[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6M0FV11W3CQV3BCFGADSJ2A":3,"skill-same:01M6M0FV11W3CQV3BCFGADSJ2A":100},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":13,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":57,"install":58,"resources":71},"01M6M0FV11W3CQV3BCFGADSJ2A","scientific-schematics",null,"Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.","endman100\u002Fskill-router-nexus","endman100","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F31997019?v=4","01M6KPDX17BYDWW4RRB0TNGGMX","01M6KPDX64Y2QBEWVFG5W5PWPF",0,"MIT","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FScience\u002Fresearch-and-communication\u002Fscientific-schematics\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"scientific schematics","scientific","diagrams","for","nano","pathways","architectures","neural network","type","banana","document","gemini","only","edit","write","read","specialized","quality","system","create","2026-11-10 10:12:30",false,"---\nname: scientific-schematics\ndescription: Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.\nallowed-tools: Read Write Edit Bash\nlicense: MIT license\nmetadata:\n    skill-author: K-Dense Inc.\n---\n\n# Scientific Schematics and Diagrams\n\n## Overview\n\nScientific schematics and diagrams transform complex concepts into clear visual representations for publication. **This skill uses Nano Banana 2 AI for diagram generation with Gemini 3.1 Pro Preview quality review.**\n\n**How it works:**\n- Describe your diagram in natural language\n- Nano Banana 2 generates publication-quality images automatically\n- **Gemini 3.1 Pro Preview reviews quality** against document-type thresholds\n- **Smart iteration**: Only regenerates if quality is below threshold\n- Publication-ready output in minutes\n- No coding, templates, or manual drawing required\n\n**Quality Thresholds by Document Type:**\n| Document Type | Threshold | Description |\n|---------------|-----------|-------------|\n| journal | 8.5\u002F10 | Nature, Science, peer-reviewed journals |\n| conference | 8.0\u002F10 | Conference papers |\n| thesis | 8.0\u002F10 | Dissertations, theses |\n| grant | 8.0\u002F10 | Grant proposals |\n| preprint | 7.5\u002F10 | arXiv, bioRxiv, etc. |\n| report | 7.5\u002F10 | Technical reports |\n| poster | 7.0\u002F10 | Academic posters |\n| presentation | 6.5\u002F10 | Slides, talks |\n| default | 7.5\u002F10 | General purpose |\n\n**Simply describe what you want, and Nano Banana 2 creates it.** All diagrams are stored in the figures\u002F subfolder and referenced in papers\u002Fposters.\n\n## Quick Start: Generate Any Diagram\n\nCreate any scientific diagram by simply describing it. Nano Banana 2 handles everything automatically with **smart iteration**:\n\n```bash\n# Generate for journal paper (highest quality threshold: 8.5\u002F10)\npython scripts\u002Fgenerate_schematic.py \"CONSORT participant flow diagram with 500 screened, 150 excluded, 350 randomized\" -o figures\u002Fconsort.png --doc-type journal\n\n# Generate for presentation (lower threshold: 6.5\u002F10 - faster)\npython scripts\u002Fgenerate_schematic.py \"Transformer encoder-decoder architecture showing multi-head attention\" -o figures\u002Ftransformer.png --doc-type presentation\n\n# Generate for poster (moderate threshold: 7.0\u002F10)\npython scripts\u002Fgenerate_schematic.py \"MAPK signaling pathway from EGFR to gene transcription\" -o figures\u002Fmapk_pathway.png --doc-type poster\n\n# Custom max iterations (max 2)\npython scripts\u002Fgenerate_schematic.py \"Complex circuit diagram with op-amp, resistors, and capacitors\" -o figures\u002Fcircuit.png --iterations 2 --doc-type journal\n```\n\n**What happens behind the scenes:**\n1. **Generation 1**: Nano Banana 2 creates initial image following scientific diagram best practices\n2. **Review 1**: **Gemini 3.1 Pro Preview** evaluates quality against document-type threshold\n3. **Decision**: If quality >= threshold → **DONE** (no more iterations needed!)\n4. **If below threshold**: Improved prompt based on critique, regenerate\n5. **Repeat**: Until quality meets threshold OR max iterations reached\n\n**Smart Iteration Benefits:**\n- ✅ Saves API calls if first generation is good enough\n- ✅ Higher quality standards for journal papers\n- ✅ Faster turnaround for presentations\u002Fposters\n- ✅ Appropriate quality for each use case\n\n**Output**: Versioned images plus a detailed review log with quality scores, critiques, and early-stop information.\n\n### Configuration\n\nSet your OpenRouter API key:\n```bash\nexport OPENROUTER_API_KEY='your_api_key_here'\n```\n\nGet an API key at: https:\u002F\u002Fopenrouter.ai\u002Fkeys\n\n### AI Generation Best Practices\n\n**Effective Prompts for Scientific Diagrams:**\n\n✓ **Good prompts** (specific, detailed):\n- \"CONSORT flowchart showing participant flow from screening (n=500) through randomization to final analysis\"\n- \"Transformer neural network architecture with encoder stack on left, decoder stack on right, showing multi-head attention and cross-attention connections\"\n- \"Biological signaling cascade: EGFR receptor → RAS → RAF → MEK → ERK → nucleus, with phosphorylation steps labeled\"\n- \"Block diagram of IoT system: sensors → microcontroller → WiFi module → cloud server → mobile app\"\n\n✗ **Avoid vague prompts**:\n- \"Make a flowchart\" (too generic)\n- \"Neural network\" (which type? what components?)\n- \"Pathway diagram\" (which pathway? what molecules?)\n\n**Key elements to include:**\n- **Type**: Flowchart, architecture diagram, pathway, circuit, etc.\n- **Components**: Specific elements to include\n- **Flow\u002FDirection**: How elements connect (left-to-right, top-to-bottom)\n- **Labels**: Key annotations or text to include\n- **Style**: Any specific visual requirements\n\n**Scientific Quality Guidelines** (automatically applied):\n- Clean white\u002Flight background\n- High contrast for readability\n- Clear, readable labels (minimum 10pt)\n- Professional typography (sans-serif fonts)\n- Colorblind-friendly colors (Okabe-Ito palette)\n- Proper spacing to prevent crowding\n- Scale bars, legends, axes where appropriate\n\n## When to Use This Skill\n\nThis skill should be used when:\n- Creating neural network architecture diagrams (Transformers, CNNs, RNNs, etc.)\n- Illustrating system architectures and data flow diagrams\n- Drawing methodology flowcharts for study design (CONSORT, PRISMA)\n- Visualizing algorithm workflows and processing pipelines\n- Creating circuit diagrams and electrical schematics\n- Depicting biological pathways and molecular interactions\n- Generating network topologies and hierarchical structures\n- Illustrating conceptual frameworks and theoretical models\n- Designing block diagrams for technical papers\n\n## How to Use This Skill\n\n**Simply describe your diagram in natural language.** Nano Banana 2 generates it automatically:\n\n```bash\npython scripts\u002Fgenerate_schematic.py \"your diagram description\" -o output.png\n```\n\n**That's it!