What inputs are required?

Path to the chart image (--input) and the chart type (--type); optional --output, --format, and --language; by default outputs structured markdown to stdout.

What formats and languages are supported?

Default output is markdown; can switch to text or latex using --format; language defaults to English but can be set to zh.

Does it generate visuals or only text legends?

Only text legends are produced; no images are rendered; the tool focuses on legend structure and content.

figure-legend-gen

Research

npx machina-cli add skill aipoch/medical-research-skills/figure-legend-gen --openclaw

Files (1)

SKILL.md

4.2 KB

Figure Legend Generator

Generate publication-quality figure legends for scientific research charts and images.

Supported Chart Types

Chart Type	Description
Bar Chart	Compare values across categories
Line Graph	Show trends over time or continuous data
Scatter Plot	Display relationships between variables
Box Plot	Show distribution and outliers
Heatmap	Display matrix data intensity
Microscopy	Fluorescence/confocal images
Flow Cytometry	FACS plots and histograms
Western Blot	Protein expression bands

Usage

python scripts/main.py --input <image_path> --type <chart_type> [--output <output_path>]

Parameters

Parameter	Required	Description
`--input`	Yes	Path to chart image
`--type`	Yes	Chart type (bar/line/scatter/box/heatmap/microscopy/flow/western)
`--output`	No	Output path for legend text (default: stdout)
`--format`	No	Output format (text/markdown/latex), default: markdown
`--language`	No	Language (en/zh), default: en

Examples

# Generate legend for bar chart
python scripts/main.py --input figure1.png --type bar

# Save to file
python scripts/main.py --input plot.jpg --type line --output legend.md

# Chinese output
python scripts/main.py --image.png --type scatter --language zh

Legend Structure

Generated legends follow academic standards:

Figure Number - Sequential numbering
Brief Title - Concise description
Main Description - What the figure shows
Data Details - Key statistics/measurements
Methodology - Brief experimental context
Statistics - P-values, significance markers
Scale Bars - For microscopy images

Technical Notes

Difficulty: Low
Dependencies: PIL, pytesseract (optional OCR)
Processing: Vision analysis for chart type detection
Output: Structured markdown by default

References

references/legend_templates.md - Templates by chart type
references/academic_style_guide.md - Formatting guidelines

Risk Assessment

Risk Indicator	Assessment	Level
Code Execution	Python scripts with tools	High
Network Access	External API calls	High
File System Access	Read/write data	Medium
Instruction Tampering	Standard prompt guidelines	Low
Data Exposure	Data handled securely	Medium

Security Checklist

Prerequisites

# 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

Basic Functionality: Standard input → Expected output
Edge Case: Invalid input → Graceful error handling
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

Source

git clone https://github.com/aipoch/medical-research-skills/blob/main/scientific-skills/Academic writing/figure-legend-gen/SKILL.md

View on GitHub

Overview

Figure-legend-gen creates publication-quality captions for scientific charts and images from an input figure and specified chart type. It supports bar charts, line graphs, scatter plots, box plots, heatmaps, microscopy images, flow cytometry, and Western blots, and outputs text legends (not visualizations) in a consistent, publication-ready structure.

How This Skill Works

The tool uses vision analysis to detect the chart type from the input image and assembles a legend in a seven-section structure: Figure Number, Brief Title, Main Description, Data Details, Methodology, Statistics, and Scale Bars. Output is structured markdown by default, with optional format and language settings; it relies on PIL and can use pytesseract for OCR when needed.

When to Use It

Preparing manuscript figure legends for a submitted or published paper.
Standardizing captions across a batch of related figures in a study.
Captioning microscopy images with scale bars and fluorescence details.
Documenting flow cytometry plots or Western blots with statistics.
Generating language-adapted legends for multilingual manuscripts.

Quick Start

Step 1: Run the tool with --input <image_path> --type <chart_type>.
Step 2: (Optional) Specify --output, --format, and --language as needed.
Step 3: Paste or save the generated legend and integrate into your manuscript.

Best Practices

Provide a high-resolution input image of the chart or figure.
Select the correct chart type (--type) to improve legend accuracy.
Review Data Details and Statistics sections for accuracy and include key metrics.
Keep the legend self-contained with sufficient context for readers.
Use the Legend Structure checklist (Figure Number, Brief Title, Main Description, Data Details, Methodology, Statistics, Scale Bars) when editing.

Example Use Cases

Bar chart comparing patient groups in a clinical trial.
Heatmap showing gene expression across samples.
Fluorescence microscopy image with a scale bar and nuclei staining.
Flow cytometry histogram illustrating marker distribution.
Western blot panel with protein bands and quantified intensities.