draw
Vector graphics and diagram creation, format conversion (ODG/SVG/PDF) with LibreOffice Draw.
Best use case
draw is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Vector graphics and diagram creation, format conversion (ODG/SVG/PDF) with LibreOffice Draw.
Teams using draw 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/draw/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How draw Compares
| Feature / Agent | draw | 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?
Vector graphics and diagram creation, format conversion (ODG/SVG/PDF) with LibreOffice Draw.
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.
SKILL.md Source
# LibreOffice Draw
## Overview
LibreOffice Draw skill for creating, editing, converting, and automating vector graphics and diagram workflows using the native ODG (OpenDocument Drawing) format.
## When to Use This Skill
Use this skill when:
- Creating vector graphics and diagrams in ODG format
- Converting between ODG, SVG, PDF, PNG formats
- Automating diagram and flowchart generation
- Creating technical drawings and schematics
- Batch processing graphics operations
## Core Capabilities
### 1. Graphics Creation
- Create new ODG drawings from scratch
- Generate diagrams from templates
- Create flowcharts and org charts
- Design technical drawings
### 2. Format Conversion
- ODG to other formats: SVG, PDF, PNG, JPG
- Other formats to ODG: SVG, PDF
- Batch conversion of multiple files
### 3. Diagram Automation
- Template-based diagram generation
- Automated flowchart creation
- Dynamic shape generation
- Batch diagram production
### 4. Graphics Manipulation
- Shape creation and manipulation
- Path and bezier curve editing
- Layer management
- Text and label insertion
### 5. Integration
- Command-line automation via soffice
- Python scripting with UNO
- Integration with workflow tools
## Workflows
### Creating a New Drawing
#### Method 1: Command-Line
```bash
soffice --draw template.odg
```
#### Method 2: Python with UNO
```python
import uno
def create_drawing():
local_ctx = uno.getComponentContext()
resolver = local_ctx.ServiceManager.createInstanceWithContext(
"com.sun.star.bridge.UnoUrlResolver", local_ctx
)
ctx = resolver.resolve(
"uno:socket,host=localhost,port=8100;urp;StarOffice.ComponentContext"
)
smgr = ctx.ServiceManager
doc = smgr.createInstanceWithContext("com.sun.star.drawing.DrawingDocument", ctx)
page = doc.getDrawPages().getByIndex(0)
doc.storeToURL("file:///path/to/drawing.odg", ())
doc.close(True)
```
### Converting Drawings
```bash
# ODG to SVG
soffice --headless --convert-to svg drawing.odg
# ODG to PDF
soffice --headless --convert-to pdf drawing.odg
# ODG to PNG
soffice --headless --convert-to png:PNG_drawing drawing.odg
# SVG to ODG
soffice --headless --convert-to odg drawing.svg
# Batch convert
for file in *.odg; do
soffice --headless --convert-to pdf "$file"
done
```
## Format Conversion Reference
### Supported Input Formats
- ODG (native), SVG, PDF
### Supported Output Formats
- ODG, SVG, PDF, PNG, JPG, GIF, BMP, WMF, EMF
## Command-Line Reference
```bash
soffice --headless
soffice --headless --convert-to <format> <file>
soffice --draw # Draw
```
## Python Libraries
```bash
pip install ezodf # ODF handling
pip install odfpy # ODF manipulation
pip install svgwrite # SVG generation
```
## Best Practices
1. Use layers for organization
2. Create templates for recurring diagrams
3. Use vector formats for scalability
4. Name objects for easy reference
5. Store ODG source files in version control
6. Test conversions thoroughly
7. Export to SVG for web use
## Troubleshooting
### Cannot open socket
```bash
killall soffice.bin
soffice --headless --accept="socket,host=localhost,port=8100;urp;"
```
### Quality Issues in PNG Export
```bash
soffice --headless --convert-to png:PNG_drawing_Export \
--filterData='{"Width":2048,"Height":2048}' drawing.odg
```
## Resources
- [LibreOffice Draw Guide](https://documentation.libreoffice.org/)
- [UNO API Reference](https://api.libreoffice.org/)
- [SVG Specification](https://www.w3.org/TR/SVG/)
## Related Skills
- writer
- calc
- impress
- base
- workflow-automationRelated Skills
zustand-store-ts
Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state/action separation. Use when building React state management, creating global stores, or implementing reacti...
zoom-automation
Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.
zoho-crm-automation
Automate Zoho CRM tasks via Rube MCP (Composio): create/update records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.
zod-validation-expert
Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.
zeroize-audit
Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C/C++/Rust code handling secrets, keys, passwords, or other sensitive data.
zendesk-automation
Automate Zendesk tasks via Rube MCP (Composio): tickets, users, organizations, replies. Always search tools first for current schemas.
zapier-make-patterns
No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity ...
youtube-summarizer
Extract transcripts from YouTube videos and generate comprehensive, detailed summaries using intelligent analysis frameworks
youtube-automation
Automate YouTube tasks via Rube MCP (Composio): upload videos, manage playlists, search content, get analytics, and handle comments. Always search tools first for current schemas.
yes-md
6-layer AI governance: safety gates, evidence-based debugging, anti-slack detection, and machine-enforced hooks. Makes AI safe, thorough, and honest.
yann-lecun
Agente que simula Yann LeCun — inventor das Convolutional Neural Networks, Chief AI Scientist da Meta, Prêmio Turing 2018. Use quando quiser: perspectivas sobre deep learning e visão...
yann-lecun-tecnico
Sub-skill técnica de Yann LeCun. Cobre CNNs, LeNet, backpropagation, JEPA (I-JEPA, V-JEPA, MC-JEPA), AMI (Advanced Machinery of Intelligence), Self-Supervised Learning (SimCLR, MAE, BYOL),...