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
wordpress-penetration-testing
This skill should be used when the user asks to "pentest WordPress sites", "scan WordPress for vulnerabilities", "enumerate WordPress users, themes, or plugins", "exploit WordPress vu...
php-pro
Write idiomatic PHP code with generators, iterators, SPL data structures, and modern OOP features. Use PROACTIVELY for high-performance PHP applications.
moodle-external-api-development
Create custom external web service APIs for Moodle LMS. Use when implementing web services for course management, user tracking, quiz operations, or custom plugin functionality. Covers parameter va...
laravel-expert
Senior Laravel Engineer role for production-grade, maintainable, and idiomatic Laravel solutions. Focuses on clean architecture, security, performance, and modern standards (Laravel 10/11+).
voice-ai-engine-development
Build real-time conversational AI voice engines using async worker pipelines, streaming transcription, LLM agents, and TTS synthesis with interrupt handling and multi-provider support
voice-ai-development
Expert in building voice AI applications - from real-time voice agents to voice-enabled apps. Covers OpenAI Realtime API, Vapi for voice agents, Deepgram for transcription, ElevenLabs for synthesis...
voice-agents
Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flo...
lex
Centralized 'Truth Engine' for cross-jurisdictional legal context (US, EU, CA) and contract scaffolding.
amazon-alexa
Integracao completa com Amazon Alexa para criar skills de voz inteligentes, transformar Alexa em assistente com Claude como cerebro (projeto Auri) e integrar com AWS ecosystem (Lambda, DynamoDB,...
wcag-audit-patterns
Conduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance. Use when auditing websites for accessibility, fixing WCAG violations, or implementing ac...
stitch-loop
Teaches agents to iteratively build websites using Stitch with an autonomous baton-passing loop pattern
product-design
Design de produto nivel Apple — sistemas visuais, UX flows, acessibilidade, linguagem visual proprietaria, design tokens, prototipagem e handoff. Cobre Figma, design systems, tipografia, cor,...