Figure

Skill richard-kim-79/archora-skills/skills/figure

Academic research agent skills for Claude Code and other Agent Skills-compatible tools. Hypothesis generation, experiment design, paper drafting, peer review simulation, and more.

Install

npx -y skills add richard-kim-79/archora-skills --skill figure

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.

What its author says it does

Copied from the file, not written here

Generates complete, runnable visualization code for research figures. Produces matplotlib/seaborn Python scripts for quantitative data and Mermaid diagrams for conceptual relationships, workflows, and taxonomies. Use when the user asks for charts, graphs, visualizations, figures, or diagrams. Produces code only — does not render images directly.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.9 KB, as published. Nobody here has run it

Figure Generator

Generate publication-quality visualization code for research figures.

Figure Types

Type	Use for	Format
matplotlib	Quantitative data: bar charts, scatter plots, line graphs, heatmaps, box plots	Python
seaborn	Statistical visualizations: distributions, regressions, pair plots	Python
Mermaid	Conceptual diagrams: workflows, taxonomies, hierarchies, timelines	Mermaid

Decision guide

Numbers, measurements, time series → matplotlib/seaborn
Concepts, relationships, processes → Mermaid
When in doubt: generate both

Output Format

## Figure 1: [Title]

**Caption:** [Full figure caption as it would appear in a paper — what is shown and the key takeaway]

**Description:** [What this figure shows and why it matters for the research]

**Type:** Python (matplotlib/seaborn)

```python
import matplotlib.pyplot as plt
import numpy as np

# [Complete, runnable code with realistic placeholder data]
plt.tight_layout()
plt.savefig('figure1.png', dpi=300)
plt.show()
```

Code requirements

Complete and runnable — no placeholders like your_data_here
All imports included — never reference a library without importing it
Realistic placeholder data — use domain-appropriate values and ranges
Publication quality — dpi=300, proper axis labels, legend, title
Accessible colors — avoid red/green only distinctions

Validation (always run after generating Python code)

Before presenting code to the user, validate syntax with Python's AST parser:

python -c "import ast; ast.parse(open('figure1.py').read()); print('✅ Syntax OK')"

If the check fails, fix the syntax error and re-validate before showing the result.

For inline code blocks, validate with:

import ast
code = """
# paste generated code here
"""
try:
    ast.parse(code)
    print("✅ Syntax OK")
except SyntaxError as e:
    print(f"❌ Syntax error: {e}")

Note: AST validation checks syntax only — it does not catch runtime errors (e.g. wrong data shapes). Always include comments explaining how to adapt placeholder data to real data.

How to run

Python figures:

pip install matplotlib seaborn numpy
python figure1.py

Mermaid diagrams:

Paste into mermaid.live
Or use any Markdown renderer that supports Mermaid (Obsidian, GitHub, etc.)