What problem does it solve? Creating figures that meet academic journal standards requires consistent color palettes, high DPI settings, correct fonts (including Chinese characters), and proper file management—details that are easy to get wrong when writing plotting code from scratch. ## Core Features & Use Cases - Journal-Grade Styling: Applies Nature/Science, Cell, and colorblind-safe color palettes with 450 DPI output and clean axis styling. - Dual Format Export: Every figure is saved as both PNG (for web/slides) and SVG (vector, for journal submission). - Data Provenance Tracking: Enforces a data manifest (figures/data-manifest.md) that records whether data is real or mock, preventing synthetic data from being presented as experimental results. - Use Case: While writing a research paper, ask for a line chart comparing two models; the Skill generates a styled matplotlib script, saves fig1_model_comparison.png and .svg under figures/chapter2/, and logs the data source in the manifest. ## Quick Start Ask the assistant to create a publication-quality line chart of your experiment results using the figures-python skill with Nature-style colors and 450 DPI output.
