scientific-figure-polish

scientific-figure-polish is a skill for Claude Code, Codex from CHENyiru3/AI-Skills-Collections. It costs 68 tokens per session (1,500 once invoked), scanned A, original, MIT.

A review and editing workflow for multi-panel scientific figures, including PDF or vector artwork and their plotting sources. It focuses on preserving scientific meaning while improving layout, text hierarchy, legends, and panel alignment.

In plain words
What is it for?
It is for refining manuscript figures, aligning comparable plots and map views, standardizing fonts and annotations, and making legends clearer.
Why use it?
It addresses figures that are crowded, inconsistent, hard to compare, or difficult to read. It improves organization without changing the underlying scientific content.

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 documents plugin — 20 skills shipped together

Good fit It is for refining manuscript figures, aligning comparable plots and map views, standardizing fonts and annotations, and making legends clearer.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chenyiru3/ai-skills-collections/scientific-figure-polish
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 CHENyiru3/AI-Skills-Collections --skill scientific-figure-polish
Clone the repo
git clone --depth 1 https://github.com/CHENyiru3/AI-Skills-Collections

Made for: Claude Code, Codex.

Or install documents, the plugin that ships this one along with the rest of its 20 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 scientific-figure-polish

README.md
[![agentmods](https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/scientific-figure-polish/github.svg)](https://agentmods.dev/skills/chenyiru3/ai-skills-collections/scientific-figure-polish)
Your own site
<a href="https://agentmods.dev/skills/chenyiru3/ai-skills-collections/scientific-figure-polish"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/scientific-figure-polish/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 scientific-figure-polish

Your own site · 80×15
<a href="https://agentmods.dev/skills/chenyiru3/ai-skills-collections/scientific-figure-polish"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/scientific-figure-polish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,500 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 $0.00068 $0.01500
Opus 5.5 $0.00027 $0.00600
Sonnet 5.5 $0.00014 $0.00300
Haiku 4.5 $0.00007 $0.00150

Measured 3d ago against content hash 5d253eaa659e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

scientific-figure-polish 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/figure_inventory.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-market/documents/design/scientific-figure-polish/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scientific Figure Polish

Apply the user's FEAST-derived figure style: compact, organized, readable, and scientifically faithful. Current user instructions override these defaults. Read style-reference.md for visual conventions and examples. For direct PDF edits, also read pdf-editing.md and use the available PDF skill for its format-specific requirements.

Priorities

  1. Preserve scientific meaning and the author's current edits.
  2. Retain the original figure's compact density and organize the content on a clear grid.
  3. Match the size and alignment of comparable units.
  4. Make equivalent text levels consistent and readable.

Tighten internal gaps before extending the artwork; cropping outside margins alone does not fix a loose composition. Preserve compactness jointly with readability.

Compactness and readability are joint constraints. If larger text does not fit, first share repeated annotations, repair wrapping, reduce gaps, or rebalance groups. Do not force the old footprint with unreadable text or overlaps. Use the smallest necessary geometry adjustment and explain a material expansion; changing scientific content requires separate justification.

Establish the current baseline

  • Inspect the actual current artwork before editing. The author also modifies files manually. When replacing shared or manually edited artwork, retain a recoverable baseline and check for intervening author edits; hashes can help identify the exact source. A read-only review does not need a backup workflow.
  • Treat the latest author-approved artwork as authoritative. Plotting sources or retained component figures may predate manual changes. Rebuild only when their scientific content and author adjustments can be preserved.
  • For density comparisons, “original” defaults to the current supplied figure before this edit. If the author identifies an earlier version as the compactness reference, use that version's organization while preserving the current scientific content and manual edits.
  • Review every unit in the requested scope. An all-figure scan includes main and supplementary figures; a named-figure request stays within that scope.
  • Render the whole figure and inspect dense details. Identify panel roles, comparable families, annotation levels, and the original density before changing geometry.
  • Optionally use scripts/figure_inventory.py for a read-only PDF inventory and review previews. Its measurements support inspection; they do not prove correct alignment or scientific fidelity.

Read the full file on GitHub · 68 lines

Files

What ships with it

5 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. 3d ago First seen · 68 lines · 68 tokens per session scan A 5d253eaa659e

Subscribe to this mod's changes

scientific-figure-polish is a skill published in the GitHub repository CHENyiru3/AI-Skills-Collections (2 stars, last pushed 3d ago), licensed MIT. It adds 68 tokens to every session and 1,500 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-11.

Related

scientific-figure-polish compared with skills from other repositories

scientific-figure-polish next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
scientific-figure-polishCHENyiru3/AI-Skills-CollectionsSkill23d agoMITA68Claude Code, Codex
scientific-schematicsK-Dense-AI/scientific-agent-skillsSkill57k5d agoMITA68Claude Code
paper-poster-htmlwanshuiyin/Auto-claude-code-research-in-sleepSkill19ktodayMITA107Claude Code
latex-postersforyourhealth111-pixel/Vibe-SkillsSkill3.8k5d agoApache-2.0A53Claude Code
figure-composercompanion-inc/feynmanSkill10k7d agoMITA42Claude Code, Codex
paperFigWUBING2023/PaperSpineSkill6.3ktodayMITA126Claude Code, Codex
schematicssynthetic-sciences/openscienceSkill4.4kyesterdayApache-2.0A134Claude Code