nature-figure-skill
A Python and R skill for publication figures with a contract, layout QA and independent export, plus the FigureForge editor
- 218 ★ on the repository
- Last commit
Minimal access
Why this level
- The skill writes plotting scripts and figure files to the working folder and runs Python or R
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/nature-figure-skillDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skill writes plotting scripts and figure files to the working folder and runs Python or R
This is third-party code. Review the repository files before installing.
What it does
nature-figure-skill helps make figures for research papers in two ways. The first is the nature-figure agent skill: a figure contract, a backend gate, a single-backend render in Python or R, layout QA, independent export and a delivery checklist. Three hard rules apply: each figure in a set is exported on its own as SVG, PDF and TIFF; legends and stat strips never cover data; color carries meaning, with roles assigned before coloring. The second is FigureForge, a browser editor with nothing to install: an infinite canvas, 22 publication-grade templates (bars with raw-dot overlays, clustered heatmap, volcano, forest, Kaplan-Meier curves, violin plots), 16 curated palettes with recoloring and export to SVG, PNG, TIFF, PDF and PPTX. The repository also holds eight more nature-* skills: text polishing, section drafting, citation, data, paper reading, referee responses, a presentation and literature search. The main skill extends Yuan1z0825's nature-skills, with the differences described in DERIVATIVE_NOTICE.md.
Who it is for. Researchers and graduate students preparing figures for journal submission who want one style, a checked layout and files in the right formats.
Good fit when
- A paper's figure set must match in fonts, axis wording and color
- The agent needs a figure contract and layout check before saving
- A figure is needed as SVG with editable text, vector PDF and TIFF for print
- A multi-panel layout is sketched quickly in the browser and filled with data afterwards
Not a fit when
- You need a quick picture for a slide with no journal requirements: a plain chart is simpler
- The data is not ready: the skill never invents numbers
- You need an interactive web visualization: the skill produces static publication files
Example request
Use nature-figure to make three figures from results.csv for a paper: a survival curve, a volcano and a forest plot, each as separate SVG, PDF and TIFF filesLimitations
The skill must be copied as a whole folder because it uses the references directory and other files. The developers call the main skill an extension of the nature-skills repository and cite commit f3941a1 as the base, as described in DERIVATIVE_NOTICE.md. The other nature-* skills have varying status: stable, beta and draft, listed in the README table. FigureForge keeps its session in the browser, so export a project as .json to move it. Python and R need the relevant plotting libraries installed.
How to disable. Delete the skills/nature-figure folder from the agent's skills directory (for example ~/.codex/skills/). FigureForge installs nothing: close the page, and projects live in the browser and in exported .json files.
FAQ
What is FigureForge?
A browser figure editor for papers: an infinite canvas, 22 publication-grade templates, 16 palettes, Figma-style alignment and grouping, and export to SVG, PNG, TIFF, PDF and PPTX. It opens online with nothing to install.
Why are figures exported separately?
The skill's first rule: three figures stay three files and are never silently merged into one. The set still agrees on fonts, axis wording, color semantics and statistical precision.
Which formats does the skill output?
SVG with editable text as primary, PDF with embedded TrueType fonts and print TIFF with resolution metadata, typically 600 dpi.
What other skills are in the repository?
Eight nature-* skills: text polishing and referee responses, section drafting, citation, data and FAIR metadata, bilingual paper reading, a presentation and literature search. The status of each is listed in the table.
How does it differ from the original nature-skills?
The repository extends nature-skills at commit f3941a1 with the FigureForge editor and a stronger figure process. The file-level changes of the initial derivative commit are listed in the README and DERIVATIVE_NOTICE.md.
Discussion
No questions or reviews yet.
Related
SkillsA skill for scientific figures to Nature, Cell and Science standards: 29 figure types, data checks and vector PDF output.
A skill that builds scientific figures from a table: it offers 2–3 chart candidates, assembles panels and checks image reuse.
SciPilot Figure
scipilot-figure-skill
A scientific visualization advisor skill: it profiles the data and picks a chart for the argument first, then renders it to journal-grade quality
A scientific graphics skill with 148 chart templates, 196 SVG architecture assets and export to editable PowerPoint
A scientific plotting skill: from data checks and statistics to R and Python charts, curated palettes and journal-ready export.
A skill that picks a scientific chart from nearly 100 templates for CSV or Excel data and outputs PNG, SVG, PDF and Python code.
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| nature-figure-skill (this card) | no | 218 | |
| Nature Skills | no | 53,354 | the original nature skill set, while this extends it with a figure contract and the FigureForge browser editor |
| Academic Figure Skill | no | 585 | creates academic figures, while this adds a contract, layout check and independent export |
README in short
The README presents two routes (editor and skill), real template outputs, FigureForge capabilities, the nature-figure process with three hard rules, a quick start, the file set per figure, nine nature-* skills and a section on the origin from nature-skills.
README badge
Original SKILL.md
--- name: nature-figure description: >- Submission-grade Nature/high-impact journal figure workflow. Use whenever the user asks to create, revise, audit, or polish manuscript figures, multi-panel scientific plots, figures4papers-style matplotlib plots, chart-family recommendations, or journal-ready SVG/PDF/TIFF outputs, especially for Nature-family or other high-impact journals. Route no-code / drag-and-drop / "just show me the layout" requests to the FigureForge browser editor; otherwise ask "Python or R?" and stop, then use only that backend for drawing, previewing, exporting, and QA. Supports matplotlib/seaborn and ggplot2/patchwork/ComplexHeatmap. Not for interactive dashboards or Illustrator/Figma-first infographics. --- # Nature Figure Making Skill A guide for producing publication-quality scientific figures as a visual argument, not as isolated pretty plots. Every figure starts from a claim, an evidence hierarchy, and a review-risk check before code or aesthetics. If the user does not yet know which chart family fits the task, start with `references/figure-selection.md` before moving into backend-specific plotting. This skill covers two routes to the same destination: the no-code **FigureForge** browser editor (`figureforge/`, 22 publication-grade templates / 16 palettes / 83 atlas panels) and the scripted **Python / R** pipeline. Triage the route first — see the routing table below. The older Python/matplotlib rules in this skill remain valid. The skill now also supports R, especially `ggplot2 + patchwork + ComplexHeatmap + ggrepel + svglite/cairo_pdf + ragg`. If the user provides a private plotting template collection, use it only as an internal adaptation source and do not reveal its path, filenames, or provenance in user-facing output. Color policy: prefer **unified method families across all panels** over maximal hue separation. For dense Nature Machine Intelligence-style figure pages, use the low-saturation `NMI pastel` family described in `references/api.md` and reserve green/red mainly for gains, drops, and other directional cues. ## Three hard rules (never trade these away) **① Type scale is FINAL PRINT SIZE, in points.** A 183 mm double-column figure uses 5–7 pt text (axis titles 6–7 pt, panel letters 7–8 pt). Never ship a 16–24 pt default — that is slide-deck size; once the canvas is scaled to journal width it crops axis titles, overlaps legends and collides tick labels. Start from the defaults in `references/api.md` (`apply_publication_style()` → 7 pt / 0.8 pt) and only go larger when the canvas itself is larger. A rendered reference of the defaults lives in `evals/visual-baseline/` — if you change the defaults, re-render it and look. **② Legends and stat blocks never sit on top of data.**