** The AI handles:\n- ✓ Layout and composition\n- ✓ Labels and annotations\n- ✓ Colors and styling\n- ✓ Quality review and refinement\n- ✓ Publication-ready output\n\n**Works for all diagram types:**\n- Flowcharts (CONSORT, PRISMA, etc.)\n- Neural network architectures\n- Biological pathways\n- Circuit diagrams\n- System architectures\n- Block diagrams\n- Any scientific visualization\n\n**No coding, no templates, no manual drawing required.**\n\n---\n\n# AI Generation Mode (Nano Banana 2 + Gemini 3.1 Pro Preview Review)\n\n## Smart Iterative Refinement Workflow\n\nThe AI generation system uses **smart iteration** - it only regenerates if quality is below the threshold for your document type:\n\n### How Smart Iteration Works\n\n```\n┌─────────────────────────────────────────────────────┐\n│  1. Generate image with Nano Banana 2             │\n│                    ↓                                │\n│  2. Review quality with Gemini 3.1 Pro Preview                │\n│                    ↓                                │\n│  3. Score >= threshold?                             │\n│       YES → DONE! (early stop)                      │\n│       NO  → Improve prompt, go to step 1            │\n│                    ↓                                │\n│  4. Repeat until quality met OR max iterations      │\n└─────────────────────────────────────────────────────┘\n```\n\n### Iteration 1: Initial Generation\n**Prompt Construction:**\n```\nScientific diagram guidelines + User request\n```\n\n**Output:** `diagram_v1.png`\n\n### Quality Review by Gemini 3.1 Pro Preview\n\nGemini 3.1 Pro Preview evaluates the diagram on:\n1. **Scientific Accuracy** (0-2 points) - Correct concepts, notation, relationships\n2. **Clarity and Readability** (0-2 points) - Easy to understand, clear hierarchy\n3. **Label Quality** (0-2 points) - Complete, readable, consistent labels\n4. **Layout and Composition** (0-2 points) - Logical flow, balanced, no overlaps\n5. **Professional Appearance** (0-2 points) - Publication-ready quality\n\n**Example Review Output:**\n```\nSCORE: 8.0\n\nSTRENGTHS:\n- Clear flow from top to bottom\n- All phases properly labeled\n- Professional typography\n\nISSUES:\n- Participant counts slightly small\n- Minor overlap on exclusion box\n\nVERDICT: ACCEPTABLE (for poster, threshold 7.0)\n```\n\n### Decision Point: Continue or Stop?\n\n| If Score... | Action |\n|-------------|--------|\n| >= threshold | **STOP** - Quality is good enough for this document type |\n| \u003C threshold | Continue to next iteration with improved prompt |\n\n**Example:**\n- For a **poster** (threshold 7.0): Score of 7.5 → **DONE after 1 iteration!**\n- For a **journal** (threshold 8.5): Score of 7.5 → Continue improving\n\n### Subsequent Iterations (Only If Needed)\n\nIf quality is below threshold, the system:\n1. Extracts specific issues from Gemini 3.1 Pro Preview's review\n2. Enhances the prompt with improvement instructions\n3. Regenerates with Nano Banana 2\n4. Reviews again with Gemini 3.1 Pro Preview\n5. Repeats until threshold met or max iterations reached\n\n### Review Log\nAll iterations are saved with a JSON review log that includes early-stop information:\n```json\n{\n  \"user_prompt\": \"CONSORT participant flow diagram...\",\n  \"doc_type\": \"poster\",\n  \"quality_threshold\": 7.0,\n  \"iterations\": [\n    {\n      \"iteration\": 1,\n      \"image_path\": \"figures\u002Fconsort_v1.png\",\n      \"score\": 7.5,\n      \"needs_improvement\": false,\n      \"critique\": \"SCORE: 7.5\\nSTRENGTHS:...\"\n    }\n  ],\n  \"final_score\": 7.5,\n  \"early_stop\": true,\n  \"early_stop_reason\": \"Quality score 7.5 meets threshold 7.0 for poster\"\n}\n```\n\n**Note:** With smart iteration, you may see only 1 iteration instead of the full 2 if quality is achieved early!\n\n## Advanced AI Generation Usage\n\n### Python API\n\n```python\nfrom scripts.generate_schematic_ai import ScientificSchematicGenerator\n\n# Initialize generator\ngenerator = ScientificSchematicGenerator(\n    api_key=\"your_openrouter_key\",\n    verbose=True\n)\n\n# Generate with iterative refinement (max 2 iterations)\nresults = generator.generate_iterative(\n    user_prompt=\"Transformer architecture diagram\",\n    output_path=\"figures\u002Ftransformer.png\",\n    iterations=2\n)\n\n# Access results\nprint(f\"Final score: {results['final_score']}\u002F10\")\nprint(f\"Final image: {results['final_image']}\")\n\n# Review individual iterations\nfor iteration in results['iterations']:\n    print(f\"Iteration {iteration['iteration']}: {iteration['score']}\u002F10\")\n    print(f\"Critique: {iteration['critique']}\")\n```\n\n### Command-Line Options\n\n```bash\n# Basic usage (default threshold 7.5\u002F10)\npython scripts\u002Fgenerate_schematic.py \"diagram description\" -o output.png\n\n# Specify document type for appropriate quality threshold\npython scripts\u002Fgenerate_schematic.py \"diagram\" -o out.png --doc-type journal      # 8.5\u002F10\npython scripts\u002Fgenerate_schematic.py \"diagram\" -o out.png --doc-type conference   # 8.0\u002F10\npython scripts\u002Fgenerate_schematic.py \"diagram\" -o out.png --doc-type poster       # 7.0\u002F10\npython scripts\u002Fgenerate_schematic.py \"diagram\" -o out.png --doc-type presentation # 6.5\u002F10\n\n# Custom max iterations (1-2)\npython scripts\u002Fgenerate_schematic.py \"complex diagram\" -o diagram.png --iterations 2\n\n# Verbose output (see all API calls and reviews)\npython scripts\u002Fgenerate_schematic.py \"flowchart\" -o flow.png -v\n\n# Provide API key via flag\npython scripts\u002Fgenerate_schematic.py \"diagram\" -o out.png --api-key \"sk-or-v1-...\"\n\n# Combine options\npython scripts\u002Fgenerate_schematic.py \"neural network\" -o nn.png --doc-type journal --iterations 2 -v\n```\n\n### Prompt Engineering Tips\n\n**1. Be Specific About Layout:**\n```\n✓ \"Flowchart with vertical flow, top to bottom\"\n✓ \"Architecture diagram with encoder on left, decoder on right\"\n✓ \"Circular pathway diagram with clockwise flow\"\n```\n\n**2. Include Quantitative Details:**\n```\n✓ \"Neural network with input layer (784 nodes), hidden layer (128 nodes), output (10 nodes)\"\n✓ \"Flowchart showing n=500 screened, n=150 excluded, n=350 randomized\"\n✓ \"Circuit with 1kΩ resistor, 10µF capacitor, 5V source\"\n```\n\n**3. Specify Visual Style:**\n```\n✓ \"Minimalist block diagram with clean lines\"\n✓ \"Detailed biological pathway with protein structures\"\n✓ \"Technical schematic with engineering notation\"\n```\n\n**4. Request Specific Labels:**\n```\n✓ \"Label all arrows with activation\u002Finhibition\"\n✓ \"Include layer dimensions in each box\"\n✓ \"Show time progression with timestamps\"\n```\n\n**5. Mention Color Requirements:**\n```\n✓ \"Use colorblind-friendly colors\"\n✓ \"Grayscale-compatible design\"\n✓ \"Color-code by function: blue for input, green for processing, red for output\"\n```\n\n## AI Generation Examples\n\n### Example 1: CONSORT Flowchart\n```bash\npython scripts\u002Fgenerate_schematic.py \\\n  \"CONSORT participant flow diagram for randomized controlled trial. \\\n   Start with 'Assessed for eligibility (n=500)' at top. \\\n   Show 'Excluded (n=150)' with reasons: age\u003C18 (n=80), declined (n=50), other (n=20). \\\n   Then 'Randomized (n=350)' splits into two arms: \\\n   'Treatment group (n=175)' and 'Control group (n=175)'. \\\n   Each arm shows 'Lost to follow-up' (n=15 and n=10). \\\n   End with 'Analyzed' (n=160 and n=165). \\\n   Use blue boxes for process steps, orange for exclusion, green for final analysis.