figures4papers skill
Skill for publication figures: matplotlib charts for papers in one house style, with vector and raster export from sample scripts.
- 9,654 ★ on the repository
- Last commit
Minimal access
Why this level
- The skill only styles plots and runs local Python scripts.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/figures4papersDetects 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 only styles plots and runs local Python scripts.
This is third-party code. Review the repository files before installing.
What it does
figures4papers is a repository of Python scripts for figures published at NeurIPS, ICML, ECCV and Nature Machine Intelligence, with a bundled `scientific-figure-making` skill. The agent reads `SKILL.md` and the `references/` files: palette, styling helpers and templates for bar, line and radar charts, heatmaps and multi-panel grids. The skill fits the job of getting a plot journal-ready: fonts, axes, legend, PNG and PDF export. The agent opens reference files as needed instead of loading all of them. Examples live in `figure_*` folders, each with a working script and its output.
Who it is for. Graduate students and researchers who plot results for a paper or talk and want one consistent look without hand-editing in a graphics tool.
Good fit when
- A paper is in progress and plots from different experiments look inconsistent.
- Bar comparisons must stay readable in a black-and-white printout.
- An agent writes the plotting script and needs a styling reference.
- A single plot has to be exported in several formats for slides and PDF.
Not a fit when
- You need interactive web charts in Plotly, Altair or Bokeh.
- The data is still being explored and publication is far off.
- The main work is 3D or geographic mapping.
Example request
Plot grouped bars for three models in the figures4papers style and save PNG and PDF.Limitations
The skill targets matplotlib; Plotly, Altair, Bokeh and Illustrator or Figma work are out of scope, as `SKILL.md` itself says. The styling follows the repository author taste, so journals with strict font rules need a separate check. The license is listed as NOASSERTION; read `LICENSE` for reuse terms before publishing figures. The author asks for citations of his papers when the material helps.
How to disable. Remove the link or the `scientific-figure-making` folder from the agent skills directory and restart it.
FAQ
Is installation required?
No. Open the repository in the agent and cite `scientific-figure-making/SKILL.md` by path in the prompt. A symlink install makes the skill available in any project.
Where does the skill go in Claude Code?
Into `~/.claude/skills/`: create the directory and link `scientific-figure-making` with `ln -s`. Cursor uses `~/.cursor/skills`, Codex uses `~/.codex/skills`.
Which charts do the examples cover?
Bar comparisons and compositions, radar and line plots, monthly trends, 3D spheres and concept diagrams. Scripts sit in the `figure_*` folders.
Does the skill work with Plotly?
No. It is written for matplotlib and does not load for such requests.
What license does the repository use?
GitHub lists the license as NOASSERTION. Check the repository `LICENSE` file for reuse terms.
Discussion
No questions or reviews yet.
Related
SkillsMicrosoft's utility and MCP server that turn PDF, Word, Excel, PowerPoint, HTML and other files into Markdown for models
Anthropic skills
Skills
Anthropic's official skill examples: docx, pdf, pptx and xlsx documents, design, MCP builder and the Agent Skills spec
A skill that draws validated architecture, workflow, sequence and data-flow diagrams as one interactive HTML file
PaddleOCR agent skills
PaddleOCR Agent Skills
Two official PaddleOCR skills: text recognition from images and PDFs, and parsing complex documents into Markdown
MinerU is a CLI with a document library: search and revisit an already parsed report using its local cache.
Tesseract OCR is a CLI for multilingual scans: select language datasets and compare recognition on a sample page.
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| figures4papers (this card) | no | 9,654 | |
| Scientific Agent Skills | no | 56,313 | a broad scientific-work skill set; figures4papers focuses on matplotlib figure styling |
| Academic Figure Skill | no | 555 | another academic figure skill; here the samples come from scripts behind published papers |
README in short
The README shows a gallery of figures from papers, explains the skill structure and gives two ways to connect it: by path without installing, or through a symlink for Cursor, Claude Code and Codex.