
from paperbanana-skill23
Generate publication-quality methodology diagrams, statistical plots, and presentation slides using a multi-agent pipeline and configurable VLM/image providers.
PaperBanana is a CLI-first multi-agent pipeline (Retriever → Planner → Stylist → Visualizer → Critic) for producing academic diagrams, statistical plots, and presentation slides. It orchestrates VLMs and image providers to generate, critique, and refine visual outputs suitable for publications and presentations.
Use when you need AI-assisted generation of methodology figures, data visualizations from CSV/JSON, single or batch slide creation, or comparative evaluation between generated images and human references. It's intended for research authors, presenters, and visualization workflows where iterative critique improves output quality.
Designed for Claude Code / agents that can run CLI commands and orchestrate external providers (Gemini, Anthropic, OpenAI, Bedrock, OpenRouter). The skill assumes network access and provider API keys in environment configuration.
PaperBanana is a multi-agent pipeline skill for generating publication-quality academic diagrams, statistical plots, and presentation slides. It has no bundled scripts — it's a documentation-only skill that instructs agents to use an external CLI package (paperbanana). The SKILL.md is thorough with detailed command reference, parameter tables, error handling with fallback chains, and user confirmation checkpoints. Requires external API keys and pip-installed package to function.
Documentation-only skill with no executable scripts. Security is clean — no shell injection, credential leaks, or suspicious patterns. API keys handled via .env and setup wizard with proper redaction. Well-structured SKILL.md with good error handling guidance and user confirmation checkpoints. Niche academic use case limits breadth of appeal.