Nature-Style Scientific Figures
Yuan1z0825/nature-skills
Creates, revises, audits and exports manuscript-ready scientific figures in Python or R, and routes AI-generated graphical abstracts to a separate workflow.
Universal QA checklist for generated scientific plots: overlapping labels, clipped text, missing axes/legends, overcrowded data, and cross-journal resolution/format guidance.
Install General Figure Guide
$ npx skills add jaechang-hits/SciAgent-Skills --skill general-figure-guide -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jaechang-hits/SciAgent-Skills general-figure-guide --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/jaechang-hits/SciAgent-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/scientific-writing/general-figure-guide .claude/skills/general-figure-guide && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "general-figure-guide" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/scientific-writing/general-figure-guide into .claude/skills/general-figure-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "general-figure-guide", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/scientific-writing/general-figure-guideType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add jaechang-hits/SciAgent-Skills --skill general-figure-guide -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jaechang-hits/SciAgent-Skills general-figure-guide --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jaechang-hits/SciAgent-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/scientific-writing/general-figure-guide .agents/skills/general-figure-guide && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "general-figure-guide" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/scientific-writing/general-figure-guide into .agents/skills/general-figure-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "general-figure-guide", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jaechang-hits/SciAgent-Skills --skill general-figure-guide -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jaechang-hits/SciAgent-Skills general-figure-guide --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jaechang-hits/SciAgent-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/scientific-writing/general-figure-guide .cursor/skills/general-figure-guide && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "general-figure-guide" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/scientific-writing/general-figure-guide into .cursor/skills/general-figure-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "general-figure-guide", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/jaechang-hits/SciAgent-Skills.git --path skills/scientific-writing/general-figure-guide--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jaechang-hits/SciAgent-Skills --skill general-figure-guide -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jaechang-hits/SciAgent-Skills general-figure-guide --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jaechang-hits/SciAgent-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/scientific-writing/general-figure-guide .gemini/skills/general-figure-guide && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "general-figure-guide" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/scientific-writing/general-figure-guide into .gemini/skills/general-figure-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "general-figure-guide", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install jaechang-hits/SciAgent-Skills general-figure-guideInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add jaechang-hits/SciAgent-Skills --skill general-figure-guide -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jaechang-hits/SciAgent-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/scientific-writing/general-figure-guide .github/skills/general-figure-guide && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "general-figure-guide" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/scientific-writing/general-figure-guide into .github/skills/general-figure-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "general-figure-guide", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jaechang-hits/SciAgent-Skills --skill general-figure-guide -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jaechang-hits/SciAgent-Skills general-figure-guide --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jaechang-hits/SciAgent-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/scientific-writing/general-figure-guide .opencode/skills/general-figure-guide && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "general-figure-guide" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/scientific-writing/general-figure-guide into .opencode/skills/general-figure-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "general-figure-guide", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
general-figure-guide- GitHub stars
- 374
- Used in
- 1 other repo
- Token cost
- ~1.8k tokens
- SKILL.md length
- 859 words
- Files
- 1
- Skills in repo
- 169
- Repo updated
- First seen
- Licence
- CC-BY-4.0
At a glance
Universal QA checklist for generated scientific plots: overlapping labels, clipped text, missing axes/legends, overcrowded data, and cross-journal resolution/format guidance.
- Works in 7 steps: Run a visual check after every plot… → Use tight_layout() or… → Set DPI at figure creation time:… → …
- Tasks that involve Accessibility
- SKILL.md covers Overview, Key Concepts, Decision Framework and Best Practices, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
General Figure Guide is an agent skill from jaechang-hits/SciAgent-Skills. Universal QA checklist for generated scientific plots: overlapping labels, clipped text, missing axes/legends, overcrowded data, and cross-journal resolution/format guidance.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Research & Science, covering Accessibility, QA and bug reports and Data visualization. The repository describes itself as: 197 bioinformatics & life science skills for Claude Code and AI agents — BixBench 92.0% accuracy. RNA-seq, single-cell, drug discovery, proteomics, and more. Powers OmicsHorizon. The licence is CC-BY-4.0.
