make-figures

Name: make-figures
Author: Aperivue

45installs53forks

How to install make-figures?

aperivue/medsci-skills/make-figures

$npx -y skills add Aperivue/medsci-skills --skill make-figures

Installs into the current project.

Summary

Generate publication-ready figures and visual abstracts for medical research papers. Supports ROC curves, forest plots, CONSORT/STARD/PRISMA flow diagrams, calibration plots, Kaplan-Meier curves, Bland-Altman plots, confusion matrices, pipeline diagrams, and journal-specific visu

Files · 1

View on GitHub

SKILL.md

1	# Make-Figures Skill
2
3	You are helping a medical researcher generate publication-ready figures for medical research
4	manuscripts. Every figure must meet journal specifications for dimensions, resolution, fonts, and
5	color accessibility. Produce clean, data-focused visuals with no chartjunk.
6
7	## Credits
8
9	The Critic Loop (Step 4b) in this skill is inspired by PaperBanana (Zhu et al., *Automating
10	Academic Illustration for AI Scientists*, arXiv:2601.23265, 2025) and by prior self-refinement
11	research — Self-Refine (Madaan et al., 2023), Reflexion (Shinn et al., 2023), and Constitutional
12	AI (Anthropic, 2022). This is a clean-room reconstruction specialized for medical publication
13	figures (STARD / CONSORT / PRISMA, journal-specific specs, Wong colorblind palette). No code,
14	prompts, or configurations are derived from PaperBanana's repository.
15
16	## Communication Rules
17
18	- Communicate with the user in their preferred language.
19	- All figure text (labels, legends, annotations) must be in English.
20	- Medical terminology is always in English.
21
22	## Data Privacy Check
23
24	Before reading any data file, check whether it might contain Protected Health Information (PHI):
25
26	1. If `_deidentified.` files exist in the working directory, use those preferentially.
27	2. If only raw CSV/Excel files exist (no `_deidentified.` counterpart), warn the user (ask in the user's preferred language):
28	> "Does this data contain patient identifiers (names, national ID / RRN, contact details, etc.)?
29	> If so, please de-identify it first with the `/deidentify` skill."
30	3. If the user confirms the data is already de-identified or contains no PHI, proceed.
31
32	## Reference Files
33
34	- Figure specifications: `${CLAUDE_SKILL_DIR}/references/figure_specs.md`
35	- Figure style: `${CLAUDE_SKILL_DIR}/../analyze-stats/references/style/figure_style.mplstyle` (or project's CLAUDE.md if available)
36	- Project data: See CLAUDE.md for data locations under `2_Data/`
37
38	Read `figure_specs.md` before generating any figure to confirm journal-specific requirements.
39
40	---
41
42	## Journal AI-Image Policies (CRITICAL — check BEFORE generation)
43
44	> Synced with the user's global rule `~/.claude/rules/journal-ai-image-policies.md`. The table below is the local copy used during autonomous workflow; the global rule is authoritative when conflicts arise.
45
46
47	\| Journal family \| Policy on AI-generated images \| Disclosure required \|
48	\|---\|---\|---\|
49	\| JACC family (incl. JACC: Asia, JACC Imaging, JACC EP, JACC BTS) \| Prohibited without prior Editor-in-Chief permission ([JACC pathway, PMC10167500](https://pmc.ncbi.nlm.nih.gov/articles/PMC10167500/)) \| Cover-letter pre-submission inquiry + ICMJE-style declaration \|
50	\| NEJM \| AI image generation prohibited \| N/A \|
51	\| Radiology / Radiology AI \| Allowed with disclosure \| Manuscript disclosure block \|
52	\| Nature family \| Allowed with disclosure + license check \| Methods + figure legend \|
53	\| Lancet family \| Disclosure required, generation discouraged \| Manuscript disclosure \|
54	\| Default (target unknown) \| Treat as prohibited until confirmed \| N/A \|
55
56	Hard rule: For JACC, NEJM, or any "unknown" target journal, never use Gemini / DALL-E / Midjourney / Stable Diffusion / Nano Banana to create images that will appear in figures, Central Illustrations, or graphical abstracts. AI text-editing of the manuscript prose remains acceptable subject to standard disclosure.
57
58	### Default workflow when AI images are not allowed
59
60	1. SMART Servier Medical Art — https://smart.servier.com/, CC BY 4.0, free, 3,000+ vector medical icons (anatomy, organs, ethnicity-specific human figures, drugs, devices). Commercial / journal use allowed. Required attribution (1 line in figure legend OR methods):
61	> Anatomical icons modified from SMART Servier Medical Art (CC BY 4.0).
62	2. NIAID BioArt (https://bioart.niaid.nih.gov) — public domain (US Govt), microbiology / immunology / lab-tech focus.
63	3. BioRender (https://www.biorender.com) — institutional license usually required; use the exported "Publication-ready" PNG/TIFF and cite per BioRender publication policy.
64	4. For "diseased" variants not directly available (e.g., calcified vessel from a clean vessel): reuse the healthy asset and overlay disease markers via matplotlib `scatter` / `Circle` / `PathPatch`. Keeps the entire pipeline non-AI and r

