Install the "scientific-schematics" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/scientific-writing/scientific-schematics into .claude/skills/scientific-schematics/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scientific-schematics", 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.
Type 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.
skills CLI
$ npx skills add jaechang-hits/SciAgent-Skills --skill scientific-schematics -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "scientific-schematics" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/scientific-writing/scientific-schematics into .agents/skills/scientific-schematics/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scientific-schematics", 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.
skills CLI
$ npx skills add jaechang-hits/SciAgent-Skills --skill scientific-schematics -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "scientific-schematics" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/scientific-writing/scientific-schematics into .cursor/skills/scientific-schematics/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scientific-schematics", 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.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add jaechang-hits/SciAgent-Skills --skill scientific-schematics -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "scientific-schematics" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/scientific-writing/scientific-schematics into .gemini/skills/scientific-schematics/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scientific-schematics", 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.
Installs 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).
skills CLI
$ npx skills add jaechang-hits/SciAgent-Skills --skill scientific-schematics -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "scientific-schematics" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/scientific-writing/scientific-schematics into .github/skills/scientific-schematics/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scientific-schematics", 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.
skills CLI
$ npx skills add jaechang-hits/SciAgent-Skills --skill scientific-schematics -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "scientific-schematics" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/scientific-writing/scientific-schematics into .opencode/skills/scientific-schematics/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scientific-schematics", 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
scientific-schematics
GitHub stars
374
Token cost
~3.8k tokens
SKILL.md length
1,696 words
Files
1
Skills in repo
169
Repo updated
First seen
Licence
CC-BY-4.0
At a glance
Designing scientific schematics, diagrams, and graphical abstracts.
Works in 4 steps: Schematic Types and Their Purpose → Tool Comparison → Color Usage in Biological Schematics → …
SKILL.md covers Overview, Key Concepts, Decision Framework and Best Practices, plus 5 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Scientific Schematics is an agent skill from jaechang-hits/SciAgent-Skills. Designing scientific schematics, diagrams, and graphical abstracts. Covers tool selection (BioRender, Inkscape, Affinity, PowerPoint), design principles for pathway diagrams, mechanism schematics, experimental workflows, and journal graphical abstracts. Includes composition, icon sourcing, color for biological entities, and accessibility. Use when creating illustrative (not data-driven) scientific figures.
Its SKILL.md is about 3.8k 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 Data visualization and Diagrams. It works with Microsoft PowerPoint. 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.
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):
biorender.com
clauswilke.com
bioicons.com
reactome.org
ncbi.nlm.nih.gov
doi.org
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
Scientific Schematics loads about 3.8k tokens when it runs. Until then it costs about 108 tokens; SKILL.md has 1,696 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~108
When it runs· the whole SKILL.md, loaded when a task matches
~3.8k
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.
Download SKILL.mdSave it as .claude/skills/scientific-schematics/SKILL.md (or your agent's skills folder).
name
scientific-schematics
description
Designing scientific schematics, diagrams, and graphical abstracts. Covers tool selection (BioRender, Inkscape, Affinity, PowerPoint), design principles for pathway diagrams, mechanism schematics, experimental workflows, and journal graphical abstracts. Includes composition, icon sourcing, color for biological entities, and accessibility. Use when creating illustrative (not data-driven) scientific figures.
license
CC-BY-4.0
Scientific Schematics
Overview
Scientific schematics are illustrative figures that communicate biological mechanisms, experimental designs, or conceptual frameworks — as distinct from data-driven figures (graphs, heatmaps). A well-designed schematic makes a manuscript's key concept immediately comprehensible to a broad scientific audience, while a poorly designed one confuses reviewers and reduces the paper's impact. This guide covers the design decisions, tool selection, composition principles, and accessibility standards specific to biological schematics in peer-reviewed publications.
Key Concepts
1. Schematic Types and Their Purpose
Not all schematics serve the same function. Choosing the wrong type leads to overloaded or underspecified figures.
Ribbon structure, surface representation, active site
Protein domain schematic, ligand binding pocket
Decision rule: If the reader needs to understand what happened step-by-step, use a workflow. If they need to understand why (cause and effect), use a mechanism/pathway diagram. If they need a 30-second paper summary, use a graphical abstract.