\" \\\n  -o figures\u002Fconsort.png\n```\n\n### Example 2: Neural Network Architecture\n```bash\npython scripts\u002Fgenerate_schematic.py \\\n  \"Transformer encoder-decoder architecture diagram. \\\n   Left side: Encoder stack with input embedding, positional encoding, \\\n   multi-head self-attention, add & norm, feed-forward, add & norm. \\\n   Right side: Decoder stack with output embedding, positional encoding, \\\n   masked self-attention, add & norm, cross-attention (receiving from encoder), \\\n   add & norm, feed-forward, add & norm, linear & softmax. \\\n   Show cross-attention connection from encoder to decoder with dashed line. \\\n   Use light blue for encoder, light red for decoder. \\\n   Label all components clearly.\" \\\n  -o figures\u002Ftransformer.png --iterations 2\n```\n\n### Example 3: Biological Pathway\n```bash\npython scripts\u002Fgenerate_schematic.py \\\n  \"MAPK signaling pathway diagram. \\\n   Start with EGFR receptor at cell membrane (top). \\\n   Arrow down to RAS (with GTP label). \\\n   Arrow to RAF kinase. \\\n   Arrow to MEK kinase. \\\n   Arrow to ERK kinase. \\\n   Final arrow to nucleus showing gene transcription. \\\n   Label each arrow with 'phosphorylation' or 'activation'. \\\n   Use rounded rectangles for proteins, different colors for each. \\\n   Include membrane boundary line at top.\" \\\n  -o figures\u002Fmapk_pathway.png\n```\n\n### Example 4: System Architecture\n```bash\npython scripts\u002Fgenerate_schematic.py \\\n  \"IoT system architecture block diagram. \\\n   Bottom layer: Sensors (temperature, humidity, motion) in green boxes. \\\n   Middle layer: Microcontroller (ESP32) in blue box. \\\n   Connections to WiFi module (orange box) and Display (purple box). \\\n   Top layer: Cloud server (gray box) connected to mobile app (light blue box). \\\n   Show data flow arrows between all components. \\\n   Label connections with protocols: I2C, UART, WiFi, HTTPS.\" \\\n  -o figures\u002Fiot_architecture.png\n```\n\n---\n\n## Command-Line Usage\n\nThe main entry point for generating scientific schematics:\n\n```bash\n# Basic usage\npython scripts\u002Fgenerate_schematic.py \"diagram description\" -o output.png\n\n# Custom iterations (max 2)\npython scripts\u002Fgenerate_schematic.py \"complex diagram\" -o diagram.png --iterations 2\n\n# Verbose mode\npython scripts\u002Fgenerate_schematic.py \"diagram\" -o out.png -v\n```\n\n**Note:** The Nano Banana 2 AI generation system includes automatic quality review in its iterative refinement process. Each iteration is evaluated for scientific accuracy, clarity, and accessibility.\n\n## Best Practices Summary\n\n### Design Principles\n\n1. **Clarity over complexity** - Simplify, remove unnecessary elements\n2. **Consistent styling** - Use templates and style files\n3. **Colorblind accessibility** - Use Okabe-Ito palette, redundant encoding\n4. **Appropriate typography** - Sans-serif fonts, minimum 7-8 pt\n5. **Vector format** - Always use PDF\u002FSVG for publication\n\n### Technical Requirements\n\n1. **Resolution** - Vector preferred, or 300+ DPI for raster\n2. **File format** - PDF for LaTeX, SVG for web, PNG as fallback\n3. **Color space** - RGB for digital, CMYK for print (convert if needed)\n4. **Line weights** - Minimum 0.5 pt, typical 1-2 pt\n5. **Text size** - 7-8 pt minimum at final size\n\n### Integration Guidelines\n\n1. **Include in LaTeX** - Use `\\includegraphics{}` for generated images\n2. **Caption thoroughly** - Describe all elements and abbreviations\n3. **Reference in text** - Explain diagram in narrative flow\n4. **Maintain consistency** - Same style across all figures in paper\n5. **Version control** - Keep prompts and generated images in repository\n\n## Troubleshooting Common Issues\n\n### AI Generation Issues\n\n**Problem**: Overlapping text or elements\n- **Solution**: AI generation automatically handles spacing\n- **Solution**: Increase iterations: `--iterations 2` for better refinement\n\n**Problem**: Elements not connecting properly\n- **Solution**: Make your prompt more specific about connections and layout\n- **Solution**: Increase iterations for better refinement\n\n### Image Quality Issues\n\n**Problem**: Export quality poor\n- **Solution**: AI generation produces high-quality images automatically\n- **Solution**: Increase iterations for better results: `--iterations 2`\n\n**Problem**: Elements overlap after generation\n- **Solution**: AI generation automatically handles spacing\n- **Solution**: Increase iterations: `--iterations 2` for better refinement\n- **Solution**: Make your prompt more specific about layout and spacing requirements\n\n### Quality Check Issues\n\n**Problem**: False positive overlap detection\n- **Solution**: Adjust threshold: `detect_overlaps(image_path, threshold=0.98)`\n- **Solution**: Manually review flagged regions in visual report\n\n**Problem**: Generated image quality is low\n- **Solution**: AI generation produces high-quality images by default\n- **Solution**: Increase iterations for better results: `--iterations 2`\n\n**Problem**: Colorblind simulation shows poor contrast\n- **Solution**: Switch to Okabe-Ito palette explicitly in code\n- **Solution**: Add redundant encoding (shapes, patterns, line styles)\n- **Solution**: Increase color saturation and lightness differences\n\n**Problem**: High-severity overlaps detected\n- **Solution**: Review overlap_report.json for exact positions\n- **Solution**: Increase spacing in those specific regions\n- **Solution**: Re-run with adjusted parameters and verify again\n\n**Problem**: Visual report generation fails\n- **Solution**: Check Pillow and matplotlib installations\n- **Solution**: Ensure image file is readable: `Image.open(path).verify()`\n- **Solution**: Check sufficient disk space for report generation\n\n### Accessibility Problems\n\n**Problem**: Colors indistinguishable in grayscale\n- **Solution**: Run accessibility checker: `verify_accessibility(image_path)`\n- **Solution**: Add patterns, shapes, or line styles for redundancy\n- **Solution**: Increase contrast between adjacent elements\n\n**Problem**: Text too small when printed\n- **Solution**: Run resolution validator: `validate_resolution(image_path)`\n- **Solution**: Design at final size, use minimum 7-8 pt fonts\n- **Solution**: Check physical dimensions in resolution report\n\n**Problem**: Accessibility checks consistently fail\n- **Solution**: Review accessibility_report.json for specific failures\n- **Solution**: Increase color contrast by at least 20%\n- **Solution**: Test with actual grayscale conversion before finalizing\n\n## Resources