PaperBanana: AI Academic Figure Generator for Research Papers

PaperBanana: AI Academic Figure Generator for Research Papers

PaperBanana is designed to generate publication-ready academic figures for research papers using a comprehensive five-agent AI pipeline. The tool supports researchers by automating the creation of publication-quality visualizations, including diagrams, statistical plots, and illustrations that align with specific academic venue styles.

What this skill does

• Runs a five-agent AI pipeline with modular Python scripts.
• Utilizes advanced visual language models (VLMs) including Gemini, OpenAI, Anthropic, and OpenRouter for diverse image model support.
• Generates diagrams through a series of agents: Retriever (references), Planner (descriptions), Stylist (polishing), Visualizer (rendering), and Critic (refinement).
• Incorporates multimodal in-context learning with curated reference images and venue style packs.
• Offers an "improve-existing-figure" mode for enhancing pre-existing figures.
• Provides "Plot Mode," capable of generating executable Python matplotlib/seaborn code that matches venue column widths.

Who it is for

• Developers and technical writing teams utilizing AI coding agents such as Claude Code, Cursor, and Codex.
• Researchers and academics seeking to streamline the preparation of visual content for conferences and scholarly publications.
• Organizations aiming to improve the consistency and quality of academic graphical content.

Use cases

• Creating research paper figures that meet the visual standards of conferences such as NeurIPS, ICML, and CVPR.
• Automating the generation of bulk methodology illustrations for journal submissions.
• Enhancing existing academic figures to align with updated conference guidelines.
• Producing data-driven statistical plots without the risk of data misrepresentation.

Technical details

• Requires Python 3.10+ and dependencies: `google-genai>=2`, `matplotlib`, `seaborn`, `numpy`, and `pillow`.
• Integration requires an active API key for configured VLMs or image models.
• Diagram mode operates through `scripts/orchestrate.py` for comprehensive pipeline execution.
• Compatible with AI platforms such as Claude Code, Cursor, and Codex.

Source & Licence

This package is built on open-source work published by javidmardanov (javidmardanov/paper-banana-skill) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.