Concept Diagrams Agent Skill
Minimal SVG diagrams as standalone HTML files.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/HezaoHezao/poirot --skill concept-diagramsThe instruction itself
10 sections, as written by the authorConcept Diagrams
Overview
Generate production-quality SVG diagrams with a unified flat, minimal design
system. Output is a single self-contained HTML file that renders identically in
any modern browser, with automatic light/dark mode.
Scope
Best suited for:
- Physics setups, chemistry mechanisms, math curves, biology
- Physical objects (aircraft, turbines, smartphones, mechanical watches)
- Anatomy, cross-sections, exploded layer views
- Floor plans, architectural conversions
- Narrative journeys (lifecycle of X, process of Y)
- Hub-spoke system integrations (smart city, IoT)
- Educational / textbook-style visuals in any domain
Look elsewhere first for:
- Software/cloud architecture with dark tech aesthetic → use
architecture-diagram
- Hand-drawn whiteboard sketches → use an excalidraw-style tool
Workflow
- Decide on the diagram type (see below)
- Lay out components using the Design System rules
- Write the full HTML page with inline SVG + CSS
- Save as a standalone
.htmlfile viawrite_file - User opens it directly in a browser — no server, no dependencies
write_file("diagram.html", "<full HTML with inline SVG + CSS>")
Diagram Types
| Type | When |
|------|------|
| Process flow | Sequential steps, lifecycle, pipeline |
| Hub-spoke | Central system + connected components (IoT, smart city) |
| Exploded layers | Component breakdown, cross-section |
| Comparison | Side-by-side, before/after |
| Cycle | Circular process, feedback loop |
| Hierarchy | Org chart, taxonomy, tree |
| Timeline | Chronological events |
Design System
Philosophy
- Flat, minimal, no 3D effects
- Semantic colors: 9 color ramps for different element types
- Sentence-case typography: not Title Case
- Automatic dark mode: CSS
prefers-color-scheme
Color Ramps (light/dark aware)
:root {
/* Primary elements */
--c-primary: #4A90D9;
--c-secondary: #50C878;
--c-accent: #F5A623;
/* Semantic */
--c-input: #7B68EE;
--c-output: #FF6B6B;
--c-process: #4ECDC4;
--c-data: #95E1D3;
--c-control: #C4A7E7;
--c-external: #DDD;
/* Light mode (default) */
--bg: #FAFAFA;
--text: #333;
--border: #E0E0E0;
}
@media (prefers-color-scheme: dark) {
:root {
--bg: #1A1A2E;
--text: #EEE;
--border: #333;
--c-external: #444;
}
}
SVG Structure
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<title>Diagram Title</title>
<style>
body { margin: 0; padding: 40px; background: var(--bg); }
svg { display: block; margin: 0 auto; }
.label { font-family: -apple-system, sans-serif; font-size: 14px; fill: var(--text); }
.title { font-size: 18px; font-weight: 600; }
.box { fill: var(--c-primary); opacity: 0.15; stroke: var(--c-primary); stroke-width: 2; rx: 8; }
.arrow { stroke: var(--text); stroke-width: 2; fill: none; marker-end: url(#arrowhead); }
</style>
</head>
<body>
<svg width="800" height="600" viewBox="0 0 800 600">
<defs>
<marker id="arrowhead" markerWidth="10" markerHeight="7" refX="10" refY="3.5" orient="auto">
<polygon points="0 0, 10 3.5, 0 7" fill="var(--text)"/>
</marker>
</defs>
<!-- Diagram elements here -->
<rect class="box" x="50" y="50" width="200" height="80"/>
<text class="label title" x="150" y="90" text-anchor="middle">Input</text>
<path class="arrow" d="M 250 90 L 350 90"/>
<!-- ... more elements ... -->
</svg>
</body>
</html>
Pitfalls
- Too much detail: keep diagrams minimal. One concept per diagram.
- Inconsistent spacing: use a grid (e.g., 50px increments) for alignment.
- No dark mode: always include
prefers-color-schememedia query. - Font not embedded: use system fonts (-apple-system, sans-serif) so the
HTML works without external font files.
- SVG overflow: set
viewBoxcorrectly so the diagram isn't clipped.
Other skills for the same job
different authors, same section of the catalogue
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
How to use it
Take hezaohezao/concept-diagrams from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.