figure

Name: figure
Author: richard-kim-79

44stars10forks

How to install figure?

richard-kim-79/archora-skills/figure

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

Installs into the current project.

Summary

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,

Files · 1

View on GitHub

SKILL.md

1	# Figure Generator
2
3	Generate publication-quality visualization code for research figures.
4
5	## Figure Types
6
7	\| Type \| Use for \| Format \|
8	\|------\|---------\|--------\|
9	\| matplotlib \| Quantitative data: bar charts, scatter plots, line graphs, heatmaps, box plots \| Python \|
10	\| seaborn \| Statistical visualizations: distributions, regressions, pair plots \| Python \|
11	\| Mermaid \| Conceptual diagrams: workflows, taxonomies, hierarchies, timelines \| Mermaid \|
12
13	## Decision guide
14
15	- Numbers, measurements, time series → matplotlib/seaborn
16	- Concepts, relationships, processes → Mermaid
17	- When in doubt: generate both
18
19	## Output Format
20
21	````markdown
22	## Figure 1: [Title]
23
24	Caption: [Full figure caption as it would appear in a paper — what is shown and the key takeaway]
25
26	Description: [What this figure shows and why it matters for the research]
27
28	Type: Python (matplotlib/seaborn)
29
30	```python
31	import matplotlib.pyplot as plt
32	import numpy as np
33
34	# [Complete, runnable code with realistic placeholder data]
35	plt.tight_layout()
36	plt.savefig('figure1.png', dpi=300)
37	plt.show()
38	```
39	````
40
41	## Code requirements
42
43	- Complete and runnable — no placeholders like `your_data_here`
44	- All imports included — never reference a library without importing it
45	- Realistic placeholder data — use domain-appropriate values and ranges
46	- Publication quality — `dpi=300`, proper axis labels, legend, title
47	- Accessible colors — avoid red/green only distinctions
48
49	## Validation (always run after generating Python code)
50
51	Before presenting code to the user, validate syntax with Python's AST parser:
52
53	```bash
54	python -c "import ast; ast.parse(open('figure1.py').read()); print('✅ Syntax OK')"
55	```
56
57	If the check fails, fix the syntax error and re-validate before showing the result.
58
59	For inline code blocks, validate with:
60	```python
61	import ast
62	code = """
63	# paste generated code here
64	"""
65	try:
66	ast.parse(code)
67	print("✅ Syntax OK")
68	except SyntaxError as e:
69	print(f"❌ Syntax error: {e}")
70	```
71
72	> 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.
73
74	## How to run
75
76	Python figures:
77	```bash
78	pip install matplotlib seaborn numpy
79	python figure1.py
80	```
81
82	Mermaid diagrams:
83	- Paste into [mermaid.live](https://mermaid.live)
84	- Or use any Markdown renderer that supports Mermaid (Obsidian, GitHub, etc.)

People who liked this also viewed

6 picks

Type

figure

44stars10forks

View on GitHub

How to install figure?

richard-kim-79/archora-skills/figure

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Figure Generator
2
3	Generate publication-quality visualization code for research figures.
4
5	## Figure Types
6
7	\| Type \| Use for \| Format \|
8	\|------\|---------\|--------\|
9	\| matplotlib \| Quantitative data: bar charts, scatter plots, line graphs, heatmaps, box plots \| Python \|
10	\| seaborn \| Statistical visualizations: distributions, regressions, pair plots \| Python \|
11	\| Mermaid \| Conceptual diagrams: workflows, taxonomies, hierarchies, timelines \| Mermaid \|
12
13	## Decision guide
14
15	- Numbers, measurements, time series → matplotlib/seaborn
16	- Concepts, relationships, processes → Mermaid
17	- When in doubt: generate both
18
19	## Output Format
20
21	````markdown
22	## Figure 1: [Title]
23
24	Caption: [Full figure caption as it would appear in a paper — what is shown and the key takeaway]
25
26	Description: [What this figure shows and why it matters for the research]
27
28	Type: Python (matplotlib/seaborn)
29
30	```python
31	import matplotlib.pyplot as plt
32	import numpy as np
33
34	# [Complete, runnable code with realistic placeholder data]
35	plt.tight_layout()
36	plt.savefig('figure1.png', dpi=300)
37	plt.show()
38	```
39	````
40
41	## Code requirements
42
43	- Complete and runnable — no placeholders like `your_data_here`
44	- All imports included — never reference a library without importing it
45	- Realistic placeholder data — use domain-appropriate values and ranges
46	- Publication quality — `dpi=300`, proper axis labels, legend, title
47	- Accessible colors — avoid red/green only distinctions
48
49	## Validation (always run after generating Python code)
50
51	Before presenting code to the user, validate syntax with Python's AST parser:
52
53	```bash
54	python -c "import ast; ast.parse(open('figure1.py').read()); print('✅ Syntax OK')"
55	```
56
57	If the check fails, fix the syntax error and re-validate before showing the result.
58
59	For inline code blocks, validate with:
60	```python
61	import ast
62	code = """
63	# paste generated code here
64	"""
65	try:
66	ast.parse(code)
67	print("✅ Syntax OK")
68	except SyntaxError as e:
69	print(f"❌ Syntax error: {e}")
70	```
71
72	> 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.
73
74	## How to run
75
76	Python figures:
77	```bash
78	pip install matplotlib seaborn numpy
79	python figure1.py
80	```
81
82	Mermaid diagrams:
83	- Paste into [mermaid.live](https://mermaid.live)
84	- Or use any Markdown renderer that supports Mermaid (Obsidian, GitHub, etc.)

People who liked this also viewed

6 picks

Type