paper-figureslisted

Produce publication-quality statistical figures and tables for scientific papers, end-to-end from the paper's own raw data using Python. Use this skill whenever the user wants to make, redo, or improve charts, plots, graphs, or tables for a manuscript, thesis, or grant — including requests like "draw a figure for this dataset", "make a bar/box/violin/forest/Kaplan-Meier plot", "I need a results table", "format my figures for Nature/Science/Cell/IEEE", "what chart should I use for this data", or "turn my CSV/Excel results into a figure for my paper". Trigger even when the user only shares a manuscript and data and asks where figures are needed. The skill reads the paper, finds where visuals are needed, picks the right statistics and chart type for the data, applies journal formatting, renders with Python, self-checks the rendered image, exports numbered assets, and writes a bilingual (中文/English) figure report with captions, annotations, and in-text citation locations.
DRZ-hang/paper-figures · ★ 0 · Data & Documents · score 72

Install: claude install-skill DRZ-hang/paper-figures

# Paper Figures — Scientific Figure & Table Studio You turn a paper's **own raw data** into publication-ready figures and tables. Every result must be reproducible from a Python script you write and run — never hand-drawn, never faked, never eyeballed. If a number can't be traced to the raw data, it doesn't go on the figure. This skill is a **workflow**, not a single command. Walk through the seven stages below in order. Each figure or table is one pass through stages 2–6; do stage 1 once for the whole paper and stage 7 once at the end. ## Communication & language Talk to the user in the language they write to you in (the user base is bilingual 中文/English). The **figure report you deliver is always bilingual** — caption and annotations in both Chinese and English — because papers and reviewers may be in either language. See `assets/report_template.md`. ## Guiding principles (read once, keep in mind throughout) - **Data first, plot second.** The argument the figure makes must already be true in the data. The plot reveals it; it never manufactures it. - **Honesty over beauty.** No truncated axes that exaggerate effects, no cherry-picked bins, no hidden n, no "representative" without saying how it was chosen. If you make a scale choice that affects interpretation (log axis, broken axis, zoom), say so in the caption. - **Reproducible.** Save every script. Re-running it on the same data must reproduce the exact figure. Set random seeds. Record library versions. - *