People who liked this also viewed

6 picks

Type

make-figures

45installs53forks

View on GitHub

How to install make-figures?

aperivue/medsci-skills/make-figures

$npx -y skills add Aperivue/medsci-skills --skill make-figures

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Make-Figures Skill
2
3	You are helping a medical researcher generate publication-ready figures for medical research
4	manuscripts. Every figure must meet journal specifications for dimensions, resolution, fonts, and
5	color accessibility. Produce clean, data-focused visuals with no chartjunk.
6
7	## Credits
8
9	The Critic Loop (Step 4b) in this skill is inspired by PaperBanana (Zhu et al., *Automating
10	Academic Illustration for AI Scientists*, arXiv:2601.23265, 2025) and by prior self-refinement
11	research — Self-Refine (Madaan et al., 2023), Reflexion (Shinn et al., 2023), and Constitutional
12	AI (Anthropic, 2022). This is a clean-room reconstruction specialized for medical publication
13	figures (STARD / CONSORT / PRISMA, journal-specific specs, Wong colorblind palette). No code,
14	prompts, or configurations are derived from PaperBanana's repository.
15
16	## Communication Rules
17
18	- Communicate with the user in their preferred language.
19	- All figure text (labels, legends, annotations) must be in English.
20	- Medical terminology is always in English.
21
22	## Data Privacy Check
23
24	Before reading any data file, check whether it might contain Protected Health Information (PHI):
25
26	1. If `_deidentified.` files exist in the working directory, use those preferentially.
27	2. If only raw CSV/Excel files exist (no `_deidentified.` counterpart), warn the user (ask in the user's preferred language):
28	> "Does this data contain patient identifiers (names, national ID / RRN, contact details, etc.)?
29	> If so, please de-identify it first with the `/deidentify` skill."
30	3. If the user confirms the data is already de-identified or contains no PHI, proceed.
31
32	## Reference Files
33
34	- Figure specifications: `${CLAUDE_SKILL_DIR}/references/figure_specs.md`
35	- Figure style: `${CLAUDE_SKILL_DIR}/../analyze-stats/references/style/figure_style.mplstyle` (or project's CLAUDE.md if available)
36	- Project data: See CLAUDE.md for data locations under `2_Data/`
37
38	Read `figure_specs.md` before generating any figure to confirm journal-specific requirements.
39
40	---
41
42	## Journal AI-Image Policies (CRITICAL — check BEFORE generation)
43
44	> Synced with the user's global rule `~/.claude/rules/journal-ai-image-policies.md`. The table below is the local copy used during autonomous workflow; the global rule is authoritative when conflicts arise.
45
46
47	\| Journal family \| Policy on AI-generated images \| Disclosure required \|
48	\|---\|---\|---\|
49	\| JACC family (incl. JACC: Asia, JACC Imaging, JACC EP, JACC BTS) \| Prohibited without prior Editor-in-Chief permission ([JACC pathway, PMC10167500](https://pmc.ncbi.nlm.nih.gov/articles/PMC10167500/)) \| Cover-letter pre-submission inquiry + ICMJE-style declaration \|
50	\| NEJM \| AI image generation prohibited \| N/A \|
51	\| Radiology / Radiology AI \| Allowed with disclosure \| Manuscript disclosure block \|
52	\| Nature family \| Allowed with disclosure + license check \| Methods + figure legend \|
53	\| Lancet family \| Disclosure required, generation discouraged \| Manuscript disclosure \|
54	\| Default (target unknown) \| Treat as prohibited until confirmed \| N/A \|
55
56	Hard rule: For JACC, NEJM, or any "unknown" target journal, never use Gemini / DALL-E / Midjourney / Stable Diffusion / Nano Banana to create images that will appear in figures, Central Illustrations, or graphical abstracts. AI text-editing of the manuscript prose remains acceptable subject to standard disclosure.
57
58	### Default workflow when AI images are not allowed
59
60	1. SMART Servier Medical Art — https://smart.servier.com/, CC BY 4.0, free, 3,000+ vector medical icons (anatomy, organs, ethnicity-specific human figures, drugs, devices). Commercial / journal use allowed. Required attribution (1 line in figure legend OR methods):
61	> Anatomical icons modified from SMART Servier Medical Art (CC BY 4.0).
62	2. NIAID BioArt (https://bioart.niaid.nih.gov) — public domain (US Govt), microbiology / immunology / lab-tech focus.
63	3. BioRender (https://www.biorender.com) — institutional license usually required; use the exported "Publication-ready" PNG/TIFF and cite per BioRender publication policy.
64	4. For "diseased" variants not directly available (e.g., calcified vessel from a clean vessel): reuse the healthy asset and overlay disease markers via matplotlib `scatter` / `Circle` / `PathPatch`. Keeps the entire pipeline non-AI and r

People who liked this also viewed

6 picks

Type