scientific-schematics

Generate scientific diagrams and review them with Gemini 3 Pro.

Updated Dec 17, 2025
One-click install
npx skills add https://github.com/robotlearning123/claude-scientific-skills --skill scientific-schematics-robotlearning123
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: scientific-schematics
Source: https://github.com/robotlearning123/claude-scientific-skills/tree/main/scientific-skills/scientific-schematics
Command: npx skills add https://github.com/robotlearning123/claude-scientific-skills --skill scientific-schematics-robotlearning123

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the generation of publication-quality scientific diagrams and their quality review, saving time and ensuring accuracy.

Core Features & Use Cases

  • AI-Driven Diagram Generation: Describe your diagram in natural language and let the AI create it automatically.
  • Quality Review: Gemini 3 Pro evaluates the diagram against document-type thresholds for scientific accuracy and readability.
  • Smart Iteration: Only regenerates the diagram if the quality is below the threshold, optimizing API usage and turnaround time.
  • Use Case: Need a flowchart for a journal paper? Simply describe the process and let the skill generate a high-quality diagram that meets publication standards.

Quick Start

Generate a flowchart for a journal paper using the scientific-schematics skill:

python scripts/generate_schematic.py "CONSORT participant flow diagram for randomized controlled trial. Start with 'Assessed for eligibility (n=500)' at top. Show 'Excluded (n=150)' with reasons: age<18 (n=80), declined (n=50), other (n=20). Then 'Randomized (n=350)' splits into two arms: 'Treatment group (n=175)' and 'Control group (n=175)'. Each arm shows 'Lost to follow-up' (n=15 and n=10). End with 'Analyzed' (n=160 and n=165). Use blue boxes for process steps, orange for exclusion, green for final analysis." -o figures/consort.png --doc-type journal

Frequently Asked Questions about scientific-schematics

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

FAQPage Schema
How do I generate publication quality scientific diagrams automatically?

Generate publication-quality scientific diagrams by describing your visual in natural language and letting AI create it automatically. You provide a text description, and the system outputs a formatted image file suitable for journal submission.

Can I automatically review scientific diagrams for publication standards?

You can automatically review scientific diagrams for publication standards using integrated Gemini 3 Pro evaluation. The system checks generated schematics against specific document-type thresholds to ensure scientific accuracy and readability.

Do I need an OpenRouter API key to generate scientific schematics?

You need an OpenRouter API key and a Python environment with the requests library to generate scientific schematics. These dependencies are required to access the AI generation and quality review features.

How does iterative refinement work for AI generated scientific diagrams?

Iterative refinement for AI-generated scientific diagrams works by regenerating the image only if the initial quality review falls below your specified threshold. This smart iteration optimizes API usage and turnaround time.

What is the best way to create a CONSORT flowchart for a journal paper?

The best way to create a CONSORT flowchart for a journal paper is to describe the participant flow in natural language, specify document types, and let automated AI generation output a compliant schematic.