science-figure

science-figure is a skill for Claude Code, Codex from shikaijieskj/science-skills. It costs 86 tokens per session (630 once invoked), scanned A, original, MIT.

A skill for planning, designing, checking, or revising scientific figures for Science-family journals. It treats a figure as an ordered explanation of evidence, with panels that each answer a specific question.

In plain words
What is it for?
Use it to plan multi-panel figures, order results, draft or revise legends, map source data, assess reviewer risks, or check publication-ready scientific visuals.
Why use it?
It helps ensure that a figure supports one clear conclusion, uses the right evidence, and maps quantitative claims to source data. If data is missing, it creates a plan or legend outline instead of inventing a plot.

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 science-skills plugin — 9 skills shipped together

Good fit Use it to plan multi-panel figures, order results, draft or revise legends, map source data, assess reviewer risks, or check publication-ready scientific visuals.

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

Made for: Claude Code, Codex.

Or install science-skills, the plugin that ships this one along with the rest of its 9 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 science-figure

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

agentmods 80×15 button for science-figure

Your own site · 80×15
<a href="https://agentmods.dev/skills/shikaijieskj/science-skills/science-figure"><img src="https://agentmods.dev/badge/skills/shikaijieskj/science-skills/science-figure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 630 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.
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 $0.00086 $0.00630
Opus 5 $0.00043 $0.00315
Sonnet 5 $0.00017 $0.00126
Haiku 4.5 $0.00009 $0.00063

Measured 12d ago against content hash 20c3c6cbc5cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

science-figure 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 12d ago.

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/science-figure/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Science Figure

Use this skill before plotting or rewriting legends. A Science-family figure is an evidence argument, not a decorative arrangement.

First move: figure contract

Before editing or making a figure, define:

  • core conclusion
  • target audience
  • panel list and each panel's question
  • evidence hierarchy
  • source data for each quantitative claim
  • likely reviewer risk
  • journal and article type, if known

If the user has not supplied data, create a panel plan and legend scaffold rather than fabricating plots.

Open extra files

File Open when
references/figure-contract.md Need to convert results into panel map, evidence hierarchy, or reviewer-risk checks
references/legend-and-panel-style.md Need legend structure, panel titles, typography, color, or abbreviation rules
references/qa-checklist.md Before final delivery or when auditing an existing figure

Figure workflow

  1. State the figure's one-sentence conclusion.
  2. Assign one job per panel: context, design, validation, main result, mechanism, comparison, generalization, or limitation.
  3. Order panels by reader logic, not by experiment chronology.
  4. Remove redundant panels unless they test different risks.
  5. Map every claim in the legend to a panel, method, statistic, or source-data file.
  6. Audit visual encoding:
    • color means the same thing across panels
    • axes and units are explicit
    • error bars and sample sizes are defined
    • statistical tests are specified where needed
    • image panels have scale bars and acquisition context
  7. Return the figure plan, legend, and unresolved data/source issues.

Science-family design defaults

  • Favor dense but legible multi-panel evidence.
  • Put the strongest result in the visual position the reader sees early.
  • Use muted neutral structure plus a small number of meaningful accent colors.
  • Avoid rainbow palettes unless the data are continuous and colorbar-labeled.
  • Never use color alone to encode categorical distinctions.
  • Legends should explain what was done and what is shown, not claim more than the data support.

Read the full file on GitHub · 75 lines

Files

What ships with it

4 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. 12d ago First seen · 75 lines · 86 tokens per session scan A 20c3c6cbc5cf

Subscribe to this mod's changes

science-figure is a skill published in the GitHub repository shikaijieskj/science-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 86 tokens to every session and 630 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

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

paper-poster-html

A workflow for building an academic conference poster as one HTML/CSS file and printing it to a PDF at an exact page size. It uses the paper’s real figures and checks layout details before review.

wanshuiyin/Auto-claude-code-research-in-sleep · 107 tokens

paperFig

Design, implement, revise, and validate publication-quality scientific figures from references, existing plotting code, and real project data. Trace every figure to source code and inputs; deconstruct reference figures; plan the scientific story and multi-panel structure; build complex model architecture and…

WUBING2023/PaperSpine · 126 tokens

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

figure-composer

Compose a publication-grade multi-panel scientific figure from a claim, dataset, or draft result. Use when the task needs panel planning, consistent figure layout, figure review, or final figure assembly.

companion-inc/feynman · 42 tokens

ccf-visual-composer

A visual design assistant for research papers, presentations, posters, and README graphics. It can lay out figures, tables, diagrams, icons, colors, and other visual elements, including editable SVG, PDF, and PPTX outputs.

mikubaka88/CCFA-Skills · 86 tokens