Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.6 Flash for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological

Scientific Schematics and Diagrams Overview Scientific schematics and diagrams transform complex concepts into clear visual representations for publication. This skill uses Nano Banana 2 AI for diagram generation with Gemini 3.7 Flash quality review. How it works: Describe your diagram in natural language Nano Banana 2 generates a PNG draft from the specified components and relationships Gemini 3.7 Flash reviews quality against document type thresholds Smart iteration : Refines when the score or verdict requests improvement Saved drafts and a review log for manual verification No coding, templates, or manual drawing required Local review thresholds by document type (heuristics chosen by this helper, not publisher acceptance criteria): Document Type Threshold Description journal 8.5/10 Nature, Science, peer reviewed journals conference 8.0/10 Conference papers thesis 8.0/10 Dissertations, theses grant 8.0/10 Grant proposals preprint 7.5/10 arXiv, bioRxiv, etc. report 7.5/10 Technical reports poster 7.0/10 Academic posters presentation 6.5/10 Slides, talks default 7.5/10 General purpose Save diagrams under figures/ using o figures/name.png , then inspect every label and relationship before including them in a paper or poster. The output location is the path you choose. What the output is: a raster PNG at whatever resolution the image model returns. This skill has no vector path and no DPI control — if a journal demands PDF, EPS, or 300 dpi TIFF, convert the PNG downstream and check the result at final print size. Quick Start: Generate Any Diagram Run from this skill directory with requests installed and OPENROUTER API KEY set. The following paid generation examples are illustrative; the request contracts are tested offline. Supply source backed labels and relationships rather than asking the image model to invent them: What happens behind the scenes: 1. Generation 1 : Nano Banana 2 creates initial image following scientific diagram best practices 2. Review 1 : Gemini 3.7 Flash evaluates quality against document type threshold 3. Decision : If quality = threshold and no improvement verdict → DONE (no more iterations needed!) 4. If below threshold or improvement requested : Improved prompt based on critique, regenerate 5. Repeat : Until quality meets threshold OR max iterations reached Smart Iteration Benefits: ✅ Saves API calls if first generation is good enough ✅ Higher quality standards for journal papers ✅ Faster turnaround for presentations/posters ✅ Appropriate quality for each use case Output : Versioned images ( name v1.png , name v2.png ), a copy of the latest successful version at the path you asked for, and name review log.json with the score, critique, and any early stop reason. When the review cannot run — a rate limit, a content filter, a reviewer that answers in some unexpected shape — the image is still generated and saved, but no score is invented for it. The log records "score": null with the reason in "review error" . "reviewed": false means the reviewer did not return a usable response; a prose answer with no parsable score can have "reviewed": true . "final reviewed" remains false without a numeric score, and the run prints Review unavailable image kept, quality not verified . Treat that image as unchecked and look at it yourself and diagnose the review error before spending on another generation. A generation failure ends the loop without automatic replay; if an earlier draft exists, it is retained with its score and the failure in the log. Configuration Set your OpenRouter API key: Get an API key at: https://openrouter.ai/keys Data leaves the machine. Your prompt is sent to OpenRouter to generate the image, and the generated image is sent back to OpenRouter for the quality review. Both are subject to OpenRouter's data policies and those of the underlying model providers. Do not describe unpublished data, patient information, or anything under embargo in the prompt. Current API contract The image call uses OpenRouter POST /api/v1/images with model , prompt , and n: 1 ; it reads data[0].b64 json and checks the returned MIME type (when supplied) and PNG signature. Quality review separately uses POST /api/v1/chat/completions with text and an image url data URL. Both use Bearer authentication. The current chat schema still allows image output; this helper follows the dedicated image generation guide without assuming the chat route was retired. Models are google/gemini 3.1 flash image (Nano Banana 2) and google/gemini 3.7 flash (review). Their IDs and modalities were checked in public catalogs; this helper's Gemini generation/review calls were validated offline, not with a paid end to end run. See [the verified contract and sources](references/iterative refinement.md openrouter contract reviewed 2026 09 30) before changing models or request fields. For trial flows, use the [CONSORT 2025 template and item 22a](https://www.consort spirit.org/item 22a randomized), reconcile enrollment/allocation/follow up/analysis counts, and report the specified primary outcome. For reviews, choose the appropriate [PRISMA 2020 template](https://www.prisma statement.org/prisma 2020 flow diagram); records, reports, and studies are distinct units. An AI score checks neither accounting system. AI Generation Best Practices Effective Prompts for Scientific Diagrams: ✓ Good prompts (specific, detailed): "CONSORT flowchart showing participant flow from screening (n=500) through randomization to final analysis" "Transformer neural network architecture with encoder stack on left, decoder stack on right, showing multi head attention and cross attention connections" "Simplified EGFR → GRB2/SOS → RAS GTP → RAF → MEK → ERK pathway; label