figures4papers
My Python scripts to make high-quality figures for publications in top AI conferences and journals.
Figures4papers is an agent skill that enables AI coding assistants to generate publication-quality scientific figures using Python scripts. Created by a Yale PhD candidate, the skill provides proven patterns and design principles for creating bar plots, radar charts, line plots, 3D visualizations, trend plots, and concept diagrams used in top-tier venues including Nature Machine Intelligence, ICML, NeurIPS, and ECCV. The skill works via a structured folder hierarchy containing API conventions, common patterns, design theory, and real-world examples that AI agents can reference to maintain consistent, professional styling across all generated figures.
Key Features
Use Cases
- 01Generating quantitative comparison bar charts for machine learning benchmarks and experimental results
- 02Creating radar plots to visualize multi-dimensional model performance across different metrics
- 03Building publication-ready trend plots and time-series visualizations for research papers
- 04Producing 3D sphere visualizations and complex concept diagrams for methodology illustrations
- 05Maintaining consistent figure styling across multiple papers and projects using shared design principles
- 06Adapting proven figure patterns from top-tier publications to new datasets and research domains
Related Skills
View moresuperpowers
An agentic skills framework & software development methodology that works.
skills
Skills for Real Engineers. Straight from my .agents directory.
skills
Public repository for Agent Skills
ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
figures4papers — FAQ
What is figures4papers and what does it do?+
Figures4papers is an AI agent skill that provides Python-based templates and design patterns for creating publication-quality scientific figures. It enables coding assistants like Cursor and Claude Code to generate charts, plots, and diagrams following proven styles used in top AI conferences and journals.
How do I install the figures4papers skill in my AI coding agent?+
You can use it without installation by opening the repository in your AI agent and referencing the skill files by path in prompts. For persistent access, create a symlink from the scientific-figure-making folder to your agent's skills directory (e.g., ~/.cursor/skills or ~/.claude/skills).
Which AI coding agents work with this skill?+
The skill works with Cursor, Claude Code, and Codex. Any AI coding agent that can read local files and execute Python scripts can use the path-based workflow without additional setup.
Do I need API keys or special prerequisites to use this skill?+
No API keys are required. You only need Python installed with common scientific plotting libraries like matplotlib, numpy, and any domain-specific packages referenced in the figure scripts you generate.
Is the figures4papers skill free to use?+
Yes, the skill is open source and freely available on GitHub. The repository includes all templates, patterns, and reference implementations at no cost.
How do I tell my AI agent to use the figures4papers skill?+
In your prompt, explicitly reference the skill files (e.g., 'Follow scientific-figure-making/SKILL.md and references/design-theory.md') and specify the figure type you need. The repository includes a ready-to-use prompt template you can copy and customize.
How do I install figures4papers?+
Open the source repository on GitHub and follow its README. figures4papers is a skill — MCP Agents Market links you directly to the official repo.
Is figures4papers free?+
figures4papers is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.