excalidraw
Generate hand-drawn style diagrams, flowcharts, and architecture diagrams as PNG images from Excalidraw JSON
Best use case
excalidraw is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Generate hand-drawn style diagrams, flowcharts, and architecture diagrams as PNG images from Excalidraw JSON
Teams using excalidraw should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/excalidraw/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How excalidraw Compares
| Feature / Agent | excalidraw | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Generate hand-drawn style diagrams, flowcharts, and architecture diagrams as PNG images from Excalidraw JSON
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# Excalidraw Diagram Generator
Generate beautiful hand-drawn style diagrams rendered as PNG images.
## Workflow
1. **Generate JSON** — Write Excalidraw element array based on what the user wants
2. **Save to file** — Write JSON to `/tmp/<name>.excalidraw`
3. **Render** — `node <skill_dir>/scripts/render.js /tmp/<name>.excalidraw /tmp/<name>.png`
4. **Send** — Send the PNG via message tool with `filePath`
## Quick Reference
```bash
node <skill_dir>/scripts/render.js input.excalidraw output.png
```
## Element Types
| Type | Shape | Key Props |
|------|-------|-----------|
| `rectangle` | Box | x, y, width, height |
| `ellipse` | Oval | x, y, width, height |
| `diamond` | Decision | x, y, width, height |
| `arrow` | Arrow | connects shapes (see Arrow Binding below) |
| `line` | Line | x, y, points: [[0,0],[dx,dy]] |
| `text` | Label | x, y, text, fontSize, fontFamily (1=hand, 2=sans, 3=code) |
### Styling (all shapes)
```json
{
"strokeColor": "#1e1e1e",
"backgroundColor": "#a5d8ff",
"fillStyle": "hachure",
"strokeWidth": 2,
"roughness": 1,
"strokeStyle": "solid"
}
```
**fillStyle**: `hachure` (diagonal lines), `cross-hatch`, `solid`
**roughness**: 0=clean, 1=hand-drawn (default), 2=very sketchy
## Arrow Binding (IMPORTANT)
**Always use `from`/`to` bindings for arrows.** The renderer auto-calculates edge intersection points — no manual coordinate math needed.
### Simple arrow (straight, between two shapes)
```json
{"type":"arrow","id":"a1","from":"box1","to":"box2","strokeColor":"#1e1e1e","strokeWidth":2,"roughness":1}
```
That's it. No x, y, or points needed. The renderer computes start/end at shape edges.
### Multi-segment arrow (routed path with waypoints)
For arrows that need to go around obstacles, use `absolutePoints` with intermediate waypoints:
```json
{
"type":"arrow","id":"a2","from":"box3","to":"box1",
"absolutePoints": true,
"points": [[375,500],[30,500],[30,127],[60,127]],
"strokeColor":"#1e1e1e","strokeWidth":2,"roughness":1
}
```
- First point = near source shape edge (will snap to actual edge)
- Last point = near target shape edge (will snap to actual edge)
- Middle points = absolute waypoint coordinates for routing
### Arrow labels
Place a separate text element near the arrow midpoint:
```json
{"type":"text","id":"label","x":215,"y":98,"width":85,"height":16,"text":"sends data","fontSize":10,"fontFamily":1,"strokeColor":"#868e96"}
```
### Arrow styles
- `"strokeStyle":"dashed"` — dashed line
- `"startArrowhead": true` — bidirectional arrow
## Template: Flowchart with Bindings
```json
{
"type": "excalidraw",
"version": 2,
"elements": [
{"type":"rectangle","id":"start","x":150,"y":50,"width":180,"height":60,"strokeColor":"#1e1e1e","backgroundColor":"#b2f2bb","fillStyle":"hachure","strokeWidth":2,"roughness":1},
{"type":"text","id":"t1","x":200,"y":65,"width":80,"height":30,"text":"Start","fontSize":20,"fontFamily":1,"strokeColor":"#1e1e1e"},
{"type":"arrow","id":"a1","from":"start","to":"decision","strokeColor":"#1e1e1e","strokeWidth":2,"roughness":1},
{"type":"diamond","id":"decision","x":140,"y":170,"width":200,"height":120,"strokeColor":"#1e1e1e","backgroundColor":"#ffec99","fillStyle":"hachure","strokeWidth":2,"roughness":1},
{"type":"text","id":"t2","x":185,"y":215,"width":110,"height":30,"text":"Condition?","fontSize":18,"fontFamily":1,"strokeColor":"#1e1e1e","textAlign":"center"},
{"type":"arrow","id":"a2","from":"decision","to":"process","strokeColor":"#1e1e1e","strokeWidth":2,"roughness":1},
{"type":"rectangle","id":"process","x":150,"y":350,"width":180,"height":60,"strokeColor":"#1e1e1e","backgroundColor":"#a5d8ff","fillStyle":"hachure","strokeWidth":2,"roughness":1},
{"type":"text","id":"t3","x":190,"y":365,"width":100,"height":30,"text":"Process","fontSize":20,"fontFamily":1,"strokeColor":"#1e1e1e"}
]
}
```
## Layout Guidelines
- **Node size**: 140-200 × 50-70 px
- **Diamond**: 180-200 × 100-120 px (taller for text)
- **Vertical spacing**: 60-100 px between nodes
- **Horizontal spacing**: 80-120 px between nodes
- **Text**: Position inside shape manually (offset ~15-30px from top-left of shape)
- **Arrow labels**: Place as separate text elements near midpoint of arrow path
## Color Palette
**Fills**: `#a5d8ff` (blue), `#b2f2bb` (green), `#ffec99` (yellow), `#ffc9c9` (red), `#d0bfff` (purple), `#f3d9fa` (pink), `#fff4e6` (cream)
**Strokes**: `#1e1e1e` (dark), `#1971c2` (blue), `#2f9e44` (green), `#e8590c` (orange), `#862e9c` (purple)
**Labels**: `#868e96` (gray, for annotations)
## Tips
- Every element needs a unique `id` (required for binding!)
- Use `from`/`to` on arrows — don't calculate coordinates manually
- `roughness:0` for clean diagrams, `1` for sketchy feel
- Text `fontFamily:1` for hand-drawn, `3` for code
- Group related elements spatially, color-code by type
- For nested layouts, use a large background rectangle as a containerRelated Skills
excalidraw-canvas
Create Excalidraw diagrams and render them as PNG images. Use whenever you need to draw, explain complex workflows, visualize UIs/wireframes, or diagram anything.
excalidraw-diagram
Generate Excalidraw diagrams from text content. Supports three output modes - Obsidian (.md), Standard (.excalidraw), and Animated (.excalidraw with animation order). Triggers on "Excalidraw", "画图", "流程图", "思维导图", "可视化", "diagram", "标准Excalidraw", "standard excalidraw", "Excalidraw动画", "动画图", "animate".
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.