skills.rest
OpenLAIR
OpenLAIROFFICIAL
Explore all skills by this author →
GitHub

aris-paper-illustration

Generate publication-quality academic paper figures using Gemini image generation with iterative Claude review.

1.1k|116|Updated Feb 26, 2026
Search Tags:#image generation#GEMINI#architecture diagram#cvpr#academic figures#paper illustration#Latex
One-click install
npx skills add https://github.com/OpenLAIR/dr-claw --skill aris-paper-illustration
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: aris-paper-illustration
Source: https://github.com/OpenLAIR/dr-claw/tree/main/skills/aris-paper-illustration
Command: npx skills add https://github.com/OpenLAIR/dr-claw --skill aris-paper-illustration

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Creating professional architecture diagrams and method illustrations for academic papers is time-consuming, and AI-generated figures often contain wrong arrow directions, missing labels, or unprofessional styling that fails conference standards.

Core Features & Use Cases

  • Multi-Stage Generation Pipeline: Claude plans the figure, Gemini optimizes layout and verifies CVPR/NeurIPS style compliance, then Paperbanana (gemini-3-pro-image-preview) renders the final image.
  • Strict Iterative Review Loop: Claude scores each generated figure against a detailed checklist (arrow correctness, block content, visual appeal) and refines until it reaches a score of 9/10 or hits the 5-iteration limit.
  • Conference Style Compliance: Enforces CVPR/ICLR/NeurIPS visual standards including coordinated color palettes, thick labeled arrows, sans-serif fonts, and print-friendly design.
  • Use Case: A researcher needs an encoder-decoder architecture diagram for a CVPR submission; the skill generates the figure, verifies every arrow direction and label, and outputs a ready-to-use LaTeX snippet.

Quick Start

Ask the assistant to generate an architecture diagram for your paper by describing the model components and data flow, for example: generate a paper illustration of my multimodal fusion pipeline with the aris-paper-illustration skill.

Frequently Asked Questions about aris-paper-illustration

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate an architecture diagram for a research paper with AI?▼

Describe your model components and data flow, and the skill creates a detailed prompt, optimizes layout with gemini-3-pro, renders the image with gemini-3-pro-image-preview, and iteratively refines it until it passes a strict quality review.

What API key do I need for AI paper figure generation?▼

You need a Gemini API key set as the GEMINI_API_KEY environment variable. Obtain one from Google AI Studio at aistudio.google.com/app/apikey and export it before running the skill.

What types of figures can this skill generate?▼

It handles architecture diagrams, method illustrations, pipeline figures, and conceptual comparison diagrams. It is not designed for statistical plots or photo-realistic images.

Does the generated figure follow CVPR or NeurIPS style guidelines?▼

Yes, the workflow enforces top-tier conference standards including coordinated 3-4 color palettes, thick labeled arrows, sans-serif fonts of at least 14pt, white backgrounds, and grayscale print readability.

Why does figure generation stop after several iterations?▼

The refinement loop is capped at 5 iterations to bound API usage. If the figure has not reached the target score of 9 by then, the best version is shown and you can choose to continue or accept it.

Related Skills

Explore More Education & Research Skills→
skyllwtskyllwt
1.6k

/poster

Generate an academic HTML poster from a LaTeX paper.

Community
Advanced
nxZhainxZhai

paper-compile

Compile LaTeX main.tex files to PDF with automated error correction.

Community
Intermediate
tqLi99tqLi99

paper-figure

Generate publication-quality figures and LaTeX-ready tables from JSON or CSV data.

Community
Advanced
causify-aicausify-ai
144

create_tikz_from_description

Convert images or textual descriptions into ready-to-compile TikZ code for LaTeX documents.

Official
Intermediate