Graphical Abstract Wizard

Source: https://github.com/aipoch/medical-research-skills

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.

When to Use

• Use this skill when the task is to Generate graphical abstract layout recommendations based on paper abstracts.
• Use this skill for data analysis tasks that require explicit assumptions, bounded scope, and a reproducible output format.
• Use this skill when you need a documented fallback path for missing inputs, execution errors, or partial evidence.

Key Features

• Scope-focused workflow aligned to: Generate graphical abstract layout recommendations based on paper abstracts.
• Packaged executable path(s): scripts/main.py.
• Structured execution path designed to keep outputs consistent and reviewable.

Dependencies

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

Example Usage

See ## Usage above for related details.

cd "20260318/scientific-skills/Data Analytics/graphical-abstract-wizard"
python -m py_compile scripts/main.py
python scripts/main.py --help

Example run plan:

1. Confirm the user input, output path, and any required config values.
2. Edit the in-file CONFIG block or documented parameters if the script uses fixed settings.
3. Run python scripts/main.py with the validated inputs.
4. Review the generated output and return the final artifact with any assumptions called out.

Implementation Details

See ## Workflow above for related details.

• Execution model: validate the request, choose the packaged workflow, and produce a bounded deliverable.
• Input controls: confirm the source files, scope limits, output format, and acceptance criteria before running any script.
• Primary implementation surface: scripts/main.py.
• Parameters to clarify first: input path, output path, scope filters, thresholds, and any domain-specific constraints.
• Output discipline: keep results reproducible, identify assumptions explicitly, and avoid undocumented side effects.

Quick Check

Use this command to verify that the packaged script entry point can be parsed before deeper execution.

python -m py_compile scripts/main.py

Audit-Ready Commands

Use these concrete commands for validation. They are intentionally self-contained and avoid placeholder paths.

python -m py_compile scripts/main.py
python scripts/main.py --help

Workflow

1. Confirm the user objective, required inputs, and non-negotiable constraints before doing detailed work.
2. Validate that the request matches the documented scope and stop early if the task would require unsupported assumptions.
3. Use the packaged script path or the documented reasoning path with only the inputs that are actually available.
4. Return a structured result that separates assumptions, deliverables, risks, and unresolved items.
5. If execution fails or inputs are incomplete, switch to the fallback path and state exactly what blocked full completion.

Usage

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

Or from stdin:

cat abstract.txt | python scripts/main.py

Parameters

*Required if not providing input via stdin

Examples

Example 1: Basic Usage

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

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

Example 3: JSON Output for Integration

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

# 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 │ │ 📥 │ ⚙️ │ 📈 │ └──────────┴──────────┴───────────┘

## 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

### 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.