Subscription (~$99/month academic; free for draft)
PNG, SVG, PDF (license required for publication)
Inkscape
Full vector editing; open-source
Medium–High
Free
SVG, PDF, PNG, EMF
Affinity Designer
Professional vector + raster hybrid
Medium
~$55 one-time
SVG, PDF, AFDESIGN
Adobe Illustrator
Industry standard; full features
High
~$55/month
SVG, PDF, AI, EPS
PowerPoint / Keynote
Quick drafts; non-scientists
Low
Included in MS/Apple
PNG (low resolution), PDF
draw.io / Lucidchart
Flowcharts, pathway diagrams
Low
Free/subscription
SVG, PNG, XML
ChimeraX / PyMOL
Molecular structure renders
Medium
Free (academic)
PNG, TIFF, movie
Key difference: BioRender provides curated biological icons (cells, proteins, instruments) that are publication-quality and royalty-free under the publication license. For complex custom graphics, Inkscape (free) or Affinity Designer (paid) offer more flexibility.
3. Color Usage in Biological Schematics
Color in biological schematics carries semantic meaning and must be used consistently.
Conventional biological color assignments:
DNA: double helix colored in blue/navy or gray
mRNA: orange or yellow
Protein: varying; use consistent color per protein family across all figures in a paper
Color coding arrows: green = activating, red = inhibiting, gray = neutral/context
Accessibility:
Never use red–green encoding alone; add shape cues (✓/✗, solid/dashed)
Test with CVD simulator before submission
Use at least 3:1 contrast ratio for text on colored backgrounds
4. Composition and Layout Principles
Visual hierarchy: The most important element should be the largest and most central. Support elements (labels, arrows, scale bars) should be visually subordinate.
Element spacing: Maintain consistent padding between grouped elements. Crowded diagrams cause readers to misread association between elements.
Arrow semantics: Every arrow must convey exactly one relationship. Do not use arrows interchangeably for "leads to," "causes," "physically binds," and "is required for" — use distinct arrow styles for each.
Text minimalism: Labels should be noun phrases only (not full sentences). Move explanatory text to the figure caption, not into the diagram itself.
Decision Framework
What is this schematic trying to communicate?
│
├── A sequence of experimental steps
│ └── → Workflow diagram
│ ├── Numbered panels or numbered arrows
│ ├── Icons for equipment (instrument, pipette, plate, animal)
│ └── Time axis or step axis
│
├── How a molecule works mechanistically
│ └── → Mechanism diagram
│ ├── Protein shapes (surface or cartoon)
│ ├── Conformational change arrows
│ └── Before/after state panels
│
├── How multiple components interact in a network
│ └── → Pathway diagram
│ ├── Nodes = proteins/metabolites (circles, rectangles)
│ ├── Edges = arrows (activation = →, inhibition = ⊣)
│ └── Compartment boxes (nucleus, cytoplasm, extracellular)
│
├── A single-panel paper summary
│ └── → Graphical abstract
│ ├── Check journal specifications (size, text policy)
│ ├── Show: question → approach → key finding → implication
│ └── Minimal text; max 3–4 panels
│
└── A 3D molecular structure
└── → Structural diagram
├── Use ChimeraX, PyMOL, or RCSB PDB viewer for render
├── Annotate active site/binding pocket
└── Add scale bar (Å or nm)
Scenario
Tool
Format
Key Consideration
First-author manuscript, fast turnaround
BioRender
PDF/SVG
Requires publication license for final submission
Lab with ongoing schematic needs
Inkscape + master template
SVG
Reusable elements; free; no vendor lock-in
Graphical abstract for Cell/Nature
BioRender or Illustrator
PNG at journal spec
Check exact pixel dimensions and text policy
Molecular mechanism with protein structure
ChimeraX + Inkscape
PNG render + SVG annotation
Use PDB structure; annotate key residues
Pathway diagram with many nodes
draw.io / Cytoscape
SVG/PDF
Auto-layout for networks with >20 nodes
Best Practices
Start with a sketch before opening any tool: Draw the schematic on paper first. Determine what elements are needed, their hierarchy, and the spatial relationships. Opening software first leads to layout decisions driven by tool constraints, not by communication goals.