and References\n\n### Detailed References\n\nLoad these files for comprehensive information on specific topics:\n\n- **`references\u002Fbest_practices.md`** - Publication standards and accessibility guidelines\n\n### External Resources\n\n**Python Libraries**\n- Schemdraw Documentation: https:\u002F\u002Fschemdraw.readthedocs.io\u002F\n- NetworkX Documentation: https:\u002F\u002Fnetworkx.org\u002Fdocumentation\u002F\n- Matplotlib Documentation: https:\u002F\u002Fmatplotlib.org\u002F\n\n**Publication Standards**\n- Nature Figure Guidelines: https:\u002F\u002Fwww.nature.com\u002Fnature\u002Ffor-authors\u002Ffinal-submission\n- Science Figure Guidelines: https:\u002F\u002Fwww.science.org\u002Fcontent\u002Fpage\u002Finstructions-preparing-initial-manuscript\n- CONSORT Diagram: http:\u002F\u002Fwww.consort-statement.org\u002Fconsort-statement\u002Fflow-diagram\n\n## Integration with Other Skills\n\nThis skill works synergistically with:\n\n- **Scientific Writing** - Diagrams follow figure best practices\n- **Scientific Visualization** - Shares color palettes and styling\n- **LaTeX Posters** - Generate diagrams for poster presentations\n- **Research Grants** - Methodology diagrams for proposals\n- **Peer Review** - Evaluate diagram clarity and accessibility\n\n## Quick Reference Checklist\n\nBefore submitting diagrams, verify:\n\n### Visual Quality\n- [ ] High-quality image format (PNG from AI generation)\n- [ ] No overlapping elements (AI handles automatically)\n- [ ] Adequate spacing between all components (AI optimizes)\n- [ ] Clean, professional alignment\n- [ ] All arrows connect properly to intended targets\n\n### Accessibility\n- [ ] Colorblind-safe palette (Okabe-Ito) used\n- [ ] Works in grayscale (tested with accessibility checker)\n- [ ] Sufficient contrast between elements (verified)\n- [ ] Redundant encoding where appropriate (shapes + colors)\n- [ ] Colorblind simulation passes all checks\n\n### Typography and Readability\n- [ ] Text minimum 7-8 pt at final size\n- [ ] All elements labeled clearly and completely\n- [ ] Consistent font family and sizing\n- [ ] No text overlaps or cutoffs\n- [ ] Units included where applicable\n\n### Publication Standards\n- [ ] Consistent styling with other figures in manuscript\n- [ ] Comprehensive caption written with all abbreviations defined\n- [ ] Referenced appropriately in manuscript text\n- [ ] Meets journal-specific dimension requirements\n- [ ] Exported in required format for journal (PDF\u002FEPS\u002FTIFF)\n\n### Quality Verification (Required)\n- [ ] Ran `run_quality_checks()` and achieved PASS status\n- [ ] Reviewed overlap detection report (zero high-severity overlaps)\n- [ ] Passed accessibility verification (grayscale and colorblind)\n- [ ] Resolution validated at target DPI (300+ for print)\n- [ ] Visual quality report generated and reviewed\n- [ ] All quality reports saved with figure files\n\n### Documentation and Version Control\n- [ ] Source files (.tex, .py) saved for future revision\n- [ ] Quality reports archived in `quality_reports\u002F` directory\n- [ ] Configuration parameters documented (colors, spacing, sizes)\n- [ ] Git commit includes source, output, and quality reports\n- [ ] README or comments explain how to regenerate figure\n\n### Final Integration Check\n- [ ] Figure displays correctly in compiled manuscript\n- [ ] Cross-references work (`\\ref{}` points to correct figure)\n- [ ] Figure number matches text citations\n- [ ] Caption appears on correct page relative to figure\n- [ ] No compilation warnings or errors related to figure\n\n## Environment Setup\n\n```bash\n# Required\nexport OPENROUTER_API_KEY='your_api_key_here'\n\n# Get key at: https:\u002F\u002Fopenrouter.ai\u002Fkeys\n```\n\n## Getting Started\n\n**Simplest possible usage:**\n```bash\npython scripts\u002Fgenerate_schematic.py \"your diagram description\" -o output.png\n```\n\n---\n\nUse this skill to create clear, accessible, publication-quality diagrams that effectively communicate complex scientific concepts. The AI-powered workflow with iterative refinement ensures diagrams meet professional standards.\n\n\n","# Scientific Schematics and Diagrams\n\n## Overview\n\nScientific schematics and diagrams transform complex concepts into clear visual representations for publication. **This skill uses Nano Banana 2 AI for diagram generation with Gemini 3.1 Pro Preview quality review.**\n\n**How it works:**\n- Describe your diagram in natural language\n- Nano Banana 2 generates publication-quality images automatically\n- **Gemini 3.1 Pro Preview reviews quality** against document-type thresholds\n- **Smart iteration**: Only regenerates if quality is below threshold\n- Publication-ready output in minutes\n- No coding, templates, or manual drawing required\n\n**Quality Thresholds by Document Type:**\n| Document Type | Threshold | Description |\n|---------------|-----------|-------------|\n| journal | 8.5\u002F10 | Nature, Science, peer-reviewed journals |\n| conference | 8.0\u002F10 | Conference papers |\n| thesis | 8.0\u002F10 | Dissertations, theses |\n| grant | 8.0\u002F10 | Grant proposals |\n| preprint | 7.5\u002F10 | arXiv, bioRxiv, etc. |\n| report | 7.5\u002F10 | Technical reports |\n| poster | 7.0\u002F10 | Academic posters |\n| presentation | 6.5\u002F10 | Slides, talks |\n| default | 7.5\u002F10 | General purpose |\n\n**Simply describe what you want, and Nano Banana 2 creates it.** All diagrams are stored in the figures\u002F subfolder and referenced in papers\u002Fposters.\n\n## Quick Start: Generate Any Diagram\n\nCreate any scientific diagram by simply describing it. Nano Banana 2 handles everything automatically with **smart iteration**:\n\n```bash\n# Generate for journal paper (highest quality threshold: 8.5\u002F10)\npython scripts\u002Fgenerate_schematic.py \"CONSORT participant flow diagram with 500 screened, 150 excluded, 350 randomized\" -o figures\u002Fconsort.png --doc-type journal\n\n# Generate for presentation (lower threshold: 6.5\u002F10 - faster)\npython scripts\u002Fgenerate_schematic.py \"Transformer encoder-decoder architecture showing multi-head attention\" -o figures\u002Ftransformer.png --doc-type presentation\n\n# Generate for poster (moderate threshold: 7.0\u002F10)\npython scripts\u002Fgenerate_schematic.py \"MAPK signaling pathway from EGFR to gene transcription\" -o figures\u002Fmapk_pathway.png --doc-type poster\n\n# Custom max iterations (max 2)\npython scripts\u002Fgenerate_schematic.py \"Complex circuit diagram with op-amp, resistors, and capacitors\" -o figures\u002Fcircuit.png --iterations 2 --doc-type journal\n```\n\n**What happens behind the scenes:**\n1. **Generation 1**: Nano Banana 2 creates initial image following scientific diagram best practices\n2. **Review 1**: **Gemini 3.1 Pro Preview** evaluates quality against document-type threshold\n3. **Decision**: If quality >= threshold → **DONE** (no more iterations needed!)