What problem does it solve? Researchers often have data but don't know which chart best supports their argument, and generic plotting produces figures that fail journal requirements—wrong sizes, missing CJK glyphs, colorblind-unsafe palettes, or misleading chart types like mean-only bars on tiny samples. ## Core Features & Use Cases - Advisor-first workflow: Profiles your data (column types, sample sizes, distributions, outliers, correlations) and recommends chart types based on your argument, actively intercepting classic mistakes like pie charts, dual Y-axes, rainbow colormaps, and mean bars with n<10. - Journal-compliant rendering: Applies Nature / Science / IEEE / Elsevier / PNAS / Chinese journal presets for column width, font size, DPI, and vector formats, with automatic CJK font configuration and colorblind-safe Okabe-Ito palettes. - Post-render self-check loop: Renders PNG previews, programmatically audits for missing glyphs, clipped text, and overlapping ticks, then re-reads the image to verify legend placement and panel alignment before exporting PDF/SVG/PNG with grayscale previews. - Use Case: You drop in a results.csv and ask for a paper figure. The skill profiles the data, asks what claim the figure should support, recommends box plot + stripplot over your requested mean bar chart (n=5 per group), renders it at Nature single-column size, self-checks the output, and exports vector files. ## Quick Start Ask the AI to analyze your CSV data file and create a publication-ready figure for your target journal, describing what conclusion the figure should support.