When your agent uses it
- Tasks that involve Accessibility
- Tasks that involve QA and bug reports
- Tasks that involve Data visualization
Example prompts
- “/general-figure-guide”
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Run a visual check after every plot generation: Inspect the rendered image for overlapping labels, clipped text, missing axes/legends…
- Use tight_layout() or constrained_layout=True: These prevent text clipping at figure boundaries, the most common layout failure in…
- Set DPI at figure creation time: Configure fig.set_dpi(300) or plt.savefig(..., dpi=300) to ensure publication-quality output from the start
- Export plots as vector formats: Use PDF, SVG, or EPS for graphs and diagrams. Reserve raster formats (PNG, TIFF) for photographs and…
- Apply consistent font sizes across panels: All text in a multi-panel figure should use the same font family and comparable sizes…
- Add transparency for dense scatter plots: Use alpha=0.3-0.5 when plotting thousands of points to reveal density structure instead of a…
- Include units on all axes: Every axis should show the measured parameter and units in parentheses (e.g., "Time (hours)", "Concentration…
What it can do on your machine
Read from SKILL.md and the folder at commit 82c862c. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
matplotlib.orgdoi.orgnature.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
General Figure Guide loads about 1.8k tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 859 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from jaechang-hits/SciAgent-Skills at commit 82c862c, republished under its CC-BY-4.0 licence (© jaechang-hits). 859 words, ~1,797 tokens.
Download SKILL.mdSave it as
.claude/skills/general-figure-guide/SKILL.md (or your agent's skills folder).- name
- general-figure-guide
- description
- Universal QA checklist for generated scientific plots: overlapping labels, clipped text, missing axes/legends, overcrowded data, and cross-journal resolution/format guidance.
- license
- CC-BY-4.0
General Scientific Figure Quality Guide
Overview
This guide provides a universal quality checklist for evaluating scientific figures, whether generated programmatically (matplotlib, seaborn, R/ggplot2) or assembled manually. It focuses on visual readability issues that are common across all journals and easily missed during automated plot generation.
Key Concepts
Visual Readability
A figure must communicate its data without requiring the reader to guess. The most common readability failures are overlapping labels, clipped text that runs outside the figure boundary, missing or unlabeled axes, absent legends, empty plot areas from incorrect data filtering, and overcrowded data points that merge into an unreadable mass.
Resolution and Output Format
Scientific figures generally require 300+ DPI for raster output (TIFF, PNG, JPEG) and vector formats (PDF, EPS, SVG) for line art and graphs. Vector formats are preferred for plots because they scale without quality loss. Raster formats are appropriate for photographs and micrographs.
Color Accessibility
Approximately 8% of males have some form of color vision deficiency. Figures that rely solely on red-green color differences exclude these readers. Use colorblind-friendly palettes (blue-orange, or viridis/cividis colormaps), add pattern or shape differentiation, and test figures with a colorblindness simulator before submission.
Uniform Image Adjustments
All major journals require that brightness, contrast, and color adjustments be applied uniformly to the entire image. Selective enhancement of specific regions (e.g., adjusting one gel lane) is considered data manipulation and grounds for rejection across all journals. Always document processing steps in the Methods section and retain original unprocessed files.
Decision Framework
Is the figure a generated plot or a photograph?
├── Generated plot (matplotlib, ggplot2, seaborn)
│ ├── Export as vector (PDF, SVG, EPS) → preferred
│ └── Export as raster → 300+ DPI minimum, PNG or TIFF
├── Photograph or micrograph
│ └── Export as raster → 300+ DPI, TIFF preferred
└── Multi-panel composite
├── Assemble panels first, then export as single file
└── Use consistent font sizes and label styles across panels| Issue | How to Detect | Fix |
|---|---|---|
| Overlapping labels | Text visually collides on axes or legend | Rotate labels, reduce font size, or increase figure dimensions |
| Clipped text | Labels or titles cut off at figure edge | Increase margins with tight_layout() or constrained_layout |
| Missing axes or legends | No axis labels, units, or legend present | Add xlabel, ylabel, legend() calls |
| Empty plot area | Blank canvas with axes but no visible data | Check data filtering, column names, and plot function arguments |
| Overcrowded data | Points merge into solid mass | Reduce marker size, add transparency (alpha), or use density plots |
Best Practices
- Run a visual check after every plot generation: Inspect the rendered image for overlapping labels, clipped text, missing axes/legends, empty areas, and overcrowded data before proceeding
