| The response presents a figure plan to the researcher for confirmation | Missed | Passed |
The instructions your model reads when the skill loads.
You produce figures that a journal will accept on first submission. Not "good enough" — publication-ready. Correct dimensions, correct resolution, correct formatting, colorblind-safe, and clean enough that a reader understands the figure without reading the caption.
Every figure follows APA 7th defaults unless a journal-specific override is specified. Every figure exports in multiple formats. Every figure is reproducible from the code.
Follow _shared/project-discovery.md to find the project.
Read:
output/results/models.rds or .pkl, or fitted model objectsoutput/results/eda-summary.rds for descriptive dataRead references/principles.md and references/criteria.md. Read _shared/apa-formatting.md for formatting standards.
Based on the analyses run, determine which figures are needed:
| Analysis Type | Standard Figures |
|---|---|
| Regression | Coefficient plot, residual diagnostics |
| Moderation | Interaction plot with error bars, J-N plot |
| Mediation | Path diagram with coefficients |
| Moderated mediation | Path diagram + conditional indirect effect plot |
| Mixed models | Random effects caterpillar plot, predicted margins |
| SEM | Full path diagram with fit indices |
| Meta-analysis | Forest plot, funnel plot |
| General | Correlation heatmap, distribution panels |
Present the figure plan to the researcher for confirmation.
test cases passed, vs 8 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.