skills/43-wentorai-research-plugins/skills/tools/diagram/excalidraw-diagram-guide/SKILL.md
Generate hand-drawn style Excalidraw diagrams from text descriptions
npx skillsauth add brycewang-stanford/Awesome-Agent-Skills-for-Empirical-Research excalidraw-diagram-guideInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Generate hand-drawn style diagrams, wireframes, and visual explanations using Excalidraw's open-source whiteboard format. This skill enables researchers to create informal yet informative sketches for brainstorming sessions, presentations, and collaborative workshops.
Excalidraw is an open-source virtual whiteboard tool that produces diagrams with a distinctive hand-drawn aesthetic. Unlike formal diagramming tools such as PlantUML or Visio, Excalidraw prioritizes approachability and rapid ideation. Its output looks intentionally informal, which makes it well-suited for early-stage research brainstorming, teaching materials, and conference posters where a polished UML diagram would feel overly rigid.
The tool stores diagrams in a JSON-based .excalidraw format, making them fully version-controllable and programmatically generatable. Researchers can describe what they need in natural language, and this skill translates those descriptions into valid Excalidraw scene files that can be opened in the Excalidraw editor or embedded directly into web pages.
Excalidraw supports real-time collaboration, end-to-end encryption for shared sessions, and export to PNG and SVG. The hand-drawn style is achieved through a custom rendering engine that applies subtle randomization to stroke paths, giving each element a natural, sketched appearance.
The Excalidraw JSON format consists of an array of elements, each with a type (rectangle, ellipse, arrow, text, line, diamond), position coordinates, dimensions, and style properties.
{
"type": "rectangle",
"x": 100,
"y": 200,
"width": 200,
"height": 80,
"strokeColor": "#1e1e1e",
"backgroundColor": "#a5d8ff",
"fillStyle": "hachure",
"strokeWidth": 1,
"roughness": 1,
"roundness": { "type": 3 }
}
| Property | Values | Description |
|----------|--------|-------------|
| fillStyle | hachure, cross-hatch, solid | Fill pattern style |
| roughness | 0, 1, 2 | Hand-drawn roughness level |
| strokeWidth | 1, 2, 4 | Line thickness |
| strokeStyle | solid, dashed, dotted | Line style |
| roundness | null, { "type": 3 } | Corner rounding |
Primary: #1971c2 (blue) Background: #a5d8ff
Accent: #e03131 (red) Background: #ffc9c9
Success: #2f9e44 (green) Background: #b2f2bb
Warning: #f08c00 (orange) Background: #ffec99
Neutral: #495057 (gray) Background: #dee2e6
Describe a research pipeline and generate the corresponding layout:
Input: "Create a flowchart showing: Literature Review -> Research Questions ->
Hypothesis Formation -> Study Design -> Data Collection -> Analysis ->
Results -> Discussion -> Publication"
Each step becomes a rounded rectangle connected by arrows. Decision points (e.g., "Results Significant?") use diamond shapes with branching arrows.
For software or experimental system diagrams, use grouped rectangles with labeled connections:
Input: "Draw a system architecture with three layers:
Frontend (React dashboard),
Backend (FastAPI + PostgreSQL),
External (OpenAlex API, CrossRef API)"
The output places each layer as a dashed-border container with internal component boxes and inter-layer arrows.
exportScale: 2 for high-DPI output.<iframe
src="https://excalidraw.com/#json=YOUR_ENCODED_DATA"
width="800"
height="600"
style="border: none;">
</iframe>
import json
def create_box(text, x, y, width=200, height=80, color="#a5d8ff"):
return [
{
"type": "rectangle",
"x": x, "y": y,
"width": width, "height": height,
"backgroundColor": color,
"fillStyle": "hachure",
"roughness": 1,
"strokeWidth": 1
},
{
"type": "text",
"x": x + 10, "y": y + 25,
"text": text,
"fontSize": 16
}
]
scene = {
"type": "excalidraw",
"version": 2,
"elements": create_box("Literature Review", 100, 100)
+ create_box("Data Analysis", 100, 250)
}
with open("research_flow.excalidraw", "w") as f:
json.dump(scene, f, indent=2)
Excalidraw supports live collaboration through shared session links. Each participant sees real-time cursor positions and edits. Sessions can be encrypted end-to-end using the built-in encryption feature, which is important when sketching unpublished research ideas.
For research teams, the recommended workflow is:
.excalidraw JSON and commit to the project repository\includesvg{} (requires svg package)IPython.display.Image.excalidraw files in the IDEtools
Recommend AND run open-source AI tools, agents, Claude Code / Codex skills, and MCP servers for any stage of a literature review — searching, reading, extracting, synthesizing, screening, citation-checking, and paper writing. Use when the user asks "what tool should I use to..." OR "install/run/use <tool> to ..." for research/lit-review work: automating a survey or related-work section, PDF→Markdown extraction for LLMs (MinerU/marker/docling), PRISMA / systematic review (ASReview), citation-backed Q&A over PDFs (PaperQA2), wiring papers into Claude/Cursor via MCP (arxiv/paper-search/zotero servers), or chatting with a Zotero library. Ships a launcher (scripts/litrun.py) that installs each tool in an isolated venv and runs it. Curated catalog of 70+ vetted projects. 支持中英文(用于「文献综述工具选型」与「一键安装/运行」)。
development
Route empirical-research requests through the Auto-Empirical Research Skills catalog when this whole repository is installed as one skill in Codex, CodeBuddy, Claude Code, or another IDE. Use to choose and load the right vendored AERS skill for causal inference, econometrics, replication, data acquisition, manuscript writing, peer review and referee responses, citation checking, de-AIGC editing, or full empirical-paper workflows without reading the entire repository at once.
documentation
Use when the project collects primary data or runs a field, lab, or survey experiment, before the intervention begins — write the pre-analysis plan, size the sample from a power calculation, and register with the AEA RCT Registry. Apply after the design is chosen in aer-identification and before any outcome data are seen.
tools
Guide economists to authoritative data sources with explicit, confirmed data specifications before retrieval; interfaces with Playwright MCP to navigate portals and extract real data, not articles about data.