- Use
tight_layout()orconstrained_layout=True: These prevent text clipping at figure boundaries, the most common layout failure in matplotlib - Set DPI at figure creation time: Configure
fig.set_dpi(300)orplt.savefig(..., dpi=300)to ensure publication-quality output from the start - Export plots as vector formats: Use PDF, SVG, or EPS for graphs and diagrams. Reserve raster formats (PNG, TIFF) for photographs and micrographs
- Apply consistent font sizes across panels: All text in a multi-panel figure should use the same font family and comparable sizes (typically 6-8 pt for labels, 8 pt for panel identifiers)
- Add transparency for dense scatter plots: Use
alpha=0.3-0.5when plotting thousands of points to reveal density structure instead of a solid mass - Include units on all axes: Every axis should show the measured parameter and units in parentheses (e.g., "Time (hours)", "Concentration (nM)")
Show full SKILL.md (351 more words)Show less
Common Pitfalls
- Not inspecting generated plots before saving: Automated pipelines often produce figures with layout issues that go unnoticed until review
- How to avoid: Always render and visually inspect each figure; if reviewing programmatically, check for text bounding-box overlaps
- Clipped axis labels or titles: Default matplotlib margins often cut off long labels or suptitles
- How to avoid: Call
fig.tight_layout()or create figures withconstrained_layout=True
- How to avoid: Call
- Missing legends on multi-series plots: Plots with multiple lines or groups are unreadable without a legend
- How to avoid: Always call
ax.legend()when plotting more than one series; verify legend entries match the data
- How to avoid: Always call
- Overcrowded scatter plots at large N: Scatter plots with >10,000 points become solid blobs at default settings
- How to avoid: Use
alphatransparency, hexbin plots, or kernel density estimation for large datasets
- How to avoid: Use
- Saving at screen resolution (72 DPI): Default screen DPI produces figures that are unprintable in journals
- How to avoid: Always specify
dpi=300(minimum) insavefig()or set it on the figure object at creation
- How to avoid: Always specify
Protocol Guidelines
- Set up figure dimensions and DPI: Before plotting, configure target width (journal column width), aspect ratio, and DPI (300+ minimum) on the figure object
- Generate the figure using your plotting library with the pre-configured settings
- Visually inspect the rendered output for these specific issues:
- Overlapping labels or annotations
- Clipped text at figure boundaries
- Missing axis labels, units, or legends
- Empty plot areas (data not rendered)
- Overcrowded or indistinguishable data points
- If any issue is found, regenerate with targeted fixes (adjust layout, font size, margins, alpha, or figure dimensions)
- Export in the correct format: vector (PDF/EPS/SVG) for plots, raster (TIFF/PNG at 300+ DPI) for photographs
- Verify the saved file: reopen the exported file to confirm it matches the on-screen rendering
Further Reading
- Matplotlib Figure Layout Guide -- tight_layout and constrained_layout usage
- Ten Simple Rules for Better Figures (PLOS) -- general principles for scientific figure design
- Points of View: Nature Methods Column -- visual design principles for scientific data
Related Skills
nature-figure-guide-- Nature-specific figure requirementscell-figure-guide-- Cell Press figure requirementsscience-figure-guide-- Science (AAAS) figure requirementspnas-figure-guide-- PNAS figure requirements
© jaechang-hits, CC-BY-4.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/scientific-writing/general-figure-guide of jaechang-hits/SciAgent-Skills.
Open the folder on GitHubat commit 82c862c
Used in 1 other repository
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in jaechang-hits/SciAgent-Skills, which our catalogue first saw on October 7, 2026.
Compare with similar skills
General Figure Guide next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| General Figure Guide this skilljaechang-hits/SciAgent-Skills | 374 | 1 repos | ~1.8k | Automated safety check: Pass | CC-BY-4.0 | |
| Nature-Style Scientific FiguresYuan1z0825/nature-skills | 47k | — | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| Paper OrchestraAr9av/PaperOrchestra | 679 | 1 repos | ~3.5k | Automated safety check: Pass | Custom licence | |
| Paper Figure DesignerHKUSTDial/Supervisor-Skills | 8.8k | — | ~1.9k | Automated safety check: Pass | CC-BY-4.0 | |
| Ma Publication Qualityhtlin222/meta-pipe | 139 | — | ~1k | Automated safety check: Pass | Custom licence | |
| Nature Polishingaiskillstore/marketplace | 433 | 1 repos | ~1.3k | Automated safety check: Pass | None |
Similar skills
Paper Orchestra
Ar9av/PaperOrchestra
Orchestrate the full PaperOrchestra (Song et al., 2026, arXiv:2604.05018) five-agent pipeline to turn unstructured research materials (idea, experimental log, LaTeX template, conference guidelines…
Paper Figure Designer
HKUSTDial/Supervisor-Skills
Advises on designing the three core figures of a technical paper, then audits them against rules for format, fonts, color and captions.
