Skip to main content
skill CX Codex

nature-figure · franklee16 — Claude Code skill: what it does, how to install

nature-figure structures high-impact publication figure design using Python or R backends.

no license ★ 240 updated 2026-09-18

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add franklee16/academic-research-skills --skill nature-figure -a claude-code
Open on GitHub

What nature-figure does

This workflow forces the coding agent to approach scientific illustration as an argument rather than pure decoration. Before generating plot scripts, Claude Code establishes a figure contract: it identifies the primary claim, verifies that every planned panel adds distinct evidence, and sets target dimensions alongside editable vector text rules for SVG, PDF, or 600 DPI TIFF files.

The framework enforces a hard backend gate. Unless the user explicitly names the environment upfront, execution halts on a single question: “Python or R?”. Cross-rendering between environments is banned; the assistant will not draft quick previews in R if Python packages are missing, choosing instead to halt and report the missing runtime.

Supported libraries include matplotlib and seaborn on the Python track, plus ggplot2, patchwork, and ComplexHeatmap on the R track. The setup focuses strictly on paper figures and explicitly excludes web dashboards or design-tool infographics.

What it helps with

  • construct multi-panel publication figures defending a central paper thesis
  • configure journal-ready SVG and PDF outputs with unoutlined editable fonts
  • audit evidence logic across scientific plot panels prior to manuscript submission

Example prompts for the agent

  • Build a multi-panel figure for a Nature paper using Python and seaborn
  • Prepare a genomic heatmap layout in R using ComplexHeatmap and patchwork
  • Audit my plot export parameters to ensure 600 DPI TIFF and editable SVG text

How to install nature-figure

1Skills CLI (Vercel)

npx skills add franklee16/academic-research-skills --skill nature-figure -a claude-code

2Manually: put the files in place

~/.claude/skills/nature-figure/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/nature-figure/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about nature-figure

How to install nature-figure in Claude Code?

Run the terminal command npx skills add franklee16/academic-research-skills --skill nature-figure -a claude-code.

What does nature-figure do?

It applies strict journal-grade workflows to create, revise, and verify scientific plots in Python or R.

Can it render a preview in Python if R packages are missing?

No, fallback cross-rendering is prohibited; the chosen language must handle every preview, visual render, and final export.

Similar skills

All skills for Science and research →

nature-figure by other authors comes first.

nature-figure Yuan1z0825 nature-figure is a Claude Code skill that creates, revises, audits, and exports scientific figures in Python or R. It routes manuscript plots, multi-panel layouts, and requested AI-generated schematics to separate workflows. CX Codex +1 20,700installs figure-generation lingzhi227 figure-generation builds publication-ready scientific plots through query expansion, code execution, and visual verification. Helps researchers format charts for papers. CX Codex +1 2,300installs mathmodel-figure-templates jihe520 mathmodel-figure-templates runs packaged Python and matplotlib scripts to generate publication-grade scientific figures. Useful when you need Taylor diagrams, ROC curves, or correlation grids quickly. CX Codex +1 1,700installs seaborn tondevrel This skill guides Python statistical plotting with Seaborn and Matplotlib. Use it for EDA, category comparisons, distributions, and relationship analysis. CX Codex +1 167installs scientific-figure gaasher Builds publication-ready scientific figures from data or prompts through an adversarial generator-critic loop evaluated against a strict rubric. CX Codex +1 ★ 185repo stars answers-charts drawthingsai answers-charts is a Claude Code skill that builds Matplotlib charts and embeds them directly into answers. It outputs verified PNG and SVG files strictly from supplied numbers. CX Codex +1 ★ 171repo stars figure-designer HKUSTDial figure-designer picks the paradigm, layout and tool for the three figures that carry a paper, then audits them against a rule set. CX Codex +1 919installs

From the same set98

The whole set →
extract-figures extract-figures pulls figures, charts, diagrams, and images from .docx, converts EMF/WMF assets to PNG, and prepares LaTeX usage notes. CX Codex +1 ★ 240repo stars aer-referee-sim aer-referee-sim runs a finished manuscript through a mock AER desk screen and three referees, then returns a verdict and a prioritized revise list. CX Codex +1 ★ 240repo stars practitioner-finance-voice The practitioner-finance-voice skill rewrites academic finance drafts into the direct tone of practitioner outlets like FAJ and JPM. It frames findings for portfolio managers without fabricating facts. CX Codex +1 ★ 240repo stars comments-synthesis comments-synthesis turns feedback from several discussants, referees or workshop readers of one paper into a single revision plan, with the points they repeat ranked first. CX Codex +1 ★ 240repo stars llm-replication-disclosure llm-replication-disclosure is a Claude Code skill that checks replication materials for LLM-assisted research and helps draft disclosure text before submission or a data-editor response. CX Codex +1 ★ 240repo stars aer-replication aer-replication builds a replication package for AEA journals under the February 2026 Data and Code Availability Policy. Checks the README and folder layout before the AEA Data Editor review. CX Codex +1 ★ 240repo stars academic-grant Transforms research paper drafts and empirical results into completed academic grant application forms using coordinated agents. CX Codex +1 ★ 240repo stars paper-reading-method-commitment The paper-reading-method-commitment skill guides a research method from a chosen or assembled starting point to a recorded status. Use it before experiment planning or research framing. CX Codex +1 ★ 240repo stars

Project sponsors

Companies that keep this analytics open