What is scientific-figure?

A workflow for assembling scientific figures, such as charts and diagrams, into publication-ready multi-panel images. It places panels at exact journal dimensions and checks that text remains large enough to read.

Use it to compose panels made with tools such as Matplotlib or Seaborn, validate font sizes, and export PDF or PNG figures.

It prevents layout changes and unreadably small labels when a figure is exported or resized for a journal.

scientific-figure — Skill for Claude Code by neuromechanist

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add neuromechanist/research-skills --skill scientific-figure

Clone the repo

git clone --depth 1 https://github.com/neuromechanist/research-skills

Made for: Claude Code.

Or install figures, the plugin that ships this one along with the rest of its 7 skills, 1 agent.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/neuromechanist/research-skills/scientific-figure/github.svg)](https://agentmods.dev/skills/neuromechanist/research-skills/scientific-figure)

Your own site

<a href="https://agentmods.dev/skills/neuromechanist/research-skills/scientific-figure"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/scientific-figure/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/neuromechanist/research-skills/scientific-figure"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/scientific-figure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 184 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,325 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Privilege Escalation · line 165
Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00184	$0.02325
Opus 5	$0.00092	$0.01162
Sonnet 5	$0.00037	$0.00465
Haiku 4.5	$0.00018	$0.00232

Measured 12d ago against content hash c5ae18e1f87d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

scientific-figure scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (examples/two-column-figure.py, examples/validate_failure_case.py, scripts/compose.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo apt install inkscape # Debian/Ubuntu

plugins/figures/skills/scientific-figure/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scientific Figure

Compose publication-quality multi-panel figures at exact journal dimensions (mm/pt), validate font sizes against journal minima before export, and write PDF/PNG that the journal will accept without resize.

Why this skill exists

The previous react-pdf workflow had two structural failures:

Composition did not respect physical size. Flexbox layout shifted dimensions in subtle ways during render.
Fonts shrank below readable thresholds. When content overflowed, react-pdf uniformly scaled the entire figure, sometimes pushing axis labels under 4 pt.

This skill replaces that workflow. Panels are placed at exact mm coordinates, text is preserved as SVG <text> elements so font sizes are inspectable before export, and the validator rescales individual panels rather than the whole figure when a font minimum is violated.

Pipeline

1. Plan        2. Build elements        3. Compose          4. Validate fonts     5. Export
   (journal      (matplotlib/seaborn      (svgutils, at        (per-element pt vs    (Inkscape if
    size, panel   per panel; SVG out;     exact mm/pt;         journal minimum;      present;
    grid)         optional icons)         text preserved)      rescale panel if      cairosvg
                                                               below minimum)        otherwise)

Every step uses on-the-fly execution via uv run --with so no permanent installs are required for the skill itself.

Step 1: Plan the figure

Before generating anything, fix the following:

Target journal — sets the canvas width. See references/journal-specs.md for the full table; the four most common are summarized below.
Panel grid — 1x1, 1x2, 2x2, wide-top + sub-panels, or freeform mm coordinates.
Color palette — pick from references/color-palettes.md and reuse across all panels.

Journal width / font minimum cheat sheet

Journal	1 column	2 column	Min body font	Notes
Nature	89 mm	183 mm	5 pt	8 pt for panel labels
Science	55 mm	120 mm	6 pt	Myriad/Helvetica preferred
Cell	85 or 112 mm	174 mm	6 pt	Max 225 mm tall
PNAS	87 mm	180 mm	6 pt	No label below 2 mm tall

Read the full file on GitHub · 194 lines

Files

What ships with it

10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

12d ago First seen · 194 lines · 184 tokens per session scan B c5ae18e1f87d

Subscribe to this mod's changes

scientific-figure is a skill published in the GitHub repository neuromechanist/research-skills (45 stars, last pushed 10d ago), licensed BSD-3-Clause. It adds 184 tokens to every session and 2,325 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Design and UX Scientific agenitc-ai ai-marketplace-tools ai-skills codex copilot

latex-posters

Use when creating or revising LaTeX research posters with beamerposter, tikzposter, or baposter, including poster layout, typography, color, print sizing, figure placement, QR codes, compilation, and print-ready PDF checks.

foryourhealth111-pixel/Vibe-Skills · 53 tokens

godot-optimization

Use when optimizing Godot games — profiler, draw calls, physics tuning, memory management, and common bottlenecks.

jame581/GodotPrompter · 28 tokens

photonforge-layout-verification

Assemble, route, inspect, and verify PhotonForge photonic layouts from schematic or netlist intent. Use when the user is working with componentfromnetlist, Reference placement, physical connections, virtual connections, pf.parametric.route, routing errors, port or terminal exposure, getnetlist, LVS-style checks…

flexcompute/plugin-marketplace · 83 tokens

food-analyzer

Analyze food photos, nutrition labels, and ingredient lists. Trigger on food images, nutrition label scans, macro questions, glycemic questions, medication interaction checks, and similar food-analysis requests.

mickpletcher/AI-Skills · 41 tokens

astrophotography-processing

Router for astrophotography processing, troubleshooting, and safe workflow guidance across deep-sky, narrowband, planetary/lunar/solar, Milky Way landscape, comet, and mosaic data.

mickpletcher/AI-Skills · 44 tokens

LQF_Machine_Learning_Expert_Guide

LQF Machine Learning Expert Guide - Routed skill for ML/Statistical Modeling with Critical Discussion Mode. Triggers on: machine learning, modeling, prediction, training, classification, regression, clustering, deep learning, neural network, model evaluation, feature engineering, hyperparameter tuning, overfitting…

foryourhealth111-pixel/Vibe-Skills · 152 tokens

scientific-figure