Ma Publication Quality
htlin222/meta-pipe
Publication-quality checks and enhancements for high-impact journal submissions, including PRISMA/MOOSE reporting, robust meta-analysis diagnostics (Hartung-Knapp, prediction intervals, influence)…
Nature Polishing
aiskillstore/marketplace
Polish, restructure, or translate academic prose into Nature-leaning English using writing-strategy principles, curated Nature/Nature Communications article patterns, and phrase-level support from…
Scientific Figure Making
ChenLiu-1996/figures4papers
Covers publication-ready matplotlib figures for academic papers, slides, and reports—bars, trends, scatter, heatmaps, and multi-panel layouts—with this…
More from jaechang-hits/SciAgent-Skills
All 169 skills in this repoNeb Irc Activation Energy
jaechang-hits/SciAgent-Skills
NEB-IRC activation energy pipeline for reaction barriers using GFN2-xTB and pysisyphus.
Molecular Visualization 3dmol
jaechang-hits/SciAgent-Skills
3Dmol.js WebGL molecular visualization emitted as self-contained HTML.
Cobrapy Metabolic Modeling
jaechang-hits/SciAgent-Skills
Constraint-based (COBRA) analysis of genome-scale metabolic models: FBA, FVA, knockouts, flux sampling, production envelopes, gapfilling, media optimization.
Rdkit Chemdraw Cdxml
jaechang-hits/SciAgent-Skills
Read, write, and edit ChemDraw CDX/CDXML files with RDKit's rdkit.Chem.rdChemDraw plus direct XML editing, always paired with a rendered PNG.
Pubmed Database
jaechang-hits/SciAgent-Skills
Programmatic PubMed access via NCBI E-utilities REST API. An agent skill from jaechang-hits/SciAgent-Skills.
Sciagent Skill Creator
jaechang-hits/SciAgent-Skills
Scaffold a new SciAgent-Skills entry. An agent skill from jaechang-hits/SciAgent-Skills.
Related
Categories
Questions about General Figure Guide
What does General Figure Guide do?
Universal QA checklist for generated scientific plots: overlapping labels, clipped text, missing axes/legends, overcrowded data, and cross-journal resolution/format guidance. General Figure Guide is an agent skill from jaechang-hits/SciAgent-Skills. Universal QA checklist for generated scientific plots: overlapping labels, clipped text, missing axes/legends, overcrowded data, and cross-journal resolution/format guidance.
When should I use General Figure Guide?
General Figure Guide fits situations like: tasks that involve Accessibility; tasks that involve QA and bug reports; tasks that involve Data visualization.
How do I install General Figure Guide in Claude Code?
Run `npx skills add jaechang-hits/SciAgent-Skills --skill general-figure-guide -a claude-code`. Or copy the skill folder (skills/scientific-writing/general-figure-guide in jaechang-hits/SciAgent-Skills) into .claude/skills/general-figure-guide in your project. Claude Code loads it when a task matches its description.
How do I install General Figure Guide in Codex?
Run `npx skills add jaechang-hits/SciAgent-Skills --skill general-figure-guide -a codex`. Or copy the skill folder (skills/scientific-writing/general-figure-guide in jaechang-hits/SciAgent-Skills) into .agents/skills/general-figure-guide in your project. Codex loads it when a task matches its description.
Can I use General Figure Guide in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jaechang-hits/SciAgent-Skills --skill general-figure-guide -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/general-figure-guide, .gemini/skills/general-figure-guide, .github/skills/general-figure-guide and .opencode/skills/general-figure-guide in your project.
What does General Figure Guide need to run?
SKILL.md names no scripts, command-line tools or credentials: General Figure Guide is instructions for the agent only.
Does General Figure Guide access the network?
SKILL.md names 3 domains. As links in the text: matplotlib.org, doi.org and nature.com. This is read from the text; nothing was executed.
Is General Figure Guide safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does General Figure Guide use?
General Figure Guide is published under the CC-BY-4.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does General Figure Guide use?
About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to General Figure Guide?
Skills that share tags, products or a category with General Figure Guide: Nature-Style Scientific Figures (Yuan1z0825/nature-skills, 47k stars), Paper Orchestra (Ar9av/PaperOrchestra, 679 stars), Paper Figure Designer (HKUSTDial/Supervisor-Skills, 8.8k stars) and Ma Publication Quality (htlin222/meta-pipe, 139 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains General Figure Guide?
jaechang-hits (a GitHub user) maintains it in jaechang-hits/SciAgent-Skills, which has 374 GitHub stars. The repository holds 169 skills in this directory. The repository was last updated on September 29, 2026.
Source: jaechang-hits/SciAgent-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.