figure-style

figure-style is a skill for Claude Code, Codex from xuzhougeng/ScientificFigureLibrary. It costs 57 tokens per session (585 once invoked), scanned A, original, MIT.

A guide for checking scientific figures made in R or Python against selected visual templates. It focuses on correct data labels and faithful reproduction of the reference design.

In plain words
What is it for?
It is for adapting plotting code and inspecting rendered scientific charts without changing the underlying data.
Why use it?
It helps find misleading labels, wrong colours, unreadable layouts, and other differences between code output and the intended figure.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the figure-library plugin — 4 skills shipped together

Good fit It is for adapting plotting code and inspecting rendered scientific charts without changing the underlying data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xuzhougeng/scientificfigurelibrary/figure-style
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 xuzhougeng/ScientificFigureLibrary --skill figure-style
Clone the repo
git clone --depth 1 https://github.com/xuzhougeng/ScientificFigureLibrary

Made for: Claude Code, Codex.

Or install figure-library, the plugin that ships this one along with the rest of its 4 skills.

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.

agentmods badge for figure-style

README.md
[![agentmods](https://agentmods.dev/badge/skills/xuzhougeng/scientificfigurelibrary/figure-style/github.svg)](https://agentmods.dev/skills/xuzhougeng/scientificfigurelibrary/figure-style)
Your own site
<a href="https://agentmods.dev/skills/xuzhougeng/scientificfigurelibrary/figure-style"><img src="https://agentmods.dev/badge/skills/xuzhougeng/scientificfigurelibrary/figure-style/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.

agentmods 80×15 button for figure-style

Your own site · 80×15
<a href="https://agentmods.dev/skills/xuzhougeng/scientificfigurelibrary/figure-style"><img src="https://agentmods.dev/badge/skills/xuzhougeng/scientificfigurelibrary/figure-style.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 585 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.00585
Opus 5 $0.00028 $0.00293
Sonnet 5 $0.00011 $0.00117
Haiku 4.5 $0.00006 $0.00059

Measured 5d ago against content hash a2e36d30ef18, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

figure-style scanned grade A with 0 findings 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (kernel.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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/figure-style/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Figure Style — faithful template first

This SFL-bundled entrypoint adapts Wisp Science's Apache-2.0 figure-style guidance. See LICENSE and NOTICE.md for the attribution and adaptation record.

Use this plugin's Skill rather than a Host copy. Follow the user's selected backend and project runtime approvals. A local R-only project rule does not prohibit Python in other projects.

Priority

  1. Data and semantic truth: labels, thresholds, colour mappings and summaries must agree with the actual data and analysis.
  2. The user's explicit current requirements.
  3. The selected template's layout, palette, font, legend, axes and visual identity.
  4. General style defaults only where the reference/user does not specify an answer.

Do not silently replace a palette, font, chart type, legend, grid or layout to comply with a generic aesthetic preference. Where the reference has low contrast, overlaps or inconsistent labels, explain the issue and propose a change; do not conceal the defect or call a restyled version a faithful reproduction. Never alter data to make a preferred shape. Plotting a synthetic scaffold is not reproducing the original experiment.

Backend routing

  • For R/ggplot2/base graphics read R guidance. R never requires the Python kernel.
  • For Python/matplotlib read Python guidance. The bundled kernel is optional and local; its absence in the Host's global skills is irrelevant.
  • For other backends apply the correctness checks without switching language or claiming an unsupported automated QA check passed.

Read correctness and render checks before finalizing the output. This Skill does not depend on figure-composer or paper-narrative; multi-panel work stays within the requested figure boundary.

Execution and output

Materialization downloads/verifies/writes references; it does not authorize arbitrary code execution. Inspect sources before adapting them, use only the project's approved runtime, never install packages automatically, and keep references immutable. Write adapted project code under figure-organization.

Read the full file on GitHub · 37 lines

Files

What ships with it

8 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.

  1. 5d ago First seen · 37 lines · 57 tokens per session scan A a2e36d30ef18

Subscribe to this mod's changes

figure-style is a skill published in the GitHub repository xuzhougeng/ScientificFigureLibrary (58 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 585 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.

Related

Other skills, from other repositories

svg-editor

Open and surgically edit SVG scientific figures in the SVG Editor MCP App. Use when the user wants to change text, colors, fonts, positions, legends, or panel letters in an existing SVG by hand, or by selecting elements and instructing the host assistant.

xuzhougeng/svg-editor · 56 tokens

agent-figure-gallery

Query visual scientific figure references, show candidates for human preference selection, export selected reference bundles, and guide plotting agents from human-selected visual examples to code action.

Dsadd4/AgentFigureGallery · 36 tokens

polish-sci-figures

A final review and preparation workflow for scientific figures, including charts, image panels, manuscripts, slides, and posters.

zhoy0409-debug/polish-sci-figures · 102 tokens

bio-data-visualization-color-palettes

Select colormaps and qualitative palettes for scientific figures using perceptual-uniformity, color-vision-deficiency safety, and luminance-monotonicity criteria. Covers Crameri scientific colormaps, viridis/cividis/magma, Okabe-Ito categorical, ColorBrewer, and the rainbow/jet critique. Use when choosing palettes for…

PKU-YuanGroup/OpenAI4S · 99 tokens

diagram-design

Create branded architecture, IT current-state, flowchart, sequence, state machine, ER/data model, timeline, swimlane, quadrant, radar/spider, polar chart (polar/radial lollipop), loop/flywheel, nested, tree, org chart, layer stack, Venn, pyramid/funnel, treemap, bar, waterfall, line, Gantt and scatter charts…

cathrynlavery/diagram-design · 201 tokens

scientific-schematics

Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.6 Flash for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and…

K-Dense-AI/scientific-agent-skills · 67 tokens