\n4. **If below threshold**: Improved prompt based on critique, regenerate\n5. **Repeat**: Until quality meets threshold OR max iterations reached\n\n**Smart Iteration Benefits:**\n- ✅ Saves API calls if first generation is good enough\n- ✅ Higher quality standards for journal papers\n- ✅ Faster turnaround for presentations\u002Fposters\n- ✅ Appropriate quality for each use case\n\n**Output**: Versioned images plus a detailed review log with quality scores, critiques, and early-stop information.\n\n### Configuration\n\nSet your OpenRouter API key:\n```bash\nexport OPENROUTER_API_KEY='your_api_key_here'\n```\n\nGet an API key at: https:\u002F\u002Fopenrouter.ai\u002Fkeys\n\n### AI Generation Best Practices\n\n**Effective Prompts for Scientific Diagrams:**\n\n✓ **Good prompts** (specific, detailed):\n- \"CONSORT flowchart showing participant flow from screening (n=500) through randomization to final analysis\"\n- \"Transformer neural network architecture with encoder stack on left, decoder stack on right, showing multi-head attention and cross-attention connections\"\n- \"Biological signaling cascade: EGFR receptor → RAS → RAF → MEK → ERK → nucleus, with phosphorylation steps labeled\"\n- \"Block diagram of IoT system: sensors → microcontroller → WiFi module → cloud server → mobile app\"\n\n✗ **Avoid vague prompts**:\n- \"Make a flowchart\" (too generic)\n- \"Neural network\" (which type? what components?)\n- \"Pathway diagram\" (which pathway? what molecules?)\n\n**Key elements to include:**\n- **Type**: Flowchart, architecture diagram, pathway, circuit, etc.\n- **Components**: Specific elements to include\n- **Flow\u002FDirection**: How elements connect (left-to-right, top-to-bottom)\n- **Labels**: Key annotations or text to include\n- **Style**: Any specific visual requirements\n\n**Scientific Quality Guidelines** (automatically applied):\n- Clean white\u002Flight background\n- High contrast for readability\n- Clear, readable labels (minimum 10pt)\n- Professional typography (sans-serif fonts)\n- Colorblind-friendly colors (Okabe-Ito palette)\n- Proper spacing to prevent crowding\n- Scale bars, legends, axes where appropriate\n\n## When to Use This Skill\n\nThis skill should be used when:\n- Creating neural network architecture diagrams (Transformers, CNNs, RNNs, etc.)\n- Illustrating system architectures and data flow diagrams\n- Drawing methodology flowcharts for study design (CONSORT, PRISMA)\n- Visualizing algorithm workflows and processing pipelines\n- Creating circuit diagrams and electrical schematics\n- Depicting biological pathways and molecular interactions\n- Generating network topologies and hierarchical structures\n- Illustrating conceptual frameworks and theoretical models\n- Designing block diagrams for technical papers\n\n## How to Use This Skill\n\n**Simply describe your diagram in natural language.** Nano Banana 2 generates it automatically:\n\n```bash\npython scripts\u002Fgenerate_schematic.py \"your diagram description\" -o output.png\n```\n\n**That's it!** The AI handles:\n- ✓ Layout and composition\n- ✓ Labels and annotations\n- ✓ Colors and styling\n- ✓ Quality review and refinement\n- ✓ Publication-ready output\n\n**Works for all diagram types:**\n- Flowcharts (CONSORT, PRISMA, etc.)\n- Neural network architectures\n- Biological pathways\n- Circuit diagrams\n- System architectures\n- Block diagrams\n- Any scientific visualization\n\n**No coding, no templates, no manual drawing required.**\n\n---\n\n# AI Generation Mode (Nano Banana 2 + Gemini 3.1 Pro Preview Review)\n\n## Smart Iterative Refinement Workflow\n\nThe AI generation system uses **smart iteration** - it only regenerates if quality is below the threshold for your document type:\n\n### How Smart Iteration Works\n\n```\n┌─────────────────────────────────────────────────────┐\n│  1. Generate image with Nano Banana 2             │\n│                    ↓                                │\n│  2. Review quality with Gemini 3.1 Pro Preview                │\n│                    ↓                                │\n│  3. Score >= threshold?                             │\n│       YES → DONE! (early stop)                      │\n│       NO  → Improve prompt, go to step 1            │\n│                    ↓                                │\n│  4. Repeat until quality met OR max iterations      │\n└─────────────────────────────────────────────────────┘\n```\n\n### Iteration 1: Initial Generation\n**Prompt Construction:**\n```\nScientific diagram guidelines + User request\n```\n\n**Output:** `diagram_v1.png`\n\n### Quality Review by Gemini 3.1 Pro Preview\n\nGemini 3.1 Pro Preview evaluates the diagram on:\n1. **Scientific Accuracy** (0-2 points) - Correct concepts, notation, relationships\n2. **Clarity and Readability** (0-2 points) - Easy to understand, clear hierarchy\n3. **Label Quality** (0-2 points) - Complete, readable, consistent labels\n4. **Layout and Composition** (0-2 points) - Logical flow, balanced, no overlaps\n5. **Professional Appearance** (0-2 points) - Publication-ready quality\n\n**Example Review Output:**\n```\nSCORE: 8.0\n\nSTRENGTHS:\n- Clear flow from top to bottom\n- All phases properly labeled\n- Professional typography\n\nISSUES:\n- Participant counts slightly small\n- Minor overlap on exclusion box\n\nVERDICT: ACCEPTABLE (for poster, threshold 7.0)\n```\n\n### Decision Point: Continue or Stop?\n\n| If Score... | Action |\n|-------------|--------|\n| >= threshold | **STOP** - Quality is good enough for this document type |\n| \u003C threshold | Continue to next iteration with improved prompt |\n\n**Example:**\n- For a **poster** (threshold 7.0): Score of 7.5 → **DONE after 1 iteration!**\n- For a **journal** (threshold 8.5): Score of 7.5 → Continue improving\n\n### Subsequent Iterations (Only If Needed)\n\nIf quality is below threshold, the system:\n1. Extracts specific issues from Gemini 3.1 Pro Preview's review\n2. Enhances the prompt with improvement instructions\n3. Regenerates with Nano Banana 2\n4. Reviews again with Gemini 3.1 Pro Preview\n5. Repeats until threshold met or max iterations reached\n\n### Review Log\nAll iterations are saved with a JSON review log that includes early-stop information:\n```json\n{\n  \"user_prompt\": \"CONSORT participant flow diagram...\",\n  \"doc_type\": \"poster\",\n  \"quality_threshold\": 7.0,\n  \"iterations\": [\n    {\n      \"iteration\": 1,\n      \"image_path\": \"figures\u002Fconsort_v1.png\",\n      \"score\": 7.5,\n      \"needs_improvement\": false,\n      \"critique\": \"SCORE: 7.5\\nSTRENGTHS:...\"\n    }\n  ],\n  \"final_score\": 7.5,\n  \"early_stop\": true,\n  \"early_stop_reason\": \"Quality score 7.5 meets threshold 7.0 for poster\"\n}\n```\n\n**Note:** With smart iteration, you may see only 1 iteration instead of the full 2 if quality is achieved early!