Reproduce any academic paper figure from an uploaded image using accumulated style experience. Use when: user uploads/attaches a paper figure and asks to reproduce or recreate it; user says "复现这个图", "reproduce this plot", "match this figure", "照着这个图画"; or user provides a paper figure PNG/screenshot and wants Python matplotlib code that generates it. Includes analysis workflow for font detection, color extraction, proportion matching, and mapping to 8 pre-built styles or creating a new style from scratch.
Generate publication-quality matplotlib figures by selecting a pre-built paper style and substituting user data. Use when: user provides data (numbers, arrays, or CSV) and wants a chart in a specific academic style; user asks to "plot this data", "make a bar chart", "draw a radar chart", "用这个风格画图", "把我的数据画出来"; or user selects a style name from the style catalog (bar_paired_delta, bar_grouped_hatch, line_confidence_band, line_training_curve, line_loss_with_inset, scatter_tsne_cluster, scatter_broken_axis, radar_dual_series).