From nature-skills
Creates submission-grade scientific figures for high-impact journals using Python (matplotlib/seaborn) or R (ggplot2/patchwork/ComplexHeatmap). Guides figure planning, backend selection, export, and QA.
How this skill is triggered — by the user, by Claude, or both
Slash command
/nature-skills:nature-figureThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill is split into two layers:
README.mdassets/chart-atlas/atlas-01-bar-charts.pngassets/chart-atlas/atlas-02-line-trends.pngassets/chart-atlas/atlas-03-heatmaps.pngassets/chart-atlas/atlas-04-scatter-bubble.pngassets/chart-atlas/atlas-05-radar-polar.pngassets/chart-atlas/atlas-06-distributions.pngassets/chart-atlas/atlas-07-forest-interval.pngassets/chart-atlas/atlas-08-area-stacked.pngassets/chart-atlas/atlas-09-image-plates.pngassets/chart-atlas/atlas-10-network-matrix.pngassets/figures4papers/assets/Dispersion_motivation.pngassets/figures4papers/assets/Dispersion_observation.pngassets/figures4papers/assets/Dispersion_observation_distillation.pngassets/figures4papers/assets/ImmunoStruct_contrastive.pngassets/figures4papers/assets/ImmunoStruct_results_IEDB.pngassets/figures4papers/assets/ImmunoStruct_schematic.pngassets/figures4papers/assets/RNAGenScape_schematic.pngassets/figures4papers/figure_CellSpliceNet/figures/ablation.pngassets/figures4papers/figure_CellSpliceNet/figures/comparison.pngThis skill is split into two layers:
static/ that holds versioned, reusable content fragments (the figure contract and default stance, plus a per-backend quick-start for Python and R).manifest.yaml) that detects the plotting backend and loads only the fragment needed for the current job. The large design, API, pattern, and QA material lives in on-demand references.Do not try to apply the figure logic from memory or from this router. Always load fragments from disk as described below.
Follow these five steps every time the skill is invoked.
Read manifest.yaml. It declares the backend axis, the allowed values, and the file paths each value maps to.
Also read every file listed under always_load (static/core/contract.md and static/core/stance.md). These hold the figure contract, the backend gate, the missing-runtime rule, the privacy rule, and the default operating stance that apply to every figure job.
Backend selection blocks everything else. Decide the backend value only from an explicit user choice or a clearly language-specific input file/workflow:
python — matplotlib / seaborn.r — ggplot2 / patchwork / ComplexHeatmap.If the user has not explicitly chosen, ask exactly one concise question — Python or R? — and stop. Do not default, guess, generate mock data, or write scripts before the answer. Only recommend a backend when the user explicitly asks you to choose; then use references/backend-selection.md, state the reason, and proceed. Once selected, the backend is exclusive for all drawing, previewing, exporting, and visual QA (see core/contract.md).
After the backend is resolved, Read the mapped fragment (static/fragments/backend/python.md or static/fragments/backend/r.md). It carries the backend-only execution rule and the publication quick-start (rcParams/theme and export helper). Do not load the other backend's fragment.
Apply the loaded material in this order:
core/contract.md) — write the core conclusion, map the evidence chain, classify the archetype, set the journal/export contract, before any code.core/stance.md) — archetype-first composition, hero panel, restrained palette, statistics/integrity as part of the figure.The chart serves the scientific logic; aesthetic polish is subordinate to making the core conclusion clear, defensible, and reviewable.
The files under references/ are deep references, not defaults. Open them on demand per the references.on_demand table in the manifest — for example references/figure-contract.md to build the contract, references/api.md for the Python palette and helpers, references/r-workflow.md for R, references/design-theory.md for color/typography/export rationale, references/common-patterns.md and references/chart-types.md for layout/chart recipes, references/nature-2026-observations.md for real Nature page archetypes, references/qa-contract.md before final delivery, and references/tutorials.md / references/demos.md for worked examples.
nature-writing, nature-polishing, nature-reader, and nature-paper2ppt.npx claudepluginhub yniantongtian-oss/nature-skills --plugin nature-skillsCreates submission-grade scientific figures for high-impact journals using Python (matplotlib/seaborn) or R (ggplot2/patchwork/ComplexHeatmap). Guides figure planning, backend selection, export, and QA.
Creates publication-ready scientific figures with multi-panel layouts, error bars, significance annotations, and colorblind-safe palettes. Orchestrates matplotlib, seaborn, and plotly for journal submission (Nature, Science, Cell).
Generates publication-quality Python data visualizations for research papers using matplotlib, seaborn, numpy, pandas, and top-journal color schemes like Nature/Science.