\n\n## Advanced AI Generation Usage\n\n### Python API\n\n```python\nfrom scripts.generate_schematic_ai import ScientificSchematicGenerator\n\n# Initialize generator\ngenerator = ScientificSchematicGenerator(\n    api_key=\"your_openrouter_key\",\n    verbose=True\n)\n\n# Generate with iterative refinement (max 2 iterations)\nresults = generator.generate_iterative(\n    user_prompt=\"Transformer architecture diagram\",\n    output_path=\"figures\u002Ftransformer.png\",\n    iterations=2\n)\n\n# Access results\nprint(f\"Final score: {results['final_score']}\u002F10\")\nprint(f\"Final image: {results['final_image']}\")\n\n# Review individual iterations\nfor iteration in results['iterations']:\n    print(f\"Iteration {iteration['iteration']}: {iteration['score']}\u002F10\")\n    print(f\"Critique: {iteration['critique']}\")\n```\n\n### Command-Line Options\n\n```bash\n# Basic usage (default threshold 7.5\u002F10)\npython scripts\u002Fgenerate_schematic.py \"diagram description\" -o output.png\n\n# Specify document type for appropriate quality threshold\npython scripts\u002Fgenerate_schematic.py \"diagram\" -o out.png --doc-type journal      # 8.5\u002F10\npython scripts\u002Fgenerate_schematic.py \"diagram\" -o out.png --doc-type conference   # 8.0\u002F10\npython scripts\u002Fgenerate_schematic.py \"diagram\" -o out.png --doc-type poster       # 7.0\u002F10\npython scripts\u002Fgenerate_schematic.py \"diagram\" -o out.png --doc-type presentation # 6.5\u002F10\n\n# Custom max iterations (1-2)\npython scripts\u002Fgenerate_schematic.py \"complex diagram\" -o diagram.png --iterations 2\n\n# Verbose output (see all API calls and reviews)\npython scripts\u002Fgenerate_schematic.py \"flowchart\" -o flow.png -v\n\n# Provide API key via flag\npython scripts\u002Fgenerate_schematic.py \"diagram\" -o out.png --api-key \"sk-or-v1-...\"\n\n# Combine options\npython scripts\u002Fgenerate_schematic.py \"neural network\" -o nn.png --doc-type journal --iterations 2 -v\n```\n\n### Prompt Engineering Tips\n\n**1. Be Specific About Layout:**\n```\n✓ \"Flowchart with vertical flow, top to bottom\"\n✓ \"Architecture diagram with encoder on left, decoder on right\"\n✓ \"Circular pathway diagram with clockwise flow\"\n```\n\n**2. Include Quantitative Details:**\n```\n✓ \"Neural network with input layer (784 nodes), hidden layer (128 nodes), output (10 nodes)\"\n✓ \"Flowchart showing n=500 screened, n=150 excluded, n=350 randomized\"\n✓ \"Circuit with 1kΩ resistor, 10µF capacitor, 5V source\"\n```\n\n**3. Specify Visual Style:**\n```\n✓ \"Minimalist block diagram with clean lines\"\n✓ \"Detailed biological pathway with protein structures\"\n✓ \"Technical schematic with engineering notation\"\n```\n\n**4. Request Specific Labels:**\n```\n✓ \"Label all arrows with activation\u002Finhibition\"\n✓ \"Include layer dimensions in each box\"\n✓ \"Show time progression with timestamps\"\n```\n\n**5. Mention Color Requirements:**\n```\n✓ \"Use colorblind-friendly colors\"\n✓ \"Grayscale-compatible design\"\n✓ \"Color-code by function: blue for input, green for processing, red for output\"\n```\n\n## AI Generation Examples\n\n### Example 1: CONSORT Flowchart\n```bash\npython scripts\u002Fgenerate_schematic.py \\\n  \"CONSORT participant flow diagram for randomized controlled trial. \\\n   Start with 'Assessed for eligibility (n=500)' at top. \\\n   Show 'Excluded (n=150)' with reasons: age\u003C18 (n=80), declined (n=50), other (n=20). \\\n   Then 'Randomized (n=350)' splits into two arms: \\\n   'Treatment group (n=175)' and 'Control group (n=175)'. \\\n   Each arm shows 'Lost to follow-up' (n=15 and n=10). \\\n   End with 'Analyzed' (n=160 and n=165). \\\n   Use blue boxes for process steps, orange for exclusion, green for final analysis.\" \\\n  -o figures\u002Fconsort.png\n```\n\n### Example 2: Neural Network Architecture\n```bash\npython scripts\u002Fgenerate_schematic.py \\\n  \"Transformer encoder-decoder architecture diagram. \\\n   Left side: Encoder stack with input embedding, positional encoding, \\\n   multi-head self-attention, add & norm, feed-forward, add & norm. \\\n   Right side: Decoder stack with output embedding, positional encoding, \\\n   masked self-attention, add & norm, cross-attention (receiving from encoder), \\\n   add & norm, feed-forward, add & norm, linear & softmax. \\\n   Show cross-attention connection from encoder to decoder with dashed line. \\\n   Use light blue for encoder, light red for decoder. \\\n   Label all components clearly.\" \\\n  -o figures\u002Ftransformer.png --iterations 2\n```\n\n### Example 3: Biological Pathway\n```bash\npython scripts\u002Fgenerate_schematic.py \\\n  \"MAPK signaling pathway diagram. \\\n   Start with EGFR receptor at cell membrane (top). \\\n   Arrow down to RAS (with GTP label). \\\n   Arrow to RAF kinase. \\\n   Arrow to MEK kinase. \\\n   Arrow to ERK kinase. \\\n   Final arrow to nucleus showing gene transcription. \\\n   Label each arrow with 'phosphorylation' or 'activation'. \\\n   Use rounded rectangles for proteins, different colors for each. \\\n   Include membrane boundary line at top.\" \\\n  -o figures\u002Fmapk_pathway.png\n```\n\n### Example 4: System Architecture\n```bash\npython scripts\u002Fgenerate_schematic.py \\\n  \"IoT system architecture block diagram. \\\n   Bottom layer: Sensors (temperature, humidity, motion) in green boxes. \\\n   Middle layer: Microcontroller (ESP32) in blue box. \\\n   Connections to WiFi module (orange box) and Display (purple box). \\\n   Top layer: Cloud server (gray box) connected to mobile app (light blue box). \\\n   Show data flow arrows between all components. \\\n   Label connections with protocols: I2C, UART, WiFi, HTTPS.\" \\\n  -o figures\u002Fiot_architecture.png\n```\n\n---\n\n## Command-Line Usage\n\nThe main entry point for generating scientific schematics:\n\n```bash\n# Basic usage\npython scripts\u002Fgenerate_schematic.py \"diagram description\" -o output.png\n\n# Custom iterations (max 2)\npython scripts\u002Fgenerate_schematic.py \"complex diagram\" -o diagram.png --iterations 2\n\n# Verbose mode\npython scripts\u002Fgenerate_schematic.py \"diagram\" -o out.png -v\n```\n\n**Note:** The Nano Banana 2 AI generation system includes automatic quality review in its iterative refinement process. Each iteration is evaluated for scientific accuracy, clarity, and accessibility.