# Paper Diagrams

Generates publication-quality academic diagrams from paper methodology text.

- Repository: https://github.com/dwzhu-pku/PaperBanana (7525 stars)
- Category: Design
- License: MIT-0
- Last updated: 2026-10-24
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add dwzhu-pku/PaperBanana --skill paperbanana -g -a claude-code -y`
Codex: `npx skills add dwzhu-pku/PaperBanana --skill paperbanana -g -a codex -y`
Cursor: `npx skills add dwzhu-pku/PaperBanana --skill paperbanana -g -a cursor -y`
Gemini CLI: `npx skills add dwzhu-pku/PaperBanana --skill paperbanana -g -a gemini-cli -y`

## Description

Generate publication-quality academic diagrams from paper methodology text

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# PaperBanana

Generate publication-quality academic diagrams and pipeline figures from a paper's methodology section and figure caption. PaperBanana orchestrates a multi-agent pipeline (Retriever, Planner, Stylist, Visualizer, Critic) to produce camera-ready figures suitable for venues like NeurIPS, ICML, and ACL.

## Environment Setup

```bash
cd <repo-root>
uv pip install -r requirements.txt
```

Set your API key via environment variable or in `configs/model_config.yaml`.

**Option 1 (Recommended): OpenRouter API key**, one key for both text reasoning and image generation:
```bash
export OPENROUTER_API_KEY="sk-or-v1-..."
```

**Option 2: Google API key**, direct access to Gemini API:
```bash
export GOOGLE_API_KEY="your-key-here"
```

If both keys are configured, OpenRouter is used by default.

## Usage

```bash
python skill/run.py \
  --content "METHOD_TEXT" \
  --caption "FIGURE_CAPTION" \
  --task diagram \
  --output output.png
```

## Parameters

The rest: https://github.com/dwzhu-pku/PaperBanana/blob/HEAD/skill/SKILL.md