Graphical Abstract Wizard#

This Skill analyzes academic paper abstracts and generates graphical abstract layout recommendations, including element suggestions, visual arrangements, and AI art prompts for Midjourney and DALL-E.

Usage#

bash

python scripts/main.py --abstract "Your paper abstract text here"

Or from stdin:

bash

cat abstract.txt | python scripts/main.py

Parameters#

ParameterTypeRequiredDescription--abstract / -astringYes*The paper abstract text to analyze--style / -sstringNoVisual style preference (scientific/minimal/colorful/sketch)--format / -fstringNoOutput format (json/markdown/text), default: markdown--output / -ostringNoOutput file path (default: stdout)

*Required if not providing input via stdin

Examples#

Example 1: Basic Usage#

bash

python scripts/main.py -a "We propose a novel deep learning approach for protein structure prediction that combines transformer architectures with geometric constraints. Our method achieves state-of-the-art accuracy on CASP14 benchmarks."

Example 2: With Style Preference#

bash

python scripts/main.py -a "abstract.txt" -s scientific -o layout.md

Example 3: JSON Output for Integration#

bash

python scripts/main.py -a "$(cat abstract.txt)" -f json > result.json

Output Format#

The Skill produces a structured analysis including:

1. Key Concepts Extracted#

• Core research topic
• Methods/techniques used
• Key findings/results
• Implications

2. Visual Element Recommendations#

• Recommended icons/symbols
• Color palette suggestions
• Layout structure

3. AI Art Prompts#

• Midjourney Prompt: Optimized for Midjourney v6
• DALL-E Prompt: Optimized for DALL-E 3

4. Layout Blueprint#

• Grid-based layout suggestion
• Element positioning
• Flow direction

Example Output#

markdown

# Graphical Abstract Recommendation

## Abstract Summary
**Topic**: Deep learning protein structure prediction
**Method**: Transformer + Geometric constraints
**Result**: State-of-the-art CASP14 accuracy

## Key Concepts
- 🧬 Protein structures
- 🤖 Neural networks
- 📊 Accuracy metrics

## Visual Elements
| Element | Symbol | Position | Color |
|---------|--------|----------|-------|
| Core Concept | Brain + DNA | Center | Blue |
| Method | Neural Network | Left | Purple |
| Result | Trophy/Chart | Right | Gold |

## Layout Suggestion

┌─────────────────────────────────┐ │ [Title/Concept] │ │ 🧬🤖 │ ├──────────┬──────────┬───────────┤ │ Input │ Process │ Output │ │ 📥 │ ⚙️ │ 📈 │ └──────────┴──────────┴───────────┘

text

## AI Art Prompts

### Midjourney

Scientific graphical abstract, protein structure prediction with neural networks, 3D molecular structures connected by glowing neural network nodes, blue and purple gradient background, clean minimalist style, academic journal style, high quality --ar 16:9 --v 6

text

### DALL-E

A clean scientific illustration for a research paper about protein structure prediction using deep learning. Show a 3D protein structure in the center surrounded by abstract neural network connections. Use a professional blue and white color scheme with subtle gradients. Include geometric shapes representing data flow. Modern, minimalist academic style suitable for a Nature or Science journal cover.

text

Technical Details#

The Skill uses NLP techniques to:

1. Extract named entities (methods, materials, concepts)
2. Identify research actions and outcomes
3. Map concepts to visual representations
4. Generate style-appropriate prompts

Dependencies#

• Python 3.8+
• OpenAI API (optional, for enhanced analysis)
• Standard library: re, json, argparse, sys

License#

MIT License - Part of OpenClaw Skills Collection

Risk Assessment#

Risk IndicatorAssessmentLevelCode ExecutionPython/R scripts executed locallyMediumNetwork AccessNo external API callsLowFile System AccessRead input files, write output filesMediumInstruction TamperingStandard prompt guidelinesLowData ExposureOutput files saved to workspaceLow

Security Checklist#

• No hardcoded credentials or API keys
• No unauthorized file system access (../)
• Output does not expose sensitive information
• Prompt injection protections in place
• Input file paths validated (no ../ traversal)
• Output directory restricted to workspace
• Script execution in sandboxed environment
• Error messages sanitized (no stack traces exposed)
• Dependencies audited

Prerequisites#

bash

# Python dependencies
pip install -r requirements.txt

Evaluation Criteria#

Success Metrics#

• Successfully executes main functionality
• Output meets quality standards
• Handles edge cases gracefully
• Performance is acceptable

Test Cases#

1. Basic Functionality: Standard input → Expected output
2. Edge Case: Invalid input → Graceful error handling
3. Performance: Large dataset → Acceptable processing time

Lifecycle Status#

• Current Stage: Draft

• Next Review Date: 2026-03-06

• Known Issues: None

• Planned Improvements:

  • Performance optimization
  • Additional feature support