nucleotide exchange and phosphorylation distinctly" "Block diagram of IoT system: sensors → microcontroller → WiFi module → cloud server → mobile app" ✗ Avoid vague prompts : "Make a flowchart" (too generic) "Neural network" (which type? what components?) "Pathway diagram" (which pathway? what molecules?) Key elements to include: Type : Flowchart, architecture diagram, pathway, circuit, etc. Components : Specific elements to include Flow/Direction : How elements connect (left to right, top to bottom) Labels : Key annotations or text to include Style : Any specific visual requirements Scientific quality instructions (requested in the prompt; verify the result): Clean white/light background High contrast for readability Clear, readable labels (minimum 10pt) Professional typography (sans serif fonts) Colorblind friendly colors (Okabe Ito palette) Proper spacing to prevent crowding Scale bars, legends, axes where appropriate When to Use This Skill This skill should be used when: Creating neural network architecture diagrams (Transformers, CNNs, RNNs, etc.) Illustrating system architectures and data flow diagrams Drawing methodology flowcharts for study design (CONSORT, PRISMA) Visualizing algorithm workflows and processing pipelines Creating circuit diagrams and electrical schematics Depicting biological pathways and molecular interactions Generating network topologies and hierarchical structures Illustrating conceptual frameworks and theoretical models Designing block diagrams for technical papers How to Use This Skill Simply describe your diagram in natural language. Nano Banana 2 generates it automatically: The AI attempts: ✓ Layout and composition ✓ Labels and annotations ✓ Colors and styling ✓ Quality review and refinement ✓ PNG output for visual and scientific verification Works for all diagram types: Flowcharts (CONSORT, PRISMA, etc.) Neural network architectures Biological pathways Circuit diagrams System architectures Block diagrams Any scientific visualization No coding, no templates, no manual drawing required. AI Generation Mode (Nano Banana 2 + Gemini 3.7 Flash Review) Smart Iterative Refinement, Advanced Usage, and Examples The generate review refine loop, the Python API and command line options, prompt engineering guidance, and four worked examples (CONSORT flowchart, neural network architecture, biological pathway, system architecture) are in [references/iterative refinement.md](references/iterative refinement.md). The loop stops when the review passes or is unavailable, or when generation fails. A below threshold score or an explicit improvement verdict can trigger a second generation; no run makes more than two attempts. Command Line Usage The main entry point for generating scientific schematics: Review is advisory: the vision model can miss incorrect counts, topology, or labels. A high score does not establish scientific validity, CONSORT/PRISMA compliance, accessibility conformance, or a journal's acceptance of AI generated figures. Best Practices Summary Design principles — ask for these in the prompt 1. Clarity over complexity Simplify, remove unnecessary elements 2. Consistent styling Describe the same visual conventions across a paper's figures 3. Colorblind accessibility Ask for the Okabe Ito palette and redundant encoding 4. Appropriate typography Sans serif fonts, generously sized labels 5. Logical flow State the direction (left to right, top to bottom) explicitly The generator includes all of these as prompt instructions by default, but naming them in your own words for the specific diagram works better than relying on the built in guidelines alone. What the pipeline cannot do 1. Vector output PNG only; no PDF, SVG, or EPS is produced 2. Resolution control the image model chooses; there is no DPI flag 3. Color space RGB only; convert for CMYK print workflows downstream 4. Exact line weights or text sizes describe them in the prompt, then verify by eye For raster submissions, check effective resolution as pixel width divided by final width in inches before converting to TIFF. Changing DPI metadata or enlarging pixels does not restore missing detail. Wrapping a PNG in PDF/EPS also leaves it raster: if the venue requires editable vector lines and text, redraw those elements with vector tools and verify their scientific content. Follow the [venue's figure specifications](https://research figure guide.nature.com/figures/preparing figures our specifications/). Integration Guidelines 1. Include in LaTeX Use \includegraphics{} for generated images 2. Caption thoroughly Describe all elements and abbreviations 3. Reference in text Explain diagram in narrative flow 4. Maintain consistency Same style across all figures in paper 5. Version control Keep prompts and generated images in repository Troubleshooting Common Issues Generation is stochastic and iteration is capped at 2, so the levers that actually change the outcome are the prompt, the document type, and re running. There is no post processing step and no quality checking library in this skill: everything you can inspect lives in the generated PNG and in <name review log.json . The diagram is wrong Overlapping text, crowded elements, or arrows that miss their targets Name the layout in the prompt: "vertical flow, one box per row, generous spacing between stages" Name the connections: "arrow from RAF to MEK labelled phosphorylation", not "show the cascade" Re run. Two runs of the same prompt differ, and a bad layout is often just an unlucky draw Content is scientifically wrong or a component is missing List the components explicitly, with counts and labels — the model will not infer them Read the critique field in the review log: the reviewer usually names what it saw missing Wrong text in labels, or figure numbering baked into the image The p

scientific-schematics