food-figure

Name: food-figure
Author: PangenomeAI

16stars1forks

How to install food-figure?

pangenomeai/academic-skills-food-nutrition/food-figure

$npx -y skills add PangenomeAI/academic-skills-food-nutrition --skill food-figure

Installs into the current project.

Summary

Comprehensive figure system for food & nutrition manuscripts: analyzes the user's data, recommends the best figure(s) to make, then produces submission-grade graphics in Python or R at the target journal's spec. Handles all common scientific figure types (bar/box/violin, line/kin

Files · 1

View on GitHub

SKILL.md

1	# Food-Figure — Data-Driven Figure System for Food & Nutrition Science
2
3	Turn a dataset (or a described result) into the right submission-grade figure.
4	**The chart serves the scientific logic; polish is subordinate to making the
5	core conclusion clear, defensible, and reviewable.** Original work; architecture
6	informed by open community figure skills (see the repo README Acknowledgements).
7
8	Load reference files as needed (progressive disclosure) — don't read them all
9	up front. The map is in the frontmatter `references` list.
10
11	## Workflow
12
13	```mermaid
14	flowchart TD
15	A[Data or described result] --> B[1. Analyze the data<br/>scripts/analyze_data.py -> profile]
16	B --> C[2. Recommend figures<br/>references/data-to-figure.md]
17	C --> D[3. Figure contract<br/>references/figure-contract.md]
18	D --> E{Backend?}
19	E -- unknown --> Eq[Ask 'Python or R?' once<br/>scripts/backend_pref.py]
20	E -- known --> F
21	Eq --> F[4. Render<br/>python-guide.md OR r-guide.md + food-recipes.md]
22	F --> G[5. Export at journal spec<br/>references/journal-specs.md]
23	G --> H[6. QA<br/>references/qa-checklist.md]
24	H --> OUT[Journal-ready SVG/PDF/TIFF + editable source]
25	```
26
27	### 1 — Analyze the data
28	If the user supplies a data file (CSV/TSV/Excel) or table, profile it first:
29	run `scripts/analyze_data.py <file>` to get, per column, the type
30	(numeric/categorical/datetime), cardinality, missingness, distribution summary,
31	and the detected structure (grouping factors, repeated measures, time/dose axis,
32	wide sensory/composition matrix). If the user only describes a result, elicit the
33	same: what varies, what's measured, n, and the error type. See
34	`references/data-to-figure.md`.
35
36	### 2 — Recommend the figure(s)
37	From the profile, propose the best figure type(s) with a one-line rationale
38	each, and say what each would show. Prefer the figure that makes the paper's
39	claim most directly; note honest alternatives. The decision rules and a full
40	catalog are in `references/data-to-figure.md` and `references/chart-types.md`.
41	Never force a chart the data can't support (e.g. bar-of-means where a
42	distribution matters → box/violin + points).
43
44	### 3 — Figure contract + provenance (before code)
45	Fix the conclusion, evidence logic, export needs (target journal), and review
46	risks (`references/figure-contract.md`). Open a figure trace card
47	(`references/figure-provenance.md`): the real data source, the script that makes
48	the figure, what it shows, and the claim it supports — so the plotted values match
49	the reported statistics. Choose the palette by data type
50	(`references/color-palettes.md`).
51
52	For a dense Figure 1/2-style request, first design the complete evidence story
53	with `references/figure-story-design.md`: experimental sequence, evidence
54	hierarchy, non-redundant panel questions, source-data map, opening schematic, and
55	an integrated synthesis panel. Do not start by filling a grid with chart types.
56
57	### 4 — Backend gate (blocking)
58	- Data figures → Python or R (always). Resolve the backend by priority:
59	explicit request → language of the user's input files/data → saved preference
60	(`python scripts/backend_pref.py get`) → ask once ("Python or R? I'll remember
61	this") and save it (`backend_pref.py set python\|r`). The chosen backend does
62	all data graphics,

People who liked this also viewed

6 picks

Type

food-figure

16stars1forks

View on GitHub

How to install food-figure?

pangenomeai/academic-skills-food-nutrition/food-figure

$npx -y skills add PangenomeAI/academic-skills-food-nutrition --skill food-figure

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Food-Figure — Data-Driven Figure System for Food & Nutrition Science
2
3	Turn a dataset (or a described result) into the right submission-grade figure.
4	**The chart serves the scientific logic; polish is subordinate to making the
5	core conclusion clear, defensible, and reviewable.** Original work; architecture
6	informed by open community figure skills (see the repo README Acknowledgements).
7
8	Load reference files as needed (progressive disclosure) — don't read them all
9	up front. The map is in the frontmatter `references` list.
10
11	## Workflow
12
13	```mermaid
14	flowchart TD
15	A[Data or described result] --> B[1. Analyze the data<br/>scripts/analyze_data.py -> profile]
16	B --> C[2. Recommend figures<br/>references/data-to-figure.md]
17	C --> D[3. Figure contract<br/>references/figure-contract.md]
18	D --> E{Backend?}
19	E -- unknown --> Eq[Ask 'Python or R?' once<br/>scripts/backend_pref.py]
20	E -- known --> F
21	Eq --> F[4. Render<br/>python-guide.md OR r-guide.md + food-recipes.md]
22	F --> G[5. Export at journal spec<br/>references/journal-specs.md]
23	G --> H[6. QA<br/>references/qa-checklist.md]
24	H --> OUT[Journal-ready SVG/PDF/TIFF + editable source]
25	```
26
27	### 1 — Analyze the data
28	If the user supplies a data file (CSV/TSV/Excel) or table, profile it first:
29	run `scripts/analyze_data.py <file>` to get, per column, the type
30	(numeric/categorical/datetime), cardinality, missingness, distribution summary,
31	and the detected structure (grouping factors, repeated measures, time/dose axis,
32	wide sensory/composition matrix). If the user only describes a result, elicit the
33	same: what varies, what's measured, n, and the error type. See
34	`references/data-to-figure.md`.
35
36	### 2 — Recommend the figure(s)
37	From the profile, propose the best figure type(s) with a one-line rationale
38	each, and say what each would show. Prefer the figure that makes the paper's
39	claim most directly; note honest alternatives. The decision rules and a full
40	catalog are in `references/data-to-figure.md` and `references/chart-types.md`.
41	Never force a chart the data can't support (e.g. bar-of-means where a
42	distribution matters → box/violin + points).
43
44	### 3 — Figure contract + provenance (before code)
45	Fix the conclusion, evidence logic, export needs (target journal), and review
46	risks (`references/figure-contract.md`). Open a figure trace card
47	(`references/figure-provenance.md`): the real data source, the script that makes
48	the figure, what it shows, and the claim it supports — so the plotted values match
49	the reported statistics. Choose the palette by data type
50	(`references/color-palettes.md`).
51
52	For a dense Figure 1/2-style request, first design the complete evidence story
53	with `references/figure-story-design.md`: experimental sequence, evidence
54	hierarchy, non-redundant panel questions, source-data map, opening schematic, and
55	an integrated synthesis panel. Do not start by filling a grid with chart types.
56
57	### 4 — Backend gate (blocking)
58	- Data figures → Python or R (always). Resolve the backend by priority:
59	explicit request → language of the user's input files/data → saved preference
60	(`python scripts/backend_pref.py get`) → ask once ("Python or R? I'll remember
61	this") and save it (`backend_pref.py set python\|r`). The chosen backend does
62	all data graphics,

People who liked this also viewed

6 picks

Type