Define a consistent visual vocabulary before drawing the first panel: Assign colors, shapes, and arrow styles to each biological entity type at the project level. Document these assignments in a legend or lab style guide. Inconsistency across figures in a paper signals carelessness and confuses reviewers.
Use the journal's graphical abstract template: Every high-impact journal (Cell, Nature, PNAS, PLOS) publishes exact dimensions, resolution requirements, and font rules for graphical abstracts. Download the template before starting — resizing after the fact destroys aspect ratios and makes text too small.
Export at publication resolution from the vector source: Always export final figures from the original vector file (SVG, AI, AFDESIGN) at the target DPI, never by screenshot or screen capture. Screenshots are raster at screen resolution (~72 dpi); journals require 300–600 dpi.
Label arrows and connections in captions, not in the diagram: Arrow labels ("activates," "phosphorylates," "recruits") add clutter and reduce diagram readability. Move these relationships to the figure caption using panel reference labels (A, B, C). The diagram should be self-explanatory to someone who reads the caption.
Group related elements visually using proximity, enclosure, and color: Elements that belong together conceptually should be spatially close, share a background color, or be enclosed in a bounding box. Do not use arbitrary spatial arrangements — viewers interpret proximity as association.
Version-control your source files: Store original editable source files (.svg, .afdesign, .ai, .brd) in version-controlled storage alongside the manuscript. Journals frequently request revised figures during revision, and re-creating from a PNG is extremely time-consuming.
Show full SKILL.md (740 more words)Show less
Common Pitfalls
Using inconsistent arrow styles across a figure
What goes wrong: Solid arrows and dashed arrows mixed arbitrarily make readers unsure whether dashed means "indirect," "hypothetical," or merely a stylistic choice.
How to avoid: Define an arrow legend: solid arrow = direct activation, dashed = indirect, flat bar = inhibition. Use this consistently in every panel of every figure in the paper.
Overloading a single panel with too many elements
What goes wrong: Pathway diagrams with 20+ nodes and 30+ arrows cannot be read in a journal figure at 170 mm width. Reviewers ask for simplification; revisions are time-consuming.
How to avoid: Limit mechanism panels to ≤8 elements. Move complex pathway context to supplementary figures. Focus the main-text schematic on the core novel finding.
Using BioRender without purchasing the publication license
What goes wrong: BioRender figures created under the free or draft license cannot be published. Submitting without proper licensing violates BioRender's terms of service and risks manuscript rejection.
How to avoid: Purchase the publication license before creating the final figure version. BioRender generates a citation string that must be included in the figure legend.
Text inside the schematic at 6 pt or smaller at print size
What goes wrong: Labels inside pathway nodes or protein icons become illegible at publication dimensions (85 mm single-column). Reviewers flag this; revision requires recreating the entire figure.
How to avoid: Work at print size from the start. In Inkscape: set canvas to 85 mm × target height. Minimum label size: 7 pt at 100% print scale.
Red–green arrow encoding for activation–inhibition without shape cues
What goes wrong: ~8% of male readers have red–green color vision deficiency and cannot distinguish activation (green) from inhibition (red) arrows.
How to avoid: Use distinct arrow shapes: → for activation, ⊣ for inhibition. Color is redundant encoding, not the only cue.
Copying schematic elements from published papers without redrawing
What goes wrong: Reproducing figures from published papers without permission violates copyright. This applies to diagrams and icons, not just photographs.
How to avoid: Use BioRender's licensed icon library, Reactome's freely licensed pathway diagrams (CC-BY), or Bioicons (free, open icons). Always redraw; never screenshot.
Missing scale bars in structural diagrams
What goes wrong: Protein structure renderings without scale bars prevent readers from assessing relative sizes of domains, ligands, or interfaces.
How to avoid: Add a scale bar (e.g., "10 Å" or "2 nm") using ChimeraX's scalebar command or annotate in Inkscape after export.
