skills.rest
manatandu
manatanduCOMMUNITY
Explore all skills by this author →
GitHub

scientific-schematics

Generate publication-quality scientific diagrams from natural language descriptions using OpenRouter image models.

Updated Jul 15, 2026
Search Tags:#image generation#flowchart#gemini#openrouter#publication figures#scientific diagrams#research visualization
One-click install
npx skills add https://github.com/manatandu/Skill-Claude --skill scientific-schematics-manatandu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scientific-schematics
Source: https://github.com/manatandu/Skill-Claude/tree/main/.agents/skills/scientific-schematics
Command: npx skills add https://github.com/manatandu/Skill-Claude --skill scientific-schematics-manatandu

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Creating publication-quality scientific diagrams (flowcharts, neural network architectures, biological pathways, circuit diagrams) traditionally requires manual drawing tools or coding. This Skill generates them automatically from natural language descriptions, with AI-driven quality review and iterative refinement. ## Core Features & Use Cases - Natural Language Diagram Generation: Describe any scientific diagram and Nano Banana Pro (Gemini 3 Pro image model) generates it via the OpenRouter API. - Smart Iterative Refinement: Gemini 3 Pro reviews each generated image against document-type quality thresholds (journal 8.5/10, poster 7.0/10, presentation 6.5/10) and only regenerates when quality falls short. - Review Logs: Every run produces versioned images (v1, v2, ...) plus a JSON review log with scores, critiques, and early-stop reasons. - Use Case: A researcher needs a CONSORT participant flow diagram for a journal submission. They describe the screening, exclusion, and randomization numbers, and receive a publication-ready PNG that passed an 8.5/10 quality review. ## Quick Start Set the OPENROUTER_API_KEY environment variable, then ask the assistant to run scripts/generate_schematic.py with your diagram description, an output path such as figures/consort.png, and a document type like 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 a scientific diagram from a text description?▼

Run scripts/generate_schematic.py with your diagram description and an output path, for example a CONSORT flowchart or Transformer architecture. The script calls the OpenRouter API, generates the image, reviews quality, and saves versioned PNGs plus a JSON review log.

What API key do I need for AI diagram generation?▼

You need an OpenRouter API key from openrouter.ai/keys. Set it as the OPENROUTER_API_KEY environment variable, add it to a .env file, or pass it with the --api-key flag. Without it, the script exits with an error.

How does the iterative quality review work?▼

After each generation, Gemini 3 Pro scores the image on accuracy, clarity, labels, layout, and appearance. If the score meets the document-type threshold (e.g., 8.5 for journal, 7.0 for poster), generation stops early; otherwise the prompt is improved and the image regenerated, up to 2 iterations.

Why did my diagram generation fail or return no image?▼

Common causes are a missing or invalid OPENROUTER_API_KEY, the requests library not installed, or API timeouts. Run with the -v verbose flag to see detailed API responses, and verify your key with echo $OPENROUTER_API_KEY.

What types of scientific diagrams can be generated?▼

The skill handles CONSORT and PRISMA flowcharts, neural network architectures (Transformers, CNNs, RNNs), biological signaling pathways, circuit diagrams, system architectures, and block diagrams. Specific prompts with layout, labels, and quantitative details produce the best results.

Related Skills

Explore More Education & Research Skills→
justaddcoffeejustaddcoffee
13

metabolomics

Translate metabolomics measurements into pathway-contextualized mechanistic interpretations.

Community
Advanced
dralkhdralkh
74

venue-templates

Provide venue-specific academic formatting guidance and templates for manuscripts, papers, posters, and proposals.

Community
Advanced
ricfulopricfulop

science-figure-style

Create publication-quality matplotlib figures meeting Science and AAAS journal formatting requirements.

Community
Intermediate
TTAWDTTTTAWDTT
8

scientific-schematics

Generate publication-quality diagrams from Python code using Graphviz, Matplotlib, Schemdraw, and NetworkX.

Community
Advanced