paperbanana

PaperBanana Skills for Claude Code

One sentence in, publication-quality academic figure out.
Powered by a 5-agent pipeline that plans, styles, generates, and self-critiques your illustrations.

English | 中文

---

Gallery

Biology — Signal Pathway	NLP — RAG Pipeline
Data Engineering — Lakehouse	Medical AI — U-Net + Mamba

All figures generated from plain text descriptions — zero manual drawing.

More Examples (architecture diagrams, slides)

Transformer Architecture	Mamba SSM Architecture
RAG Pipeline

---

Skills in this Marketplace

Skill	Scope	Description	Version
paperbanana	user	Academic diagrams, plots, slides, and quality evaluation	v4.0.0
paperbanana-slide-deck	project	Full slide deck orchestration (RDIV workflow) + 150+ style presets	v1.1.0

Feature Matrix

Capability	Status	Details
Methodology diagrams	✅	Text → publication-quality figure in 30s
Statistical plots	✅	CSV/JSON data → auto-styled academic plot
Presentation slides	✅	Markdown → 4K slide with 150+ style presets
Multi-venue styles	✅ New	--venue neurips|icml|acl|ieee|custom
PDF input	✅ New	--input paper.pdf --pages 3-5
6-item quality eval	✅ New	Binary checklist: completeness, layout, annotation, color, legibility, hallucination
Autoresearch loop	✅ New	Automated prompt self-optimization with keep/revert
Error handling	✅ New	Critic UNREVIEWED status, provider fallback chains, retry filtering
5 VLM providers	✅	Gemini, Claude, OpenAI, Bedrock, OpenRouter
Auto-refine	✅	--auto loops until Critic is satisfied
Run continuation	✅	--continue with --feedback for iterative refinement
Dynamic aspect ratio	✅	8 Imagen ratios, Planner auto-recommends

---

What's New in v4.0

Eval-First Quality System

A 6-item binary checklist evaluator that measures academic figure quality without human reference images:

Check	Question	Pass Criteria
Completeness	All input concepts represented?	Every key concept has a visual element
Layout	Logical flow direction?	Clear L→R, T→B, or radial flow
Annotation	All components labeled?	Every visual element has text
Color Restraint	≤3 primary colors?	Academic palette discipline
Legibility	Readable at 50% zoom?	Text survives PDF column layout
No Hallucination	Zero unlabeled concepts?	Nothing invented beyond input

Baseline: 76% → 100% after prompt optimization. Color restraint was the bottleneck (33% → 100%).

Autoresearch Self-Optimization

Automated prompt mutation loop inspired by Karpathy's autoresearch:

Mutate prompt → Generate figures → Evaluate checklist → Keep or Revert → Repeat