\n\n## Best Practices Summary\n\n### Design Principles\n\n1. **Clarity over complexity** - Simplify, remove unnecessary elements\n2. **Consistent styling** - Use templates and style files\n3. **Colorblind accessibility** - Use Okabe-Ito palette, redundant encoding\n4. **Appropriate typography** - Sans-serif fonts, minimum 7-8 pt\n5. **Vector format** - Always use PDF\u002FSVG for publication\n\n### Technical Requirements\n\n1. **Resolution** - Vector preferred, or 300+ DPI for raster\n2. **File format** - PDF for LaTeX, SVG for web, PNG as fallback\n3. **Color space** - RGB for digital, CMYK for print (convert if needed)\n4. **Line weights** - Minimum 0.5 pt, typical 1-2 pt\n5. **Text size** - 7-8 pt minimum at final size\n\n### Integration Guidelines\n\n1. **Include in LaTeX** - Use `\\includegraphics{}` for generated images\n2. **Caption thoroughly** - Describe all elements and abbreviations\n3. **Reference in text** - Explain diagram in narrative flow\n4. **Maintain consistency** - Same style across all figures in paper\n5. **Version control** - Keep prompts and generated images in repository\n\n## Troubleshooting Common Issues\n\n### AI Generation Issues\n\n**Problem**: Overlapping text or elements\n- **Solution**: AI generation automatically handles spacing\n- **Solution**: Increase iterations: `--iterations 2` for better refinement\n\n**Problem**: Elements not connecting properly\n- **Solution**: Make your prompt more specific about connections and layout\n- **Solution**: Increase iterations for better refinement\n\n### Image Quality Issues\n\n**Problem**: Export quality poor\n- **Solution**: AI generation produces high-quality images automatically\n- **Solution**: Increase iterations for better results: `--iterations 2`\n\n**Problem**: Elements overlap after generation\n- **Solution**: AI generation automatically handles spacing\n- **Solution**: Increase iterations: `--iterations 2` for better refinement\n- **Solution**: Make your prompt more specific about layout and spacing requirements\n\n### Quality Check Issues\n\n**Problem**: False positive overlap detection\n- **Solution**: Adjust threshold: `detect_overlaps(image_path, threshold=0.98)`\n- **Solution**: Manually review flagged regions in visual report\n\n**Problem**: Generated image quality is low\n- **Solution**: AI generation produces high-quality images by default\n- **Solution**: Increase iterations for better results: `--iterations 2`\n\n**Problem**: Colorblind simulation shows poor contrast\n- **Solution**: Switch to Okabe-Ito palette explicitly in code\n- **Solution**: Add redundant encoding (shapes, patterns, line styles)\n- **Solution**: Increase color saturation and lightness differences\n\n**Problem**: High-severity overlaps detected\n- **Solution**: Review overlap_report.json for exact positions\n- **Solution**: Increase spacing in those specific regions\n- **Solution**: Re-run with adjusted parameters and verify again\n\n**Problem**: Visual report generation fails\n- **Solution**: Check Pillow and matplotlib installations\n- **Solution**: Ensure image file is readable: `Image.open(path).verify()`\n- **Solution**: Check sufficient disk space for report generation\n\n### Accessibility Problems\n\n**Problem**: Colors indistinguishable in grayscale\n- **Solution**: Run accessibility checker: `verify_accessibility(image_path)`\n- **Solution**: Add patterns, shapes, or line styles for redundancy\n- **Solution**: Increase contrast between adjacent elements\n\n**Problem**: Text too small when printed\n- **Solution**: Run resolution validator: `validate_resolution(image_path)`\n- **Solution**: Design at final size, use minimum 7-8 pt fonts\n- **Solution**: Check physical dimensions in resolution report\n\n**Problem**: Accessibility checks consistently fail\n- **Solution**: Review accessibility_report.json for specific failures\n- **Solution**: Increase color contrast by at least 20%\n- **Solution**: Test with actual grayscale conversion before finalizing\n\n## Resources and References\n\n### Detailed References\n\nLoad these files for comprehensive information on specific topics:\n\n- **`references\u002Fbest_practices.md`** - Publication standards and accessibility guidelines\n\n### External Resources\n\n**Python Libraries**\n- Schemdraw Documentation: https:\u002F\u002Fschemdraw.readthedocs.io\u002F\n- NetworkX Documentation: https:\u002F\u002Fnetworkx.org\u002Fdocumentation\u002F\n- Matplotlib Documentation: https:\u002F\u002Fmatplotlib.org\u002F\n\n**Publication Standards**\n- Nature Figure Guidelines: https:\u002F\u002Fwww.nature.com\u002Fnature\u002Ffor-authors\u002Ffinal-submission\n- Science Figure Guidelines: https:\u002F\u002Fwww.science.org\u002Fcontent\u002Fpage\u002Finstructions-preparing-initial-manuscript\n- CONSORT Diagram: http:\u002F\u002Fwww.consort-statement.org\u002Fconsort-statement\u002Fflow-diagram\n\n## Integration with Other Skills\n\nThis skill works synergistically with:\n\n- **Scientific Writing** - Diagrams follow figure best practices\n- **Scientific Visualization** - Shares color palettes and styling\n- **LaTeX Posters** - Generate diagrams for poster presentations\n- **Research Grants** - Methodology diagrams for proposals\n- **Peer Review** - Evaluate diagram clarity and accessibility\n\n## Quick Reference Checklist\n\nBefore submitting diagrams, verify:\n\n### Visual Quality\n- [ ] High-quality image format (PNG from AI generation)\n- [ ] No overlapping elements (AI handles automatically)\n- [ ] Adequate spacing between all components (AI optimizes)\n- [ ] Clean, professional alignment\n- [ ] All arrows connect properly to intended targets\n\n### Accessibility\n- [ ] Colorblind-safe palette (Okabe-Ito) used\n- [ ] Works in grayscale (tested with accessibility checker)\n- [ ] Sufficient contrast between elements (verified)\n- [ ] Redundant encoding where appropriate (shapes + colors)\n- [ ] Colorblind simulation passes all checks\n\n### Typography and Readability\n- [ ] Text minimum 7-8 pt at final size\n- [ ] All elements labeled clearly and completely\n- [ ] Consistent font family and sizing\n- [ ] No text overlaps or cutoffs\n- [ ] Units included where applicable\n\n### Publication Standards\n- [ ] Consistent styling with other figures in manuscript\n- [ ] Comprehensive caption written with all abbreviations defined\n- [ ] Referenced appropriately in manuscript text\n- [ ] Meets journal-specific dimension requirements\n- [ ] Exported in required format for journal (PDF\u002FEPS\u002FTIFF)\n\n### Quality Verification (Required)\n- [ ] Ran `run_quality_checks()` and achieved PASS status\n- [ ] Reviewed overlap detection report (zero high-severity overlaps)\n- [ ] Passed accessibility verification (grayscale and colorblind)\n- [ ] Resolution validated at target DPI (300+ for print)\n- [ ] Visual quality report generated and reviewed\n- [ ] All quality reports saved with figure files\n\n### Documentation and Version Control\n- [ ] Source files (.tex, .py) saved for future revision\n- [ ] Quality reports archived in `quality_reports\u002F` directory\n- [ ] Configuration parameters documented (colors, spacing, sizes)\n- [ ] Git commit includes source, output, and quality reports\n- [ ] README or comments explain how to regenerate figure\n\n### Final Integration Check\n- [ ] Figure displays correctly in compiled manuscript\n- [ ] Cross-references work (`\\ref{}` points to correct figure)\n- [ ] Figure number matches text citations\n- [ ] Caption appears on correct page relative to figure\n- [ ] No compilation warnings or errors related to figure\n\n## Environment Setup\n\n```bash\n# Required\nexport OPENROUTER_API_KEY='your_api_key_here'\n\n# Get key at: https:\u002F\u002Fopenrouter.ai\u002Fkeys\n```\n\n## Getting Started\n\n**Simplest possible usage:**\n```bash\npython scripts\u002Fgenerate_schematic.py \"your diagram description\" -o output.png\n```\n\n---\n\nUse this skill to create clear, accessible, publication-quality diagrams that effectively communicate complex scientific concepts. The AI-powered workflow with iterative refinement ensures diagrams meet professional standards.