Workflow
Define the message — write one sentence stating what the schematic must communicate
Sketch on paper — rough layout, element list, arrow types
Choose tool — BioRender for icon-heavy biology; Inkscape for custom vectors; ChimeraX for structures
Set canvas to print dimensions — match journal column width before placing any element
Build in layers — background → structural elements (membranes, organelles) → protein/molecule icons → arrows → labels
Run accessibility check — CVD simulation; test grayscale version
Export from vector source — PDF or TIFF at target DPI (≥300 dpi raster, vector for line art)
Archive source file — commit .svg/.afdesign/.brd to version control alongside manuscript
Protocol Guidelines
BioRender publication workflow: Create figure → File → Publish Figure → Generate Attribution → copy citation string into figure legend. The attribution reads: "Created with BioRender.com" with a unique agreement ID. Without this, the figure cannot be legally published.
Inkscape CMYK-safe workflow: Inkscape does not natively support CMYK. For CMYK journals: design in RGB → export to PDF → convert using Ghostscript (gs -sDEVICE=pdfwrite -dUseCIEColor). Verify colors after conversion.
ChimeraX protein structure render: open 6YYT → graphics silhouettes true → lighting soft → saveimage figure.png width 2400 height 2400 → annotate in Inkscape.
Multi-panel figure assembly in Inkscape: Use Inkscape extensions → Grids → set column guides at journal column widths. Import each panel as a linked SVG to enable per-panel updates without recreating the composite.
Scientific Schematics 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.
Scientific Schematics compared with similar skills
Skill
Stars
Used in
Tokens
Auto-check
Licence
Repo updated
Scientific Schematics this skilljaechang-hits/SciAgent-Skills
A skill your agent uses when the user needs engineering or research-paper figures: system architecture diagrams, algorithm workflows, hardware schematics, benchmark charts, ablation plots, figure…
Design research method figures from an existing paper, retrieve visual priors from component or private PPTX libraries, produce editable diagrams, and revise selected objects while preserving…
Designing scientific schematics, diagrams, and graphical abstracts. Scientific Schematics is an agent skill from jaechang-hits/SciAgent-Skills. Designing scientific schematics, diagrams, and graphical abstracts.
When should I use Scientific Schematics?
Scientific Schematics fits situations like: creating illustrative (not data-driven) scientific figures; tasks that involve Data visualization; tasks that involve Diagrams.
How do I install Scientific Schematics in Claude Code?
Run `npx skills add jaechang-hits/SciAgent-Skills --skill scientific-schematics -a claude-code`. Or copy the skill folder (skills/scientific-writing/scientific-schematics in jaechang-hits/SciAgent-Skills) into .claude/skills/scientific-schematics in your project. Claude Code loads it when a task matches its description.
How do I install Scientific Schematics in Codex?
Run `npx skills add jaechang-hits/SciAgent-Skills --skill scientific-schematics -a codex`. Or copy the skill folder (skills/scientific-writing/scientific-schematics in jaechang-hits/SciAgent-Skills) into .agents/skills/scientific-schematics in your project. Codex loads it when a task matches its description.
Can I use Scientific Schematics 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 scientific-schematics -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scientific-schematics, .gemini/skills/scientific-schematics, .github/skills/scientific-schematics and .opencode/skills/scientific-schematics in your project.
What does Scientific Schematics need to run?
SKILL.md names no scripts, command-line tools or credentials: Scientific Schematics is instructions for the agent only.
Does Scientific Schematics access the network?
SKILL.md names 6 domains. As links in the text: biorender.com, clauswilke.com, bioicons.com, reactome.org, ncbi.nlm.nih.gov and doi.org. This is read from the text; nothing was executed.
Is Scientific Schematics 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 Scientific Schematics use?
Scientific Schematics 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 Scientific Schematics use?
About 3.8k tokens (SKILL.md is roughly 15k 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 Scientific Schematics?
Skills that share tags, products or a category with Scientific Schematics: Engineering Figure Agent (heyu-233/engineering-figure-agent, 307 stars), Figure Legend Writer (aipoch/medical-research-skills, 1.9k stars), Academic Figure Skill (TingxiYu/academic-figure-skill, 483 stars) and Astra Figure Workflow (IamJerryXu/AstraDraw, 148 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Scientific Schematics?
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.