\n\n\n",{"name":5,"license":48,"metadata":49,"description":7,"allowed-tools":51},"MIT license",{"skill-author":50},"K-Dense Inc.","Read Write Edit Bash","main","f19b254e8975d0bfddb394686706106930d7964d","Science\u002Fresearch-and-communication\u002Fscientific-schematics","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus","https:\u002F\u002Fgithub.com\u002Fendman100","2026-11-12 18:13:37",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add endman100\u002Fskill-router-nexus --skill scientific-schematics",{"tool":64,"command":65},"bunx","bunx skills add endman100\u002Fskill-router-nexus --skill scientific-schematics",{"tool":67,"command":68},"pnpm","pnpm dlx skills add endman100\u002Fskill-router-nexus --skill scientific-schematics","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FScience\u002Fresearch-and-communication\u002Fscientific-schematics\u002FSKILL.md",true,[72,78,82,86,92,96],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fbest_practices.md","REFERENCE","参考文档",16026,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FScience\u002Fresearch-and-communication\u002Fscientific-schematics\u002Freferences\u002Fbest_practices.md",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002FQUICK_REFERENCE.md",4784,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FScience\u002Fresearch-and-communication\u002Fscientific-schematics\u002Freferences\u002FQUICK_REFERENCE.md",{"path":83,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002FREADME.md",8676,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FScience\u002Fresearch-and-communication\u002Fscientific-schematics\u002Freferences\u002FREADME.md",{"path":87,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":90,"sourceHtmlUrl":91},"scripts\u002Fexample_usage.sh","SCRIPT","脚本",3052,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FScience\u002Fresearch-and-communication\u002Fscientific-schematics\u002Fscripts\u002Fexample_usage.sh",{"path":93,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":94,"sourceHtmlUrl":95},"scripts\u002Fgenerate_schematic_ai.py",32647,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FScience\u002Fresearch-and-communication\u002Fscientific-schematics\u002Fscripts\u002Fgenerate_schematic_ai.py",{"path":97,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":98,"sourceHtmlUrl":99},"scripts\u002Fgenerate_schematic.py",5146,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FScience\u002Fresearch-and-communication\u002Fscientific-schematics\u002Fscripts\u002Fgenerate_schematic.py",[101,121,154,177,186,210],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":105,"sourceHtmlUrl":106,"categories":107,"keywords":113,"publishedAt":43},"01M6MPCT5BXVER8HQZTW3QE9AS","create-master","基于佛教经典文献，生成特定高僧大德的 AI 教学角色","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FMetaphysics-and-Spirituality\u002FMaster-skill\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FMetaphysics-and-Spirituality\u002FMaster-skill\u002FSKILL.md",[108],{"categoryNo":109,"categoryName":110,"taxonomyType":111,"taxonomyTypeDesc":112},"01JBSEEDCAT000000000000039","教师与教育","PROFESSION","适用职业",[114,115,42,116,117,118,36,37,38,119,120],"create master","master","生成","true","webfetch","grep","Bash",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":125,"sourceHtmlUrl":126,"categories":127,"keywords":135,"publishedAt":43},"01M6M43AKE95Y64E1JRXEF5QQ3","writing-dna-skill","从至少 20 篇完整文章中蒸馏可复用的写作 DNA，分析语言、文章结构、选题逻辑、素材策略、认知框架和视觉风格，并生成 Writing-DNA.md；按该 DNA 写作时会读取全部蒸馏产物和 5 篇相关原文。用于中英文作者、账号、品牌或出版物的风格分析与一致性写作。 Distill reusable Writing DNA from at least 20 complete articles for Chinese or English authors, publications, brands, and accounts; use for language, structure, topic logic, source strategy, cognitive-frame, and visual-style analysis.","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fwriting-dna-skill\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fwriting-dna-skill\u002FSKILL.md",[128,131,132],{"categoryNo":129,"categoryName":130,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":133,"categoryName":134,"taxonomyType":111,"taxonomyTypeDesc":112},"01JBSEEDCAT000000000000036","内容创作者",[136,137,138,139,140,141,142,143,144,145,146,147,148,116,149,150,151,26,152,153],"writing dna skill","DNA","writing","strategy","english","logic","visual","structure","chinese","reusable","use","style","distill","analysis","frame","source","at","complete",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":158,"sourceHtmlUrl":159,"categories":160,"keywords":163,"publishedAt":43},"01M6M428TTCGQ4ME3KY99VN037","stop-slop","Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fstop-slop\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fstop-slop\u002FSKILL.md",[161,162],{"categoryNo":129,"categoryName":130,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":133,"categoryName":134,"taxonomyType":111,"taxonomyTypeDesc":112},[164,165,166,167,168,169,170,171,172,146,173,174,175,26,176,138],"slop","stop slop","stop","drafting","when","drafts","https","patterns","prose","remove","editing","text","content",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":181,"sourceHtmlUrl":182,"categories":183,"keywords":184,"publishedAt":43},"01M6M41X0B7EBX42TK435DMGGR","shuorenhua","检查和清理中英文文本里的 AI 套路，适用于“去 AI 味”“说人话”“自然一点”“别像模板”“先标问题”这类改写和审稿需求；按场景控制力度，同时保留事实、术语、语域和责任主体。","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fshuorenhua\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fshuorenhua\u002FSKILL.md",[],[179,185],"文本",{"skillNo":187,"name":188,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":190,"sourceHtmlUrl":191,"categories":192,"keywords":193,"publishedAt":43},"01M6M3ZD12WBEW5KXKDM4N6DFG","naming","Name products, SaaS, brands, open source projects, bots, and apps. Use when the user needs to name something, find a brand name, or pick a product name. Metaphor-driven process that produces memorable, meaningful names and avoids AI slop.","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fnaming-main\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fnaming-main\u002FSKILL.md",[],[188,194,195,196,197,198,146,199,38,151,200,201,202,203,120,204,205,206,207,168,208,209,164],"repo","websearch","product name","apps","bots","view","brand","pick","gh","projects","open","saas","open source","product","describe","ai slop",{"skillNo":211,"name":212,"nameZh":6,"description":213,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":214,"sourceHtmlUrl":215,"categories":216,"keywords":218,"publishedAt":43},"01M6M3YVXAFAAWJ7F6JMPFREYE","humanizer-zh","去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。\n基于维基百科的\"AI 写作特征\"综合指南。检测并修复以下模式：夸大的象征意义、\n宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、\nAI 词汇、否定式排比、过多的连接性短语。","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fhumanizer-zh\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FWriting-and-Content\u002Fhumanizer-zh\u002FSKILL.md",[217],{"categoryNo":129,"categoryName":130,"taxonomyType":20,"taxonomyTypeDesc":21},[219,220,221,38,37,36,138,116,185,222,164,166],"humanizer","zh","humanizer zh","翻译"]